modelId
stringlengths 5
122
| author
stringlengths 2
42
| last_modified
unknown | downloads
int64 0
738M
| likes
int64 0
11k
| library_name
stringclasses 245
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 48
values | createdAt
unknown | card
stringlengths 1
901k
|
|---|---|---|---|---|---|---|---|---|---|
DopeorNope/love_but_hate-10.7B | DopeorNope | "2024-01-03T17:27:28Z" | 1,109 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-03T16:58:30Z" | # Please **Never use my model for merging!!!** |
LI-ST/Mistral-7B-ko-v0.002 | LI-ST | "2024-01-09T07:35:45Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"ko",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-08T10:20:42Z" | ---
license: cc-by-nc-nd-4.0
language:
- en
- ko
library_name: transformers
pipeline_tag: text-generation
---
<p><h1>Mistral-7B-ko</h1></p>
basemodel: Open-Orca/Mistral-7B-OpenOrca
=================================================
<BR>
This model is a temporary model for testing.
<BR>
We will be deleting it soon.
<BR>
================================================= |
Edentns/DataVortexS-10.7B-v0.1 | Edentns | "2024-02-24T14:18:49Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"ko",
"dataset:nlpai-lab/kullm-v2",
"base_model:hyeogi/SOLAR-10.7B-dpo-v0.1",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-10T12:03:23Z" | ---
tags:
- text-generation
license: cc-by-nc-sa-4.0
language:
- ko
base_model: hyeogi/SOLAR-10.7B-dpo-v0.1
pipeline_tag: text-generation
datasets:
- nlpai-lab/kullm-v2
---
# **DataVortexS-10.7B-v0.1**
<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;">
## Our Team
| Research & Engineering | Product Management |
| :--------------------: | :----------------: |
| Kwangseok Yang | Seunghyun Choi |
| Jeongwon Choi | Hyoseok Choi |
## **Model Details**
### **Base Model**
[hyeogi/SOLAR-10.7B-dpo-v0.1](https://huggingface.co/hyeogi/SOLAR-10.7B-dpo-v0.1)
### **Trained On**
- **OS**: Ubuntu 20.04
- **GPU**: H100 80GB 1ea
- **transformers**: v4.36.2
### **Dataset**
- [nlpai-lab/kullm-v2](https://huggingface.co/datasets/nlpai-lab/kullm-v2)
### **Instruction format**
It follows **Alpaca** format.
E.g.
```python
text = """\
๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค.
### Instruction:
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?
### Response:
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค.
### Instruction:
์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?
"""
```
## **Model Benchmark**
### **[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**
| Task | 0-shot | 5-shot | 10-shot | 50-shot |
| :--------------- | -------------: | -----------: | ------------: | -----------: |
| kobest_boolq | 0.334282 | 0.642861 | 0.691496 | 0.638754 |
| kobest_copa | 0.584962 | 0.564325 | 0.570654 | 0.581035 |
| kobest_hellaswag | 0.340022 | 0.339401 | 0.341917 | 0.337713 |
| kobest_sentineg | 0.328257 | 0.414905 | 0.464711 | 0.888914 |
| **Average** | **0.39688075** | **0.490373** | **0.5171945** | **0.611604** |
### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
| 35.39 | 28.48 | 39.79 | 35.98 | 44.72 | 27.63 |
## **Implementation Code**
This model contains the chat_template instruction format.
You can use the code below.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-v0.1")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-v0.1")
messages = [
{"role": "system", "content": "๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค."},
{"role": "user", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?"},
{"role": "assistant", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค."},
{"role": "user", "content": "์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## **License**
The model is licensed under the [cc-by-nc-sa-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license, which allows others to copy, modify, and share the work non-commercially, as long as they give appropriate credit and distribute any derivative works under the same license.
<div align="center">
<a href="https://edentns.com/">
<img src="./Logo.png" alt="Logo" style="height: 3em;">
</a>
</div>
|
etri-xainlp/llama2-12.8b_lora-dpo_v1 | etri-xainlp | "2024-01-17T02:22:50Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-17T01:58:46Z" | ---
license: apache-2.0
---
# etri-xainlp/llama2-12.8b_lora-dpo_v1
## Model Details
**Model Developers** ETRI xainlp team
**Input** text only.
**Output** text only.
**Model Architecture**
**Base Model** [meta-llama/Llama-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf)
**Training Dataset**
- sft+lora: 710k instruction-following set
- dpo+lora: 90k user preference set
- We use A100 GPU 80GB * 8, when training. |
TeamUNIVA/Komodo_6B_v1.0.0 | TeamUNIVA | "2024-03-04T09:25:34Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ko",
"en",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-30T10:39:06Z" | ---
license: apache-2.0
language:
- ko
- en
---
# Base Model
beomi/Yi-Ko-6B
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "TeamUNIVA/Komodo_6B_v1.0.0"
model = AutoModelForCausalLM.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
text = '''<|system|>
๋น์ ์ ์ฌ์ฉ์์ ์ง๋ฌธ์ ์น์ ํ๊ฒ ๋ต๋ณ์ ํ๋ ์ฑ๋ด์
๋๋ค.
<|user|>
์๋
ํ์ธ์?
<|bot|>
'''
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
jungyuko/DAVinCI-Yi-Ko-6B-v0.8 | jungyuko | "2024-01-31T08:57:58Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-31T08:13:40Z" | ---
license: cc-by-nc-4.0
---
## DAVinCI-Yi-Ko-6B-v0.8
This model is a fine-tuned version of [beomi/Yi-Ko-6B](https://huggingface.co/beomi/Yi-Ko-6B) on an unknown dataset.
### Model description
More information needed
### Intended uses & limitations
More information needed
### Training and evaluation data
More information needed
### Training procedure
### Training hypuerparameters
The following hyperparameters were used during training:
* learning_rate: 2e-05
* train_batch_size: 4
* eval_batch_size: 8
* seed: 42
* gradient_accumulation_steps: 8
* total_train_batch_size: 32
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr_scheduler_type: linear
* num_epochs: 1.0
* mixed_precision_training: Native AMP
### Training results
### Framework versions
* Transformers 4.36.2
* Pytorch 2.1.2+cu121
* Datasets 2.0.0
* Tokenizers 0.15.0 |
ITT-AF/ITT-42dot_LLM-PLM-1.3B-dpo-v1.0 | ITT-AF | "2024-02-14T06:31:32Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-03T13:23:29Z" | ---
license: cc-by-nc-4.0
---
# ITT-AF/ITT-42dot_LLM-PLM-1.3B-dpo-v1.0
This model is a fine-tuned version of [42dot/42dot_LLM-PLM-1.3B](https://huggingface.co/42dot/42dot_LLM-PLM-1.3B) on an custom dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 24
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.0.0
- Tokenizers 0.15.0 |
mu0gum/AIFT-42dot_LLM-PLM-1.3B-ao-instruct-all-v1.0 | mu0gum | "2024-02-14T06:28:03Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-13T16:05:06Z" | ---
license: cc-by-nc-4.0
---
# AIFT-42dot_LLM-PLM-1.3B-ao-instruct-all-v1.0
๋ฒ ์ด์ค ๋ชจ๋ธ : 42dot/42dot_LLM-PLM-1.3B
ํ์ต ๋ฐ์ดํฐ : ์์ฒด ์ ์ํ Open Orca ์คํ์ผ ๋ฐ์ดํฐ์
์ฝ 48,000๊ฑด (์ค๋ณต ์ ๊ฑฐ ๋ฐ ๋ฐ์ดํฐ ๋ถํฌ ์กฐ์ )
ํ์ต ๋ฐฉ๋ฒ : Full finetuning
epoch : 3
## ko-lm-evaluation-harness(5-shot)
|kobest_boolq|kobest_copa|kobest_hellaswag|pawsx_ko|
|--|--|--|--|
|0.5220797720797721|0.72|0.458|0.563|
## Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.0.0
- Tokenizers 0.15.0 |
JONGYUN/DPO_Test_2 | JONGYUN | "2024-03-05T23:44:19Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-21T04:03:49Z" | ---
license: apache-2.0
---
language:
- ko
pipeline_tag: text-generation
---
# Llama-2-7b-hf dpo test model
### Model Details
- Developed by: JongYun CHOI
- Backbone Model: yanolja/KoSOLAR-10.7B-v0.2
- Library: [transformers](https://github.com/huggingface/transformers)
-
### Used Datasets
- private dataset
### Prompt Template
```
### ์ง๋ฌธ: {Instruction}
### ๋ต๋ณ: {Answer}
```
|
ENERGY-DRINK-LOVE/eeve_dpo-v3 | ENERGY-DRINK-LOVE | "2024-03-07T02:54:50Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"dpo",
"generated_from_trainer",
"conversational",
"arxiv:2305.18290",
"base_model:yanolja/EEVE-Korean-Instruct-10.8B-v1.0",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-27T21:57:37Z" | ---
license: apache-2.0
tags:
- trl
- dpo
- generated_from_trainer
base_model: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# ENERGY-DRINK-LOVE/eeve_dpo-v3
### Our Team
* Jingyeom Kim
* Youjin Chung
## Model
### Base Model
* [yanolja/EEVE-Korean-Instruct-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0)
### Hardware and Software
* Hardware: A100 * 8 for training our model
* Deepspeed library & Huggingface TRL Trainer
### Dataset
* DPO_dataset
* ์์ฒด ์ ์ dpo dataset(AI-hub dataset ํ์ฉ)
* OpenOrca DPO ๋ฑ ์์ด ๋ฐ์ดํฐ์
๋ฒ์ญ(ENERGY-DRINK-LOVE/translate_share_gpt_dedup_llama_SFT_1024, ์์ฒด๋ชจ๋ธ ํ์ฉ)
### Training Method
* [DPO](https://arxiv.org/abs/2305.18290)
## Benchmark
**[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**
| Task | 0-shot | 5-shot |
| :--------------- | -----------: | -----------: |
| kobest_boolq | 0.950142 | 0.944444 |
| kobest_copa | 0.751 | 0.835 |
| kobest_hellaswag | 0.474 | 0.508 |
| kobest_sentineg | 0.811083 | 0.972292 |
| **Average** | **0.74655625** | **0.81493399** |
**[Ko-LLM-Leaderboard](https://www.aihub.or.kr/leaderboard/view.do?currMenu=500&topMenu=102)**
* (240307๊ธฐ์ค 7๋ฑ)
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
| 57.97 | 57.51 | 67.01 | 56.3 | 54.86 | 54.19 |
|
ITT-AF/ITT-Yi-Ko-6B-v5.0 | ITT-AF | "2024-02-29T09:48:33Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-29T08:21:02Z" | ---
license: cc-by-nc-4.0
---
## ITT-AF/ITT-Yi-Ko-6B-v5.0
This model is a fine-tuned version of [beomi/Yi-Ko-6B](https://huggingface.co/beomi/Yi-Ko-6B) on an custom dataset.
### Model description
More information needed
### Intended uses & limitations
More information needed
### Training and evaluation data
More information needed
### Training procedure
### Training hypuerparameters
The following hyperparameters were used during training:
* learning_rate: 2e-05
* train_batch_size: 4
* eval_batch_size: 8
* seed: 42
* gradient_accumulation_steps: 8
* total_train_batch_size: 32
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr_scheduler_type: linear
* num_epochs: 1.0
* mixed_precision_training: Native AMP
### Training results
### Framework versions
* Transformers 4.36.2
* Pytorch 2.1.2+cu121
* Datasets 2.0.0
* Tokenizers 0.15.0 |
hwkwon/S-SOLAR-10.7B-SFT-v1.2 | hwkwon | "2024-03-10T06:55:30Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ko",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-10T06:45:22Z" | ---
license: cc-by-nc-4.0
language:
- ko
---
# S-SOLAR-10.7B
<!-- Provide a quick summary of what the model is/does. -->
<!--This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).-->
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model is a fine-tuned version of [Edentns/DataVortexS-10.7B-dpo-v1.11](https://huggingface.co/Edentns/DataVortexS-10.7B-dpo-v1.11) with DeepSpeed.
### Trained Data
TBA
### Prompt Template
```
### User: User query input
### Assistant:
```
### License
This model is licensed under the cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.
|
hyeogi/SOLAR-10.7B-v1.4 | hyeogi | "2024-03-12T06:11:03Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"SOLAR-10.7B",
"conversational",
"ko",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-12T05:31:08Z" | ---
language:
- ko
pipeline_tag: text-generation
tags:
- SOLAR-10.7B
license: cc-by-nc-4.0
---
# SOLAR-10.7B
### Model Details
- Base Model: [yanolja/KoSOLAR-10.7B-v0.2](https://huggingface.co/yanolja/KoSOLAR-10.7B-v0.2)
### Datasets
- sampling and translate [Open-Orca/SlimOrca](https://huggingface.co/datasets/Open-Orca/SlimOrca)
- sampling and instrcution format [HAERAE-HUB/KMMLU](https://huggingface.co/datasets/HAERAE-HUB/KMMLU)
|
chahyunmook/42dot-test-upload | chahyunmook | "2024-03-25T04:32:45Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ko",
"arxiv:1910.09700",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-25T04:18:59Z" | ---
library_name: transformers
license: cc-by-4.0
language:
- ko
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
JY623/KoSOLRA-10.7B-merge-v2.2 | JY623 | "2024-04-04T10:48:23Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"base_model:JY623/KoSOLAR-10.7B-merge-v2.0",
"base_model:rrw-x2/KoSOLAR-10.7B-v2.1",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-04T10:18:27Z" | ---
base_model:
- JY623/KoSOLAR-10.7B-merge-v2.0
- rrw-x2/KoSOLAR-10.7B-v2.1
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# merge_base_ft_2
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [JY623/KoSOLAR-10.7B-merge-v2.0](https://huggingface.co/JY623/KoSOLAR-10.7B-merge-v2.0)
* [rrw-x2/KoSOLAR-10.7B-v2.1](https://huggingface.co/rrw-x2/KoSOLAR-10.7B-v2.1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: JY623/KoSOLAR-10.7B-merge-v2.0
layer_range: [0, 48]
- model: rrw-x2/KoSOLAR-10.7B-v2.1
layer_range: [0, 48]
merge_method: slerp
base_model: JY623/KoSOLAR-10.7B-merge-v2.0
parameters:
t: 0.2
dtype: bfloat16
``` |
sWizad/pokemon-trainer-sprite-pixelart | sWizad | "2024-04-17T01:06:06Z" | 1,109 | 37 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"migrated",
"pixel art",
"sprites",
"pixel",
"style",
"pokemon",
"game cg",
"video game art",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:other",
"region:us"
] | text-to-image | "2024-04-15T16:27:10Z" | ---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- pixel art
- sprites
- pixel
- style
- pokemon
- game cg
- video game art
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt:
widget:
- text: 'harley quinn, simple background'
output:
url: >-
9737393.jpeg
- text: 'a woman with blonde hair, wearing a white summer dress, simple background'
output:
url: >-
9737398.jpeg
- text: 'maleficent, evil fairy, simple background'
output:
url: >-
9737407.jpeg
- text: 'Daenerys Targaryen, Game of Thrones, simple background'
output:
url: >-
9737466.jpeg
- text: 'joker, simple background'
output:
url: >-
9737478.jpeg
- text: 'jack sparrow, pirates of caribbean '
output:
url: >-
9737508.jpeg
- text: 'iron man '
output:
url: >-
9737483.jpeg
- text: 'deadpool '
output:
url: >-
9737471.jpeg
- text: 'neo the matrix '
output:
url: >-
9737470.jpeg
- text: 'charlie chaplin '
output:
url: >-
9737472.jpeg
- text: 'Super Mario stepped on a turtle '
output:
url: >-
9737429.jpeg
- text: 'link of zelda, with a sword '
output:
url: >-
9737481.jpeg
- text: '1girl angel with 2 large angel wings and a halo, perfect curves, wearing a white dress, '
output:
url: >-
9737509.jpeg
- text: 'woman, beautiful kimono, sakura '
output:
url: >-
9737499.jpeg
- text: '1girl, glasses, witch, hat, blue flame '
output:
url: >-
9737502.jpeg
- text: '1girl, solo, hood, '
---
# Pokemon Trainer Sprite PixelArt
<Gallery />
([CivitAI](https://civitai.com/models/159333))
## Model description
<h1 id="heading-524">Pokรฉmon Trainer Sprite Generator</h1><p>LIKE THIS MODEL? GIVE A โค๏ธ</p><p>Trained on Pokรฉmon sprites of 96x96 and BLIP image captions.</p><h2 id="heading-525">Quick Tips</h2><ul><li><p><strong>No Trigger Word Needed:</strong> This model does not require a trigger word.</p></li><li><p><strong>Art Styles:</strong> You can use the tags <code>gen1</code> and <code>gen2</code> to generate different art styles.</p></li><li><p><strong>Trainer Recognition:</strong> The model can recognize some trainer names, such as Ash and Bruno.</p></li><li><p>This LoRA has been tested with Dreamshaper and RealisticVision, but I belive that it should work well with other models too.</p></li></ul><p></p><h3 id="heading-146">Model Versions</h3><p>This Pokรฉmon Trainer Sprite LoRA is available in two different versions: 768x768 and 512x512. Both models are trained on images upscaled from their original 96x96 size and are specifically designed to produce sprites at their respective resolutions. The choice between these two versions allows users to customize their experience based on their specific needs.</p><p></p><p>For the best results, we recommend using the 768x768 version. Set your desired resolution to 768x768, and then downscale the result 8 times to achieve a 96x96 sprite. This downscaling process can be performed using any image editing program, but for a smoother post-processing experience, we recommend using a plug-in available at (<a target="_blank" rel="ugc" href="https://github.com/mrreplicart/sd-webui-pixelart">https://github.com/mrreplicart/sd-webui-pixelart</a>).</p><p></p><p><span style="color:rgb(255, 255, 255)">Enjoy your Pokรฉmon Trainer sprite!</span></p><p></p><p></p>
## Download model
Weights for this model are available in Safetensors format.
[Download](/sWizad/pokemon-trainer-sprite-pixelart/tree/main) them in the Files & versions tab.
## Use it with the [๐งจ diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('sWizad/pokemon-trainer-sprite-pixelart', weight_name='pk_trainer_xl_v1.safetensors')
image = pipeline('1girl, solo, hood, simple background').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
|
EnumaInc/llama-8b-ko-slimorca-45000 | EnumaInc | "2024-04-25T14:58:07Z" | 1,109 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:beomi/Llama-3-Open-Ko-8B",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-25T09:04:12Z" | ---
license: other
base_model: beomi/Llama-3-Open-Ko-8B
tags:
- generated_from_trainer
model-index:
- name: out-llama-8b-ko-slimorca_45000
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.0`
```yaml
base_model: beomi/Llama-3-Open-Ko-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
# datasets:
# - path: /workspace/axolotl/datasets/mix_corpus_extended_validated_stage1.json
# type: completion
# field: text
# /workspace/axolotl/datasets/slimorca_20000.jsonl
datasets:
- path: /workspace/axolotl/datasets/slimorca_ko_45000.jsonl
type: sharegpt
conversation: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
eval_sample_packing: False
output_dir: ./out-llama-8b-ko-slimorca_45000
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 100
evals_per_epoch: 1
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
pad_token: <|end_of_text|>
```
</details><br>
# out-llama-8b-ko-slimorca_45000
This model is a fine-tuned version of [beomi/Llama-3-Open-Ko-8B](https://huggingface.co/beomi/Llama-3-Open-Ko-8B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8945
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.0058 | 0.99 | 102 | 0.8945 |
### Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
|
Nitral-AI/Poppy_Porpoise-0.72-L3-8B | Nitral-AI | "2024-06-22T18:45:09Z" | 1,109 | 20 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:Nitral-AI/PP_0.71b",
"base_model:Nitral-AI/PP_0.71a",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-02T00:39:25Z" | ---
base_model:
- Nitral-AI/PP_0.71b
- Nitral-AI/PP_0.71a
library_name: transformers
tags:
- mergekit
- merge
license: other
---
# "Poppy Porpoise" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences.
# Quants Available From Lewdiculus: https://huggingface.co/Lewdiculous/Poppy_Porpoise-0.72-L3-8B-GGUF-IQ-Imatrix
# Recomended ST Presets:(Updated for 0.72) [Porpoise Presets](https://huggingface.co/Nitral-AI/Poppy_Porpoise-0.72-L3-8B/tree/main/Poppy%200.72%20Presets%20(updated))
If you want to use vision functionality:
* You must use the latest versions of [Koboldcpp](https://github.com/LostRuins/koboldcpp).
# To use the multimodal capabilities of this model and use **vision** you need to load the specified **mmproj** file, this can be found inside this model repo. [Llava MMProj](https://huggingface.co/Nitral-AI/Llama-3-Update-3.0-mmproj-model-f16)
* You can load the **mmproj** by using the corresponding section in the interface:
 |
chlee10/T3Q-LLM3-Llama3-sft1.0 | chlee10 | "2024-05-02T06:05:12Z" | 1,109 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-02T05:36:54Z" | ---
library_name: transformers
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
NousResearch/Hermes-2-Theta-Llama-3-70B | NousResearch | "2024-06-20T20:00:04Z" | 1,109 | 53 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"distillation",
"synthetic data",
"function calling",
"structured outputs",
"json mode",
"conversational",
"en",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-06-14T10:49:31Z" | ---
license: llama3
language:
- en
pipeline_tag: text-generation
tags:
- distillation
- synthetic data
- function calling
- structured outputs
- json mode
---
# Hermes 2 Theta Llama-3 70B Model Card
## Model Description
Hermes-2 ฮ (Theta) 70B is the continuation of our experimental merged model released by [Nous Research](https://nousresearch.com/), in collaboration with Charles Goddard and [Arcee AI](https://www.arcee.ai/), the team behind [MergeKit](https://github.com/arcee-ai/mergekit).
Hermes-2 ฮ is a merged and then further RLHF'ed version our excellent Hermes 2 Pro model and Meta's Llama-3 Instruct model to form a new model, Hermes-2 ฮ, combining the best of both worlds of each model.
# Comparison to Llama-3 70B Instruct Model:
# Example Outputs
## System Prompt: Roleplay as an Anime Catgirl who's good at programming and a hacker.
## Providing Structured Outputs for Annotating LLM Training Data
## System Prompt: Roleplay as a bombastic alchemist from the 17th century in France. You are on a journey with the user to find the philosopher's stone.
# Prompt Format & Capabilities
Hermes 2 ฮ uses ChatML as the prompt format, opening up a very structured and steerable, multiturn system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where uniquely added tokens were added to denote the beginning and end of any turn, along with roles for the turns.
The model is also specifically trained for Function Calling, Structured Outputs with JSON, and Feature Extraction from RAG Documents (see below).
## Conversational Chats
Here is an example prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are a helpful, intelligent assistant AI named "Hermes", a conversational chatbot that can follow instructions, converse with the user, and perform a variety of tasks, including tasks on knowledge, reasoning, mathematics, and code. Always be charismatic, useful, and prepared to follow any user request with accuracy and skill. You should respond with high quality, fluent, and detailed responses. Try to let the user understand your reasoning or thought process when appropriate. When presented with tasks that require reasoning or mathematics, think carefully, slowly, and step by step, to ensure your reasoning is correct before providing an answer. Utilize the "Examples" section to assist you in performing the task. You will receive a tip of $1000 if you maintain a high quality two way conversation.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
## Function Calling Format
Our model was trained on specific system prompts and structures for Function Calling. While the system prompt looks complicated, we have created a GitHub repo containing code to easily build these based on real python functions.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
<tools>
{"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}}
</tools>
Use the following pydantic model json schema for each tool call you will make:
{"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"}
For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function.
See example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:
<schema>
{schema}
</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
# Benchmark Details
## GPT4All:
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.6638|_ |0.0138|
| | |acc_norm|0.6903|_ |0.0135|
|arc_easy | 0|acc |0.8851|_ |0.0065|
| | |acc_norm|0.8712|_ |0.0069|
|boolq | 1|acc |0.8820|_ |0.0056|
|hellaswag | 0|acc |0.6579|_ |0.0047|
| | |acc_norm|0.8432|_ |0.0036|
|openbookqa | 0|acc |0.3920|_ |0.0219|
| | |acc_norm|0.4740|_ |0.0224|
|piqa | 0|acc |0.8286|_ |0.0088|
| | |acc_norm|0.8351|_ |0.0087|
|winogrande | 0|acc |0.7893|_ |0.0115|
```
Average: 76.93
## AGIEval:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.4055|_ |0.0309|
| | |acc_norm|0.4094|_ |0.0309|
|agieval_logiqa_en | 0|acc |0.5100|_ |0.0196|
| | |acc_norm|0.5023|_ |0.0196|
|agieval_lsat_ar | 0|acc |0.2783|_ |0.0296|
| | |acc_norm|0.2957|_ |0.0302|
|agieval_lsat_lr | 0|acc |0.7451|_ |0.0193|
| | |acc_norm|0.7333|_ |0.0196|
|agieval_lsat_rc | 0|acc |0.8290|_ |0.0230|
| | |acc_norm|0.8104|_ |0.0239|
|agieval_sat_en | 0|acc |0.9029|_ |0.0207|
| | |acc_norm|0.9029|_ |0.0207|
|agieval_sat_en_without_passage| 0|acc |0.5825|_ |0.0344|
| | |acc_norm|0.5631|_ |0.0346|
|agieval_sat_math | 0|acc |0.6318|_ |0.0326|
| | |acc_norm|0.6227|_ |0.0328|
```
Average: 60.50
## BigBench:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.6737|_ |0.0341|
|bigbench_date_understanding | 0|multiple_choice_grade|0.7724|_ |0.0219|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3256|_ |0.0292|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.4763|_ |0.0264|
| | |exact_str_match |0.0000|_ |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.4720|_ |0.0223|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.3486|_ |0.0180|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.6367|_ |0.0278|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.5220|_ |0.0224|
|bigbench_navigate | 0|multiple_choice_grade|0.5930|_ |0.0155|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.8600|_ |0.0078|
|bigbench_ruin_names | 0|multiple_choice_grade|0.7411|_ |0.0207|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.5281|_ |0.0158|
|bigbench_snarks | 0|multiple_choice_grade|0.6961|_ |0.0343|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.5751|_ |0.0158|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.9880|_ |0.0034|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2296|_ |0.0119|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1691|_ |0.0090|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.6367|_ |0.0278|
```
Average: 56.91
## TruthfulQA:
```| Task |Version|Metric|Value | |Stderr|
|-------------|------:|------|-----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.4565|_ |0.0174|
| | |mc2 |0.6288|_ |0.0151|
```
62.88
## IFEval:
**87.99**
## MTBench:
First Turn - **9.1625**
Second Turn - **8.925**
Average - **9.04375**
# Inference Code
Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
```python
# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM
import bitsandbytes, flash_attn
tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Theta-Llama-3-70B', trust_remote_code=True)
model = LlamaForCausalLM.from_pretrained(
"NousResearch/Hermes-2-Theta-Llama-3-70B",
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
load_in_4bit=True,
use_flash_attention_2=True
)
prompts = [
"""<|im_start|>system
You are a helpful, intelligent assistant AI named "Hermes", a conversational chatbot that can follow instructions, converse with the user, and perform a variety of tasks, including tasks on knowledge, reasoning, mathematics, and code. Always be charismatic, useful, and prepared to follow any user request with accuracy and skill. You should respond with high quality, fluent, and detailed responses. Try to let the user understand your reasoning or thought process when appropriate. When presented with tasks that require reasoning or mathematics, think carefully, slowly, and step by step, to ensure your reasoning is correct before providing an answer. Utilize the "Examples" section to assist you in performing the task. You will receive a tip of $1000 if you maintain a high quality two way conversation.<|im_end|>
<|im_start|>user
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
<|im_start|>assistant""",
]
for chat in prompts:
print(chat)
input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")
```
## Inference Code for Function Calling:
All code for utilizing, parsing, and building function calling templates is available on our github:
[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
# Chat Interfaces
When quantized versions of the model are released, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
## Quantized Versions:
GGUF Versions Available Here: https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-70B-GGUF
# How to cite:
```bibtext
@misc{Hermes-2-Theta-Llama-3-70B,
url={[https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-70B][NousResearch/Hermes-2-Theta-Llama-3-70B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-70B))},
title={Hermes-2-Theta-Llama-3-70B},
author={"Teknium", Charles Goddard, "interstellarninja", "theemozilla", "karan4d", "huemin_art"}
}
```
|
NikolayKozloff/Viking-7B-Q4_K_M-GGUF | NikolayKozloff | "2024-06-29T19:01:23Z" | 1,109 | 1 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"fi",
"en",
"da",
"sv",
"no",
"nn",
"is",
"dataset:cerebras/SlimPajama-627B",
"dataset:bigcode/starcoderdata",
"dataset:mc4",
"base_model:LumiOpen/Viking-7B",
"license:apache-2.0",
"region:us"
] | null | "2024-06-29T19:01:02Z" | ---
base_model: LumiOpen/Viking-7B
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
- mc4
language:
- fi
- en
- da
- sv
- 'no'
- nn
- is
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# NikolayKozloff/Viking-7B-Q4_K_M-GGUF
This model was converted to GGUF format from [`LumiOpen/Viking-7B`](https://huggingface.co/LumiOpen/Viking-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/LumiOpen/Viking-7B) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo NikolayKozloff/Viking-7B-Q4_K_M-GGUF --hf-file viking-7b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo NikolayKozloff/Viking-7B-Q4_K_M-GGUF --hf-file viking-7b-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo NikolayKozloff/Viking-7B-Q4_K_M-GGUF --hf-file viking-7b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo NikolayKozloff/Viking-7B-Q4_K_M-GGUF --hf-file viking-7b-q4_k_m.gguf -c 2048
```
|
John6666/wai-c-v3-sdxl | John6666 | "2024-06-30T16:08:22Z" | 1,109 | 0 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"stable-diffusion-xl",
"anime",
"semi-realistic",
"pony",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2024-06-30T15:58:29Z" | ---
license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
tags:
- text-to-image
- stable-diffusion
- stable-diffusion-xl
- anime
- semi-realistic
- pony
---
Original model is [here](https://civitai.com/models/440170/wai-c?modelVersionId=609321).
|
chavinlo/alpaca-13b | chavinlo | "2023-05-09T02:14:39Z" | 1,108 | 108 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-03-31T05:05:43Z" | # Alpaca-native 13B
NO LORA |
jjzha/jobbert_skill_extraction | jjzha | "2023-10-26T10:25:11Z" | 1,108 | 9 | transformers | [
"transformers",
"pytorch",
"safetensors",
"bert",
"token-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | "2023-04-06T13:41:51Z" | This is a demo using the models from:
```
@inproceedings{zhang-etal-2022-skillspan,
title = "{S}kill{S}pan: Hard and Soft Skill Extraction from {E}nglish Job Postings",
author = "Zhang, Mike and
Jensen, Kristian and
Sonniks, Sif and
Plank, Barbara",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.366",
doi = "10.18653/v1/2022.naacl-main.366",
pages = "4962--4984",
abstract = "Skill Extraction (SE) is an important and widely-studied task useful to gain insights into labor market dynamics. However, there is a lacuna of datasets and annotation guidelines; available datasets are few and contain crowd-sourced labels on the span-level or labels from a predefined skill inventory. To address this gap, we introduce SKILLSPAN, a novel SE dataset consisting of 14.5K sentences and over 12.5K annotated spans. We release its respective guidelines created over three different sources annotated for hard and soft skills by domain experts. We introduce a BERT baseline (Devlin et al., 2019). To improve upon this baseline, we experiment with language models that are optimized for long spans (Joshi et al., 2020; Beltagy et al., 2020), continuous pre-training on the job posting domain (Han and Eisenstein, 2019; Gururangan et al., 2020), and multi-task learning (Caruana, 1997). Our results show that the domain-adapted models significantly outperform their non-adapted counterparts, and single-task outperforms multi-task learning.",
}
```
Note that there is another endpoint, namely `jjzha/jobbert_knowledge_extraction`.
Knowledge can be seen as hard skills and skills are both soft and applied skills. |
sambanovasystems/BLOOMChat-176B-v1 | sambanovasystems | "2023-05-19T20:34:37Z" | 1,108 | 367 | transformers | [
"transformers",
"pytorch",
"bloom",
"text-generation",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-10T21:17:39Z" | ---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
license: other
inference: false
---
# BLOOMChat V1.0
<!-- Provide a quick summary of what the model is/does. -->
BLOOMChat is a 176 billion parameter multilingual chat model. It is instruction tuned from [BLOOM (176B)](https://huggingface.co/bigscience/bloom) on assistant-style conversation datasets and supports conversation, question answering and generative answers in multiple languages.
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [SambaNova Systems](https://sambanova.ai/)
- **Co-developed by:** [Together Computer](https://www.together.xyz/)
- **Model type:** Language Model
- **Language(s):** Multiple; see [training data from BLOOM](https://huggingface.co/bigscience/bloom#training-data)
- **License:** BLOOMChat-176B LICENSE v1.0
- **Instruction Tuned from model:** [BigScience Group BLOOM](https://huggingface.co/bigscience/bloom)
### Basic Information
<!-- Provide the basic links for the model. -->
- **Blog Post**: [Link](https://sambanova.ai/blog/introducing-bloomchat-176b-the-multilingual-chat-based-llm/)
- **Discord**: [Link](https://discord.com/invite/8z2Pe7cpRv)
- **HF Hosting**: [Chat with me!](https://huggingface.co/spaces/sambanovasystems/BLOOMChat)
- **Github**: [Link](https://github.com/sambanova/bloomchat)
### Licensing
To increase accessibility and to support the open-source community, SambaNova is releasing BLOOMChat under a modified version of the Apache 2.0 license, which includes use-based restrictions from BLOOMโs RAIL license. While use-based restrictions are necessarily passed through, there are no blanket restrictions on reuse, distribution, commercialization or adaptation. [Please review SambaNovaโs BLOOMChat-176B License](LICENSE)
## Uses
<details>
<summary>Click to expand</summary>
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
This model is intended for commercial and research use.
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
BLOOMChat should NOT be used for:
- Mission-critical applications
- Applications that involve the safety of others
- Making highly important decisions
- Important automated pipelines
This model is still in early development and can be prone to mistakes and hallucinations, there is still room for improvement. This model is intended to provide the community with a multilingual chat LLM baseline.
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases, limitations, and restrictions of the model, which are listed down at the bottom of the page.
</details>
---
## How to Get Started with the Model
<details>
<summary>Click to expand</summary>
### Loading in model with Huggingface
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("sambanovasystems/BLOOMChat-176B-v1")
model = AutoModelForCausalLM.from_pretrained("sambanovasystems/BLOOMChat-176B-v1", device_map="auto", torch_dtype="auto")
```
### Quick Start Inference on SambaNova's in-house Reconfigurable Dataflow Unit (RDU)
The inference code to run the model can be found our [github repo](https://github.com/sambanova/bloomchat/blob/main/rdu_quick_start/inference.py). This code requires the [SambaFlow](https://docs.sambanova.ai/developer/latest/sambaflow-intro.html) SDK to execute. For those interested in running models on RDUs, [please feel free to get in touch](https://sambanova.ai/getstarted).
### Quick Start Inference on GPU
First create a python virtual environment for these packages
```
python3 -m venv bloomchat_venv
source bloomchat_venv/bin/activate
pip install --upgrade pip
```
<!-- Please follow this section [Inference solutions for BLOOM 176B](https://github.com/huggingface/transformers-bloom-inference#bloom-inference-via-command-line) in the Huggingface Tutorial for environment set up and stop before the [BLOOM inference via command-line
](https://github.com/huggingface/transformers-bloom-inference#bloom-inference-via-command-line) section. -->
```
pip install flask flask_api gunicorn pydantic accelerate huggingface_hub>=0.9.0 deepspeed>=0.7.3 deepspeed-mii==0.0.2
```
And then
```
pip install transformers==4.27.0
```
You will see messages like this
```
ERROR: deepspeed-mii 0.0.2 has requirement transformers==4.21.2, but you'll have transformers 4.27.0 which is incompatible.
Installing collected packages: transformers
Found existing installation: transformers 4.21.2
Uninstalling transformers-4.21.2:
Successfully uninstalled transformers-4.21.2
Successfully installed transformers-4.27.0
```
Now let's git clone the [huggingface/transformers-bloom-inference](https://github.com/huggingface/transformers-bloom-inference) repo.
```
git clone https://github.com/huggingface/transformers-bloom-inference.git
cd transformers-bloom-inference/
```
And then you need to modify two files in this [transformers-bloom-inference](https://github.com/huggingface/transformers-bloom-inference) repo:
- Modifying `inference_server/models/hf_accelerate.py`
- This is because for our testing of this repo we used 4 80GB A100 GPUs and would run into memory issues
- Modifying `inference_server/cli.py`
- This is because the model was trained using specific human, bot tags
- Trailing spaces may lead to subpar performance
Modifications for `inference_server/models/hf_accelerate.py`:
```diff
diff --git a/inference_server/models/hf_accelerate.py b/inference_server/models/hf_accelerate.py
index 9be3c3f..a8ecb1d 100644
--- a/inference_server/models/hf_accelerate.py
+++ b/inference_server/models/hf_accelerate.py
@@ -1,4 +1,5 @@
from argparse import Namespace
+from accelerate.utils.modeling import get_max_memory
import torch
@@ -12,6 +13,12 @@ class HFAccelerateModel(Model):
kwargs = {"pretrained_model_name_or_path": args.model_name, "device_map": "auto"}
+ original_max_memory_dict = get_max_memory()
+
+ reduce_max_memory_dict = {device_key: int(original_max_memory_dict[device_key] * 0.85) for device_key in original_max_memory_dict}
+
+ kwargs["max_memory"] = reduce_max_memory_dict
+
if get_world_size() > 1:
kwargs["device_map"] = "balanced_low_0"
```
Modifications for `inference_server/cli.py`:
```diff
diff --git a/inference_server/cli.py b/inference_server/cli.py
index fc903d5..5450236 100644
--- a/inference_server/cli.py
+++ b/inference_server/cli.py
@@ -22,6 +22,9 @@ def main() -> None:
while True:
input_text = input("Input text: ")
+ input_text = input_text.strip()
+ modified_input_text = f"<human>: {input_text}\n<bot>:"
+
if input("change generate_kwargs? [y/n] ") == "y":
while True:
try:
@@ -33,7 +36,7 @@ def main() -> None:
print("message =", e_message)
continue
- response = model.generate(text=[input_text], generate_kwargs=generate_kwargs)
+ response = model.generate(text=[modified_input_text], generate_kwargs=generate_kwargs)
print_rank_0("Output text:", response.text[0])
print_rank_0("Generated tokens:", response.num_generated_tokens[0])
```
And now you are good to go!
Running command for bf16, NO sampling
```
python -m inference_server.cli --model_name sambanovasystems/BLOOMChat-176B-v1 --model_class AutoModelForCausalLM --dtype bf16 --deployment_framework hf_accelerate --generate_kwargs '{"do_sample": false, "max_new_tokens": 512}'
```
Running command for bf16, YES sampling
```
python -m inference_server.cli --model_name sambanovasystems/BLOOMChat-176B-v1 --model_class AutoModelForCausalLM --dtype bf16 --deployment_framework hf_accelerate --generate_kwargs '{"do_sample": true, "temperature": 0.8, "repetition_penalty": 1.2, "top_p": 0.9, "max_new_tokens": 512}'
```
---
Running command for int8 (sub optimal performance, but fast inference time) NO sampling:
```
python -m inference_server.cli --model_name sambanovasystems/BLOOMChat-176B-v1 --model_class AutoModelForCausalLM --dtype int8 --deployment_framework hf_accelerate --generate_kwargs '{"do_sample": false, "max_new_tokens": 512}'
```
Running command for int8 (sub optimal performance, but fast inference time) YES sampling:
```
python -m inference_server.cli --model_name sambanovasystems/BLOOMChat-176B-v1 --model_class AutoModelForCausalLM --dtype int8 --deployment_framework hf_accelerate --generate_kwargs '{"do_sample": true, "temperature": 0.8, "repetition_penalty": 1.2, "top_p": 0.9, "max_new_tokens": 512}'
```
**DISCLAIMER:** When using int8, the results will be subpar compared to bf16 as the model is being [quantized](https://huggingface.co/blog/hf-bitsandbytes-integration#introduction-to-model-quantization).
### Suggested Inference Parameters
- Temperature: 0.8
- Repetition penalty: 1.2
- Top-p: 0.9
- Max generated tokens: 512
### Suggested Prompts To Try in GPU Tutorial
```
Input text: Write a script in which Bob accidentally breaks his dad's guitar
```
```
Input text: Create an itemized list of tasks to complete to start a clothing brand
```
```
Input text: ๅไธๅฒ็้ฃๆฏไปไน้ข่ฒ็?
```
</details>
---
## Some example completions for English
<details>
<summary>Click to expand</summary>
```
<human>: What does it mean for the Fed to raise or lower interest rates?
<bot>: The Federal Reserve (also known as the Fed) is the central banking system of the United States. It was created in 1913, and is an independent agency of the federal government. The Fed has a dual mandate of maximizing employment and stabilizing prices. The Fed sets interest rates, and can influence the money supply and the credit markets through its actions.
Raising interest rates means that the Fed is trying to reduce the money supply in the economy, and is trying to discourage borrowing and encourage saving. Lowering interest rates means that the Fed is trying to stimulate economic growth by encouraging borrowing and reducing the cost of credit.
The Fed raises or lowers interest rates in order to influence the economy and achieve its goals for employment and price stability. Interest rates are one of the primary tools that the Fed uses to achieve its goals.
```
```
<human>: Write an engaging and well-written property listing description for selling a house. Address of the house and some of the details are given to you. Fill in the information gap with hallucinations if needed.
Property Address: 412 Monterey Ave, Capitola, CA 95010
Parking: 3 cars + a finished single car garage
Details:
- open floorplan
- window with views to park/mountains
- Kitchen with shaker cabinetry and white Calcatta quartz counters
<bot>: This home at 412 Monterey Ave, Capitola, CA 95010 is the perfect place to call home. With its open floor plan, it provides the perfect space for entertaining guests. The kitchen is equipped with shaker cabinetry and white Calcatta quartz counters, providing the perfect space to create culinary masterpieces. The window with views to the park and mountains provide a beautiful view of the outdoors, making this home feel like a piece of paradise. The three-car garage and finished single car garage provide ample parking space, making this home a must-see for anyone looking for a new home.
```
```
<human>: What is artificial intelligence? Explain it so an 8 year old will understand.
<bot>: Artificial Intelligence (AI) is a computer program or machine that can do things that would normally require human intelligence, such as recognizing patterns, making decisions, and learning from experience. AI can be found in many places, such as self-driving cars, smartphones, and even robots. AI is used to make things easier for people, like when your smartphone can translate text into another language or when your voice-controlled speaker can play music for you.
AI works by using algorithms and big data to learn and improve over time. For example, self-driving cars use AI to analyze the environment around them and make decisions about how to drive. The car gathers data from its sensors, processes it using algorithms, and adjusts its behavior accordingly. This process is called machine learning.
AI is still a developing technology, and there are still many things that AI programs cannot do yet. However, as AI continues to evolve, it is likely that it will become more and more capable of performing tasks that were once thought to require human intelligence.
```
</details>
---
## Some example completions for Multilingual
<details>
<summary>Click to expand</summary>
#### Arabic
```
<human>: ูู ุงูุนู
ู ูุตู ุฏูุงู
ููุฑุฉ ุฌูุฏุฉ ูู
ุฑุงูููู ุจูู ุนู
ุฑ ูกูฅ ู ูกูฉ ุนุงู
<bot>: ูุนู
ุ ูู
ูู ุฃู ุชููู ููุฑุฉ ุฌูุฏุฉ ูุจุนุถ ุงูู
ุฑุงูููู ูู ูุฐุง ุงูุนู
ุฑ. ููุงู ุงูุนุฏูุฏ ู
ู ุงูููุงุฆุฏ ุงูุชู ูุฏ ูุญูููุง ุงูู
ุฑุงูููู ุฅุฐุง ุนู
ููุง ุจูุตู ุฏูุงู
:
- ูุณุงุนุฏูู
ุนูู ุชุนูู
ุงูู
ุณุคูููุฉ ูุฅุฏุงุฑุฉ ุงูููุช: ุนูุฏู
ุง ูุนู
ู ุงูู
ุฑุงูู ุจูุตู ุฏูุงู
ุ ูุฅูู ูุชุนูู
ููููุฉ ุฅุฏุงุฑุฉ ููุชู ุจุดูู ูุนุงู ูููููุฉ ุชูุณูู
ุณุงุนุงุช ุนู
ูู ุฅูู ู
ูุงู
ุฃุตุบุฑ.
- ูุญุณู ู
ูุงุฑุงุช ุงูุชูุงุตู ูุงูุนู
ู ุงูุฌู
ุงุนู: ุบุงูุจูุง ู
ุง ูููู ู
ูุงู ุงูุนู
ู ุจูุฆุฉ ู
ุชุนุฏุฏุฉ ุงูุซูุงูุงุช ุญูุซ ููุชูู ุงูู
ุฑุงูููู ุจู
ุฌู
ูุนุฉ ู
ุชููุนุฉ ู
ู ุงูุฃุดุฎุงุต ููุชุนูู
ูู ููููุฉ ุงูุชุนุงูู ู
ุนูู
ูุชุจุงุฏู ุงูุฃููุงุฑ.
- ูููุฑ ูุฑุตุฉ ููุชุนุฑู ุนูู ุนุงูู
ุงูุนู
ู: ูุชูุญ ุงูุนู
ู ููู
ุฑุงูู ุงูุชุนุฑู ุนูู ุนุงูู
ุงูุนู
ู ูุงูุชุณุงุจ ุฎุจุฑุฉ ุนู
ููุฉ ููู
ุฉ ุณุชุณุงุนุฏู ูุงุญููุง ุนูุฏ ุงูุจุญุซ ุนู ูุธููุฉ ุฃู ุจุฏุก ุญูุงุชู ุงูู
ูููุฉ.
- ูุนุฒุฒ ุงูุดุนูุฑ ุจุงูู
ุณุคูููุฉ ูุงูุซูุฉ ุจุงูููุณ: ุนูุฏู
ุง ูุนู
ู ุงูู
ุฑุงูู ุจูุตู ุฏูุงู
ููุญุตู ุนูู ุฏุฎู ุฎุงุต ุจูุ ูุฅูู ููุชุณุจ ุดุนูุฑูุง ุฃูุจุฑ ุจุงูู
ุณุคูููุฉ ูุงูุซูุฉ ุจุงูููุณ.
ูู
ุน ุฐููุ ูุง ููุจุบู ุฅุฌุจุงุฑ ุงูู
ุฑุงูููู ุนูู ุงูุนู
ู ุจูุตู ุฏูุงู
ุฏูู ู
ูุงููุชูู
ุงูู
ุณุจูุฉ. ูุฌุจ ุฃูุถูุง ู
ุฑุงุนุงุฉ ุฃุนู
ุงุฑูู
ููุฏุฑุงุชูู
ุงูุจุฏููุฉ ูุงูุนูููุฉ ูุจู ุชูุธูููู
.
```
**DISCLAIMER**: Text ordering may be off for Arabic due to code block not being able to render
#### Chinese
```
<human>: ่ฏทๅๆๆจ่ไธ้จๅจๆซ็็็ตๅฝฑๅนถ่ฏดๆๅๅ ใ
<bot>: โๅผบ็ๅๆจๆจ่ใ็พไธฝไบบ็ใ่ฟ้จๅฝฑ็ใ่ฏฅ็็ฑ็ฝไผฏๆยท่ดๅฐผๅฐผ่ชๅฏผ่ชๆผ๏ผ่ฎฒ่ฟฐไบไบๆๆถๆไธๅฏน็นๅคช็ถๅญ่ขซ้่ฟไบ็บณ็ฒน้ไธญ่ฅ๏ผ็ถไบฒ็จ่ชๅทฑ็ๆณ่ฑกๅไธบๅฟๅญ็ผ็ปไบไธไธช็พๅฅฝ็ซฅ็็ไธ็๏ผ่ฎฉๅฟๅญ็ๅฟ็ตๆฒกๆๅๅฐไธๆฏซไผคๅฎณ็ๆ
ไบใ
่ฏฅ็่ขซ่ชไธบโๆไผๅคง็ๆไบ็โใโไบบ็ฑปๆๅฒไปฅๆฅๆไฝณๅฝฑ็ไนไธโ๏ผ่ฑ็ฃ่ฏๅ้ซ่พพ9.6ๅใๅฎไธไป
ๆฏไธ้จๆไบบ็ไบฒๆ
็๏ผๆดๆฏไธ้จๅฏๅซๅฒ็็ๅฑๅฟ็ๅไบบ็ๅฏ็คบๅฝใ็ไธญ็ถไบฒ็ไน่ง่ฑ่พพใๅนฝ้ป้ฃ่ถฃ็ไบบ็ๆๅบฆ๏ผๅฏนไปปไฝไบ้ฝๆฑๆ็งฏๆ็ญๆ
็ๆๅบฆ๏ผๅณไฝฟๅจๆฎ้
ทๆ ๆฏ็้ไธญ่ฅ้ไนๆฏๅฆๆญค๏ผๆทฑๆทฑๅฐๆๆ็่งไผใๅๆถ๏ผ่ฟไนๆฏไธ้จๅ
ณไบ็ฑไธๅธๆ็็ตๅฝฑ๏ผ่ฎฉๆไปฌๆดๅ ็ๆๅฝไธๆๆฅๆ็ไธๅ๏ผๅญฆไผๅฆไฝๅป็ฑ่บซ่พน็ๆฏไธไธชไบบใ
ๆปไน๏ผ่ฟๆฏไธ้จๅผๅพไธ็ๅ็็ๅฅฝ็ตๅฝฑ๏ผ็ธไฟกๆจไธๅฎไผๅๆฌข็๏ผ
```
#### French
```
<human>: Il y a tโil un petit-dรฉjeuner de 700-1000 calories sans oeuf mais qui inclut des protรฉines.
<bot>: Oui, voici une recette de petit dรฉjeuner ร base d'avoine et de fromage blanc :
Ingrรฉdients :
- 1 tasse (250 ml) de lait d'amande ou autre lait vรฉgรฉtal
- 2 cuillรจres ร soupe bombรฉes (30 g) de flocons d'avoine
- 1/2 banane mรปre รฉcrasรฉe
- 1/4 de pomme fraรฎche รฉpluchรฉe et coupรฉe en dรฉs
- 1 cuillรจre ร soupe de beurre d'amande ou autre purรฉe d'olรฉagineux
- 1 cuillรจre ร cafรฉ de cannelle moulue
- 1 pincรฉe de sel
Prรฉparation :
1. Dans une petite casserole, faites chauffer le lait jusqu'ร ce qu'il soit chaud.
2. Ajoutez les flocons d'avoine, la banane, la pomme, le beurre d'amande, la cannelle et le sel dans le bol du mixeur et mรฉlangez bien pour obtenir une pรขte homogรจne.
3. Versez le mรฉlange dans le lait chaud et remuez rapidement avec une spatule en bois pour รฉviter que les flocons d'avoine ne s'agglutinent au fond de la casserole.
4. Laissez mijoter sur feu doux pendant environ 5 minutes tout en continuant de remuer rรฉguliรจrement.
5. Transfรฉrez ensuite le porridge dans un bol et servez immรฉdiatement. Vous pouvez ajouter quelques fruits rouges frais pour dรฉcorer et apporter encore plus de gourmandise ร votre petit dรฉjeuner ! Bon appรฉtit !
```
#### Hindi
```
<human>: เคฆเคฟเคฒเฅเคฒเฅ เคธเฅ เคเคฏเคชเฅเคฐ เคเฅเคธเฅ เคเคพเคฏเฅ? เคฌเคธ เคธเฅ เคฏเคพ เคเคพเคฐ เคธเฅ? เคฆเฅเคจเฅ เคเฅ เคฌเคพเคฐเฅ เคฎเฅ เคตเคฟเคธเฅเคคเคพเคฐ เคฎเฅ เคฌเคคเคพเคฏเฅ.
<bot>: เคฆเคฟเคฒเฅเคฒเฅ เคธเฅ เคเคฏเคชเฅเคฐ เคเคพเคจเฅ เคเคพ เคธเคฌเคธเฅ เคเคธเคพเคจ เคเคฐ เคคเฅเคเคผ เคคเคฐเฅเคเคพ เคนเฅ เคเคฟ เคเคช เค
เคชเคจเฅ เคเฅเคฆ เคเฅ เคเคพเคฐ เคฒเฅเคเคฐ เคเคพเคเค, เคเฅเคฏเฅเคเคเคฟ เคฏเคน เคเคชเคเฅ เค
เคชเคจเฅ เคธเคฎเคฏ เคชเคฐ เคจเคฟเคฐเฅเคญเคฐ เคฐเคนเคจเฅ เคเฅ เคธเฅเคตเคคเคเคคเฅเคฐเคคเคพ เคฆเฅเคคเคพ เคนเฅเฅค เคนเคพเคฒเคพเคเคเคฟ, เคฏเคฆเคฟ เคเคชเคเฅ เคชเคพเคธ เค
เคชเคจเฅ เคเคพเคฐ เคจเคนเฅเค เคนเฅ, เคคเฅ เคเคช เคฆเคฟเคฒเฅเคฒเฅ เคธเฅ เคเคฏเคชเฅเคฐ เคคเค เคเค เคจเคฟเคเฅ เคตเคพเคนเคจ เคเคฟเคฐเคพเค เคชเคฐ เคฒเฅ เคธเคเคคเฅ เคนเฅเคเฅค เคฏเคฆเคฟ เคเคช เคธเคพเคฐเฅเคตเคเคจเคฟเค เคชเคฐเคฟเคตเคนเคจ (เคฌเคธ) เคเคพ เคเคชเคฏเฅเค เคเคฐเคจเคพ เคเคพเคนเคคเฅ เคนเฅเค, เคคเฅ เคฆเคฟเคฒเฅเคฒเฅ เคฎเฅเค เคเค เคธเคฐเคเคพเคฐเฅ เคเคฐ เคจเคฟเคเฅ เคฌเคธ เคธเฅเคตเคพเคเค เคเคชเคฒเคฌเฅเคง เคนเฅเค เคเฅ เคเคฏเคชเฅเคฐ เคเฅ เคเฅเคกเคผเคคเฅ เคนเฅเคเฅค เคฆเคฟเคฒเฅเคฒเฅ เคธเฅ เคเคฏเคชเฅเคฐ เคเคพเคจเฅ เคตเคพเคฒเฅ เคเฅเค เคชเฅเคฐเคฎเฅเค เคฌเคธเฅเค เคนเฅเค-
1. เคฐเคพเคเคธเฅเคฅเคพเคจ เคฐเฅเคกเคตเฅเค: เคฏเฅ เคฐเคพเคเฅเคฏ เคธเคฐเคเคพเคฐ เคฆเฅเคตเคพเคฐเคพ เคธเคเคเคพเคฒเคฟเคค เคฌเคธเฅเค เคนเฅเค เคเฅ เคฆเคฟเคฒเฅเคฒเฅ เคธเฅ เคเคฏเคชเฅเคฐ เคเฅ เคฌเฅเค เคเคฒเคคเฅ เคนเฅเคเฅค เคฏเฅ เคจเคฟเคฏเคฎเคฟเคค เคฐเฅเคช เคธเฅ เคเคฒเคคเฅ เคนเฅเค เคเคฐ เคเคจเคเฅ เคฒเคฟเค เค
เคเฅเคฐเคฟเคฎ เคเคฐเคเฅเคทเคฃ เคเคตเคถเฅเคฏเค เคจเคนเฅเค เคนเฅเฅค
2. ALSA: เคฏเคน เคเค เคจเคฟเคเฅ เคเคเคชเคจเฅ เคนเฅ เคเฅ เคฆเคฟเคฒเฅเคฒเฅ เคธเฅ เคเคฏเคชเฅเคฐ เคเฅ เคฌเฅเค เคจเคฟเคฏเคฎเคฟเคค เคฐเฅเคช เคธเฅ เคเคฒเคคเฅ เคนเฅเฅค เคเคธเคเฅ เคเคฟเคเคเฅเค เคเฅ เคฌเฅเคเคฟเคเค เคเคจเคฒเคพเคเคจ เคเคฐ เคเคซเคฒเคพเคเคจ เคฆเฅเคจเฅเค เคฎเคพเคงเฅเคฏเคฎเฅเค เคธเฅ เคเฅ เคเคพ เคธเคเคคเฅ เคนเฅเฅค
3. RedBus: เคฏเคน เคเค เคเคจเคฒเคพเคเคจ เคฌเคธ เคฌเฅเคเคฟเคเค เคตเฅเคฌเคธเคพเคเค เคนเฅ เคเคนเคพเค เคธเฅ เคเคช เคฆเคฟเคฒเฅเคฒเฅ เคธเฅ เคเคฏเคชเฅเคฐ เคเฅ เคฌเฅเค เคเคฒเคจเฅเคตเคพเคฒเฅ เคตเคฟเคญเคฟเคจเฅเคจ เคเคเคชเคจเคฟเคฏเฅเค เคเฅ เคฌเคธเฅเค เคฎเฅเค เคธเฅเค เคเคฐเคเฅเคทเคฟเคค เคเคฐเคพ เคธเคเคคเฅ เคนเฅเคเฅค
4. Ola and Uber: เคเคจ เคเคชเฅเคธ เคเคพ เคเคชเคฏเฅเค เคเคฐเคเฅ เคเคช เคฆเคฟเคฒเฅเคฒเฅ เคธเฅ เคเคฏเคชเฅเคฐ เคคเค เคเฅเคฌ เคฐเคพเคเคก เคฌเฅเค เคเคฐ เคธเคเคคเฅ เคนเฅเค, เคฒเฅเคเคฟเคจ เคงเฅเคฏเคพเคจ เคฐเคเฅเค เคเคฟ เคฏเคน เคตเคฟเคเคฒเฅเคช เคธเคธเฅเคคเคพ เคจเคนเฅเค เคนเฅเคเคพเฅค เคฆเคฟเคฒเฅเคฒเฅ เคธเฅ เคเคฏเคชเฅเคฐ เคเคพเคจเฅ เคเคพ เคธเคฌเคธเฅ เค
เคเฅเคเคพ เคตเคฟเคเคฒเฅเคช เคเคชเคเฅ เคตเฅเคฏเคเฅเคคเคฟเคเคค เคเคตเคถเฅเคฏเคเคคเคพเคเค, เคฌเคเค, เคเคฐ เคเคชเคฒเคฌเฅเคงเคคเคพ เคชเคฐ เคจเคฟเคฐเฅเคญเคฐ เคเคฐเคคเคพ เคนเฅเฅค เคฏเคฆเคฟ เคเคช เค
เคชเคจเฅ เคเฅเคฆ เคเฅ เคเคพเคฐ เคฐเคเคคเฅ เคนเฅเค, เคคเฅ เคเคธเคเคพ เคฒเคพเคญ เคเค เคพเคเค เค
เคจเฅเคฏเคฅเคพ เคเคฟเคธเฅ เคญเฅ เคธเคพเคฐเฅเคตเคเคจเคฟเค เคชเคฐเคฟเคตเคนเคจ เคธเคพเคงเคจ เคเคพ เคเคฏเคจ เคเคฐเฅเค เคเฅ เคเคชเคเฅ เคเคตเคถเฅเคฏเคเคคเคพเคเค เคเฅ เคชเฅเคฐเคพ เคเคฐเฅเฅค
```
#### Spanish
```
<human>: ยฟMe puedes dar algunas recomendaciones de juegos? Estoy buscando juegos de rol con un sistema de magia รบnico, un sistema de construcciรณn รบnico y una buena historia. Por favor limรญtate a juegos que se puedan jugar en PC directamente, o por emulaciรณn.
<bot>: Claro! Aquรญ te dejo tres recomendaciones:
1. The Outer Worlds: es un juego de rol de ciencia ficciรณn con un sistema de magia basado en la tecnologรญa alienรญgena que permite al jugador personalizar sus habilidades para adaptarse a su estilo de juego.
2. Divinity: Original Sin 2 - Definitive Edition: este juego combina elementos de RPG con estrategia en tiempo real (RTS), lo que le da al jugador un control total sobre cรณmo construir y mejorar su personaje y el mundo que lo rodea.
3. Pillars of Eternity: esta aventura de fantasรญa oscura tiene lugar en un vasto mundo abierto donde los jugadores pueden elegir entre diferentes clases y desarrollar relaciones con otros personajes del juego. La mecรกnica de combate estรก basada en turnos y utiliza hechizos y armas cuerpo a cuerpo.
Estos son solo algunos ejemplos de juegos que podrรญan interesarte segรบn tus criterios. Hay muchos mรกs tรญtulos disponibles en el mercado que podrรญan ajustarse a tu gusto, asรญ que no dudes en explorar otras opciones si estos juegos no cumplen con tus expectativas.
```
</details>
---
## Evaluation Graphs
<details>
<summary>Click to expand</summary>
<!-- This section describes the evaluation protocols and provides the results. -->
<figure style="text-align:center;">
<figcaption><b>BLOOMChat vs Baselines Model in Human Preference Rankings</b></figcaption>
</figure>
<br>
<figure style="text-align:center;">
<figcaption><b>BLOOMChat vs GPT-4 in Human Preference Ranking</b></figcaption>
</figure>
<br>
<figure style="text-align:center;">
<figcaption><b>BLOOMChat surpasses other Bloom variants and state-of-the-art open-source chat models in translation tasks [NOTE: Evaluation of the BLOOM and BLOOMZ in WMT18 en->zh zh->en used (human, bot) ChatML tags due to an unintentional configuration. Results might be suboptimal.]</b></figcaption>
</figure>
<br>
</details>
---
## Training Details
<details>
<summary>Click to expand</summary>
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
- [OIG dataset from OpenChatKit](https://huggingface.co/datasets/laion/OIG)
- [Dolly 2.0](https://huggingface.co/datasets/databricks/databricks-dolly-15k)
- [Oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1)
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
We trained BLOOMChat with [SambaNova DataScale systems](https://sambanova.ai/products/datascale/) with SambaNova's in-house Reconfigurable Dataflow Unit (RDU). We started from [BLOOM (176B)](https://huggingface.co/bigscience/bloom), an open-source multilingual LLM pretrained by the [BigScience group](https://huggingface.co/bigscience). We instruction-tune BLOOM (176B) on OpenChatKit with each data source subsampled to 100k for one epoch, followed by three epochs over the combined OpenChatKit and Dolly 2.0.
All of the code used to prepare the datasets and the scripts to run training and inference are open-sourced and freely available at [sambanova/bloomchat](https://github.com/sambanova/bloomchat/tree/main)
### Prompting Style Used For Training
```
<human>: {input1 that the user wants from the bot}
<bot>: {response1}</s>
<human>: {input2 that the user wants from the bot}
<bot>: {response2}</s>
```
### Hyperparameters
**Instruction-tuned Training on OIG**
- Hardware: SambaNova Reconfigurable Dataflow Unit (RDU)
- Optimizer: AdamW
- Grad accumulation: 1
- Epochs: 1
- Global Batch size: 128
- Batch tokens: 128 * 2048 = 262,144 tokens
- Learning Rate: 1e-5
- Learning Rate Scheduler: Cosine Schedule with Warmup
- Warmup Steps: 0
- End Learning Ratio: 0.1
- Weight decay: 0.1
**Instruction-tuned Training on Dolly 2.0 and Oasst1**
- Hardware: SambaNova Reconfigurable Dataflow Unit (RDU)
- Optimizer: AdamW
- Grad accumulation: 1
- Epochs: 3
- Global Batch size: 128
- Batch tokens: 128 * 2048 = 262,144 tokens
- Learning Rate: 1e-5
- Learning Rate Scheduler: Cosine Schedule with Warmup
- Warmup Steps: 0
- End Learning Ratio: 0.1
- Weight decay: 0.1
</details>
---
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
Like all LLMs, BLOOMChat has certain limitations:
- Hallucination: BLOOMChat may sometimes generate responses that contain plausible-sounding but factually incorrect or irrelevant information.
- Code Switching: The model might unintentionally switch between languages or dialects within a single response, affecting the coherence and understandability of the output.
- Repetition: BLOOMChat may produce repetitive phrases or sentences, leading to less engaging and informative responses.
- Coding and Math: The model's performance in generating accurate code or solving complex mathematical problems may be limited.
- Toxicity: BLOOMChat may inadvertently generate responses containing inappropriate or harmful content.
## Acknowledgment
We would like to extend our gratitude to [Together](https://www.together.xyz/) for their insightful technical discussions on overall project planning, data processing, model training, human evaluation experiment design, open-source endeavors, and their contributions on data processing code on OpenChatKit, OASST1, and Dolly 2.0.
We are grateful to the various researchers and open-source projects that have contributed to the development of BLOOMChat. We thank [BigScience](https://bigscience.huggingface.co/) for providing the [BLOOM](https://huggingface.co/bigscience/bloom) model, which served as the base for our instruction tuning. We also thank [LAION](https://laion.ai/) for their [OIG dataset](https://huggingface.co/datasets/laion/OIG), OpenAssistant Conversations Dataset ([OASST1](https://huggingface.co/datasets/OpenAssistant/oasst1)) and also thank [Databricks](https://www.databricks.com/) for providing [Dolly 2.0](https://huggingface.co/datasets/databricks/databricks-dolly-15k), to provide the dataset that we instruction tuned on.
We appreciate [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness) and [BigScience](https://bigscience.huggingface.co/) for their essential benchmarking contributions, which is very helpful in evaluating BLOOMChat's performance. We appreciate the inspiration from the wave of various recent open-source chat models, including [OpenAssistant-30B](https://huggingface.co/OpenAssistant/oasst-sft-7-llama-30b-xor), [LLaMA-Adapter-V2-65B](https://github.com/ZrrSkywalker/LLaMA-Adapter/tree/main/llama_adapter_v2_chat65b), [Vicuna-13b](https://huggingface.co/lmsys/vicuna-13b-delta-v0), [Koala-13b](https://huggingface.co/TheBloke/koala-13B-HF), [OASST-Pythia-12b](https://huggingface.co/OpenAssistant/oasst-sft-1-pythia-12b), [Alpaca-13b](https://huggingface.co/anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g), [ChatGLM-6b](https://github.com/THUDM/ChatGLM-6B), [FastChat-T5-3b](https://huggingface.co/lmsys/fastchat-t5-3b-v1.0), [Dolly-v2-12b](https://huggingface.co/databricks/dolly-v2-12b), [LLaMA-13b](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/), [StableLM-Tuned-Alpha-7b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b), [RedPajama-INCITE-Chat-7B-v0.1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-7B-v0.1), [RedPajama-INCITE-Chat-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-7B-v0.1), [MPT-7B-Chat](https://huggingface.co/mosaicml/mpt-7b-chat) and so on. We look forward to witnessing the continued growth and success of open-source chat-based models.
We highly appreciate the hard work and dedication of these researchers and organizations towards the advancement of the open-source community. Their contributions were invaluable in the development of BLOOMChat, and we hope that our model can contribute to further advancements in the field.
## Cite BLOOMChat
```
@software{bloomchat,
title = {{BLOOMChat: a New Open Multilingual Chat LLM}},
author = {SambaNova Systems, Together Computer},
url = {https://huggingface.co/sambanovasystems/BLOOMChat-176B-v1}
month = {5},
year = {2023},
version = {1.0},
}
``` |
GAI-LLM/Yi-Ko-6B-dpo-v5 | GAI-LLM | "2024-01-08T05:06:18Z" | 1,108 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"ko",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-03T04:04:13Z" | ---
license: cc-by-nc-4.0
language:
- ko
library_name: transformers
pipeline_tag: text-generation
---
**The license is `cc-by-nc-4.0`.**
# **GAI-LLM/Yi-Ko-6B-dpo-v5**
## Model Details
**Model Developers** Donghoon Oh, Hanmin Myung, Eunyoung Kim (SK C&C G.AI Eng)
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture**
Yi-Ko-6B-dpo-v5 is an auto-regressive language model based on the LLaMA2 transformer architecture.
**Base Model** [beomi/Yi-Ko-6B](https://huggingface.co/beomi/Yi-Ko-6B)
**Training Dataset**
- We combined Open Korean Dateset using mixed-strategy with DPO.
- We use A100 GPU 80GB * 8, when training.
# **Model Benchmark**
## KO-LLM leaderboard
- Follow up as [Open KO-LLM LeaderBoard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard).
# Implementation Code
```python
### GAI-LLM/Yi-Ko-6B-dpo-v5
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "GAI-LLM/Yi-Ko-6B-dpo-v5"
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)
``` |
Edentns/DataVortexS-10.7B-v0.2 | Edentns | "2024-02-24T14:18:32Z" | 1,108 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"ko",
"dataset:beomi/KoAlpaca-v1.1a",
"dataset:Edentns/Worktronics-FAQ",
"base_model:hyeogi/SOLAR-10.7B-dpo-v0.1",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-04T15:35:36Z" | ---
tags:
- text-generation
license: cc-by-nc-sa-4.0
language:
- ko
base_model: hyeogi/SOLAR-10.7B-dpo-v0.1
pipeline_tag: text-generation
datasets:
- beomi/KoAlpaca-v1.1a
- Edentns/Worktronics-FAQ
---
# **DataVortexS-10.7B-v0.2**
<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;">
## Our Team
| Research & Engineering | Product Management |
| :--------------------: | :----------------: |
| Kwangseok Yang | Seunghyun Choi |
| Jeongwon Choi | Hyoseok Choi |
## **Model Details**
### **Base Model**
[hyeogi/SOLAR-10.7B-dpo-v0.1](https://huggingface.co/hyeogi/SOLAR-10.7B-dpo-v0.1)
### **Trained On**
- **OS**: Ubuntu 20.04
- **GPU**: H100 80GB 1ea
- **transformers**: v4.36.2
### **Dataset**
- [beomi/KoAlpaca-v1.1a](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a)
- Edentns/Worktronics-FAQ - private
### **Instruction format**
It follows **Alpaca** format.
E.g.
```python
text = """\
๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค.
### Instruction:
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?
### Response:
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค.
### Instruction:
์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?
"""
```
## **Model Benchmark**
### **[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**
| Task | 0-shot | 5-shot | 10-shot | 50-shot |
| :--------------- | ------------: | -------------: | -------------: | -------------: |
| kobest_boolq | 0.501449 | 0.668845 | 0.652565 | 0.655491 |
| kobest_copa | 0.635474 | 0.685637 | 0.708601 | 0.725683 |
| kobest_hellaswag | 0.417966 | 0.442942 | 0.428077 | 0.425199 |
| kobest_sentineg | 0.681941 | 0.880517 | 0.921754 | 0.939528 |
| **Average** | **0.5592075** | **0.66948525** | **0.67774925** | **0.68647525** |
### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
| 43.6 | 38.74 | 50.74 | 38.98 | 44.7 | 44.86 |
## **Implementation Code**
This model contains the chat_template instruction format.
You can use the code below.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-v0.2")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-v0.2")
messages = [
{"role": "system", "content": "๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค."},
{"role": "user", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?"},
{"role": "assistant", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค."},
{"role": "user", "content": "์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## **License**
The model is licensed under the [cc-by-nc-sa-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license, which allows others to copy, modify, and share the work non-commercially, as long as they give appropriate credit and distribute any derivative works under the same license.
<div align="center">
<a href="https://edentns.com/">
<img src="./Logo.png" alt="Logo" style="height: 3em;">
</a>
</div>
|
GAI-LLM/OPEN-SOLAR-KO-10.7B-dpo-dedup | GAI-LLM | "2024-01-31T07:57:08Z" | 1,108 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"ko",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-31T07:40:27Z" | ---
license: cc-by-nc-4.0
language:
- ko
library_name: transformers
pipeline_tag: text-generation
---
**The license is `cc-by-nc-4.0`.**
# **GAI-LLM/OPEN-SOLAR-KO-10.7B-dpo-dedup**
## Model Details
**Model Developers** Donghoon Oh, Hanmin Myung, Eunyoung Kim (SK C&C G.AI Eng)
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture**
GAI-LLM/OPEN-SOLAR-KO-10.7B-dpo-dedup is an auto-regressive language model based on the LLaMA2 transformer architecture.
**Base Model** [GAI-LLM/OPEN-SOLAR-KO-10.7B-mixed-v15-dedup](https://huggingface.co/GAI-LLM/OPEN-SOLAR-KO-10.7B-mixed-v15-dedup)
**Training Dataset**
- We combined Open Korean Dateset using mixed-strategy with DPO
- We use A100 GPU 80GB * 8, when training.
# **Model Benchmark**
## KO-LLM leaderboard
- Follow up as [Open KO-LLM LeaderBoard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard).
# Implementation Code
```python
### GAI-LLM/OPEN-SOLAR-KO-10.7B-dpo-dedup
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "GAI-LLM/OPEN-SOLAR-KO-10.7B-dpo-dedup"
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)
``` |
mu0gum/AIFT-42dot_LLM-PLM-1.3B-ao-instruct-all-v1.3 | mu0gum | "2024-02-28T13:58:50Z" | 1,108 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-28T13:46:39Z" | ---
license: cc-by-nc-4.0
---
# AIFT-42dot-LLM-PLM-1.3B-ao-instruct-all-v1.3
๋ฒ ์ด์ค ๋ชจ๋ธ : 42dot/42dot_LLM-PLM-1.3B
ํ์ต ๋ฐ์ดํฐ : ์์ฒด ์ ์ํ Open Orca ์คํ์ผ ๋ฐ์ดํฐ์
์ฝ 63,000๊ฑด (์ค๋ณต ์ ๊ฑฐ ๋ฐ ๋ฐ์ดํฐ ๋ถํฌ ์กฐ์ )
ํ์ต ๋ฐฉ๋ฒ : Full finetuning
epoch : 3
## ko-lm-evaluation-harness(5-shot)
|kobest_boolq|kobest_copa|kobest_hellaswag|pawsx_ko|
|--|--|--|--|
|0.522079772079772|0.722|0.47|0.557|
## Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.0.0
- Tokenizers 0.15.0 |
ENERGY-DRINK-LOVE/DataVortexS_dpov3 | ENERGY-DRINK-LOVE | "2024-03-16T08:22:35Z" | 1,108 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"dpo",
"generated_from_trainer",
"arxiv:2305.18290",
"base_model:Edentns/DataVortexS-10.7B-dpo-v1.11",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-11T09:26:21Z" | ---
license: cc-by-nc-4.0
base_model: Edentns/DataVortexS-10.7B-dpo-v1.11
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: nhn_dpo_v3_DataVortexS-10.7B-dpo-v1.11_DPO
results: []
---
# ENERGY-DRINK-LOVE/DataVortexS_dpov3
### Our Team
* Youjin Chung
* Jingyeom Kim
## Model
### Base Model
* [Edentns/DataVortexS-10.7B-dpo-v1.11](https://huggingface.co/Edentns/DataVortexS-10.7B-dpo-v1.11)
### Hardware and Software
* Hardware: A100 * 8 for training our model
* Deepspeed library & Huggingface TRL Trainer
### Dataset
* DPO_dataset
* ์์ฒด ์ ์ dpo dataset(AI-hub dataset ํ์ฉ)
* OpenOrca DPO ๋ฑ ์์ด ๋ฐ์ดํฐ์
๋ฒ์ญ(ENERGY-DRINK-LOVE/translate_share_gpt_dedup_llama_SFT_1024, ์์ฒด๋ชจ๋ธ ํ์ฉ)
### Training Method
* [DPO](https://arxiv.org/abs/2305.18290)
## Benchmark
**[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**
**[Ko-LLM-Leaderboard](https://www.aihub.or.kr/leaderboard/view.do?currMenu=500&topMenu=102)**
* (240316๊ธฐ์ค 7๋ฑ)
* 
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
| 60.18 | 56.23 | 69.15 | 52.76 | 67.87 | 54.9 |
|
kreimben/CodeMind-gemma-2b | kreimben | "2024-05-22T06:24:57Z" | 1,108 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"code",
"conversational",
"en",
"dataset:kreimben/leetcode_with_youtube_captions",
"dataset:kreimben/leetcode_user_submissions",
"base_model:google/gemma-1.1-2b-it",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-17T13:08:57Z" | ---
language:
- en
license: mit
library_name: transformers
tags:
- code
base_model:
- google/gemma-1.1-2b-it
datasets:
- kreimben/leetcode_with_youtube_captions
- kreimben/leetcode_user_submissions
widget:
- text: explain about two sum problem. from brute force approach to the most advanced
algorithms.
example_title: two sum example
- text: explain about leetcode 72 edit distance. i don't get even the approach.
example_title: edit distance example
- text: explain about leetcode 139 Word Break. please give me the approach.
example_title: word break example
inference:
parameters:
max_new_tokens: 250
temperature: 0.3
pipeline_tag: text-generation
---
# CodeMind
## ์๊ฐ
์ฝ๋ฉ ํ
์คํธ ๋ฌธ์ ํด๊ฒฐ ๋ฐ ํ์ต ๋ณด์กฐ๋ฅผ ์ง์ํด ์ฃผ๋ ์ธ์ด ๋ชจ๋ธ์
๋๋ค. Leetcode ํด์ค ์์ ์๋ง ๋ฐ ์ ์ ๋ค์ ํฌ์คํ
๊ธ์ ์ด์ฉํด ํ์ธํ๋ํ์ฌ ์ฝ๋ฉ ํ
์คํธ์ ์กฐ๊ธ ๋ ํนํ๋ ๋ต์์ ์ ์ํด ์ค ์ ์๊ฒ ํ์์ต๋๋ค.
## ๋ชจ๋ธ ์ธ๋ถ ์ ๋ณด
- **๋ชจ๋ธ ์ด๋ฆ**: CodeMind
- **๊ธฐ๋ณธ ๋ชจ๋ธ**: google/gemma-1.1-2b-it
- **ํ๋ จ ์ธ์ด**: ์์ด
- **๋ชจ๋ธ ํฌ๊ธฐ**: 2.51B ํ๋ผ๋ฏธํฐ
## ํ์ ๊ตฌ์ฑ
- NLP 3๋ช
- SRE 2๋ช
## ์ฃผ์ ๊ธฐ๋ฅ
- ๋ฌธ์ ์ ํ ๋ฐ ์ ๊ทผ๋ฒ ์ค๋ช
- ์ ๋ต ์ฝ๋ ์์ฑ
## ํ๋ จ ๋ฐ์ดํฐ
- [**LeetCode ์ฌ์ฉ์ ์ ์ถ๋ฌผ**](https://huggingface.co/datasets/kreimben/leetcode_user_submissions): ๋ค์ํ ์๊ณ ๋ฆฌ์ฆ ๋ฌธ์ ์ ํ์ด์ฌ ์๋ฃจ์
- [**์ ํ๋ธ ์บก์
**](https://huggingface.co/datasets/kreimben/leetcode_with_youtube_captions): LeetCode ๋ฌธ์ ์ ๋ํ ์ค๋ช
๋ฐ ๋จ๊ณ๋ณ ๊ฐ์ด๋
## ์ฌ์ฉ๋ ๋ผ์ด๋ธ๋ฌ๋ฆฌ
- [transformers](https://github.com/huggingface/transformers): ์์ฐ์ด ์ฒ๋ฆฌ ๋ชจ๋ธ์ ์ํ ๋ผ์ด๋ธ๋ฌ๋ฆฌ
- [datasets](https://github.com/huggingface/datasets): ๋ฐ์ดํฐ์
์ฒ๋ฆฌ ๋ฐ ๊ด๋ฆฌ ๋ผ์ด๋ธ๋ฌ๋ฆฌ
- [bitsandbytes](https://github.com/TimDettmers/bitsandbytes): ์ต์ ํ๋ ์ฐ์ฐ์ ์ํ ๋ผ์ด๋ธ๋ฌ๋ฆฌ
- [peft](https://github.com/huggingface/peft): ํ์ธ ํ๋์ ์ํ ๋ผ์ด๋ธ๋ฌ๋ฆฌ
- [trl](https://github.com/huggingface/trl): ์ธ์ด ๋ชจ๋ธ ํ๋์ ์ํ ๋ผ์ด๋ธ๋ฌ๋ฆฌ
- [pandas](https://github.com/pandas-dev/pandas): ๋ฐ์ดํฐ ์กฐ์์ ์ํ ๋ผ์ด๋ธ๋ฌ๋ฆฌ
## ํ์ผ ๊ตฌ์กฐ
- **dataset/**: ๋ฐ์ดํฐ์
ํ์ผ์ ํฌํจํฉ๋๋ค.
- **eval/**: ํ๊ฐ ์คํฌ๋ฆฝํธ๋ฅผ ํฌํจํฉ๋๋ค.
- **fine-tuning/**: fine tuning ๊ด๋ จ ๋
ธํธ๋ถ ๋ฐ ์คํฌ๋ฆฝํธ๋ฅผ ํฌํจํฉ๋๋ค.
- `gemma-1.1-2b-it peft qlora.ipynb`: fine tuning ๊ณผ์ ์ ๋ํ ์ธ๋ถ ์ฌํญ์ด ํฌํจ๋ ๋
ธํธ๋ถ์
๋๋ค.
- **demo.ipynb**: ๋ฐ๋ชจ ๋
ธํธ๋ถ์ผ๋ก ๋ชจ๋ธ ์ฌ์ฉ ์์ ๊ฐ ํฌํจ๋์ด ์์ต๋๋ค.
- **requirements.txt**: ํ๋ก์ ํธ ์์กด์ฑ ๋ชฉ๋ก์ด ํฌํจ๋์ด ์์ต๋๋ค.
- **utils.py**: ์ ํธ๋ฆฌํฐ ํจ์๋ค์ด ํฌํจ๋์ด ์์ต๋๋ค.
## ์ฌ์ฉ ๋ฐฉ๋ฒ
์ด ๋ชจ๋ธ์ HuggingFace์ ๋ชจ๋ธ ํ๋ธ๋ฅผ ํตํด ์ก์ธ์คํ ์ ์์ผ๋ฉฐ, API๋ฅผ ์ฌ์ฉํ์ฌ ์์ฉ ํ๋ก๊ทธ๋จ์ ํตํฉํ ์ ์์ต๋๋ค. ์ฝ๋ฉ ๋ฌธ์ ๋๋ ํ๋ก๊ทธ๋๋ฐ ๊ด๋ จ ์ง๋ฌธ์ ์ ๊ณตํ๋ฉด ๋ชจ๋ธ์ด ๊ด๋ จ ์ค๋ช
, ์ฝ๋ ์ค๋ํซ ๋๋ ๊ฐ์ด๋๋ฅผ ์์ฑํฉ๋๋ค.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("kreimben/CodeMind-gemma-2b")
model = AutoModelForCausalLM.from_pretrained("kreimben/CodeMind-gemma-2b")
inputs = tokenizer("์ฝ๋ฉ ๋ฌธ์ ๋ ์ง๋ฌธ์ ์ฌ๊ธฐ์ ์
๋ ฅํ์ธ์", return_tensors="pt")
outputs = model.generate(inputs.input_ids)
print(tokenizer.decode(outputs[0]))
```
## ํ๋ จ ๊ณผ์
### ๋ชจ๋ธ ๋ฐ ํ ํฌ๋์ด์ ๋ก๋
```python
import os
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16
)
model_id = 'google/gemma-1.1-2b-it'
token = os.getenv('HF_READ')
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"": 0}, token=token)
model.config.use_cache = False
model.gradient_checkpointing_enable()
tokenizer = AutoTokenizer.from_pretrained(model_id)
tokenizer.padding_side = 'right'
tokenizer.pad_token = tokenizer.eos_token
```
### LoRA ๊ตฌ์ฑ ๋ฐ ๋ชจ๋ธ ์ค๋น
```python
from peft import LoraConfig, get_peft_model, prepare_model_for_kbit_training
import bitsandbytes as bnb
model = prepare_model_for_kbit_training(model)
def find_all_linear_names(model):
cls = bnb.nn.Linear4bit
lora_module_names = set()
for name, module in model.named_modules():
if isinstance(module, cls):
names = name.split('.')
lora_module_names.add(names[0] if len(names) == 1 else names[-1])
if 'lm_head' in lora_module_names:
lora_module_names.remove('lm_head')
return list(lora_module_names)
modules = find_all_linear_names(model)
lora_config = LoraConfig(
r=64,
lora_alpha=32,
target_modules=modules,
lora_dropout=0.05,
bias="none",
task_type="CAUSAL_LM"
)
model = get_peft_model(model, lora_config)
```
### ๋ฐ์ดํฐ ์ค๋น
```python
import pandas as pd
from datasets import Dataset
submission_dataset = datasets.load_dataset('kreimben/leetcode_user_submissions_only_python', split='train').to_pandas()
submission_dataset = submission_dataset[['title', 'question_hints', 'question_content', 'content']]
captions_dataset = datasets.load_dataset('kreimben/leetcode_with_youtube_captions', split='train').to_pandas()
captions_dataset = captions_dataset[['title', 'question_hints', 'question_content', 'cc_content']]
captions_dataset.rename(columns={'cc_content': 'content'}, inplace=True)
dataset = pd.concat([submission_dataset, captions_dataset])
del submission_dataset, captions_dataset
dataset = Dataset.from_pandas(dataset)
GEMMA_2B_IT_MODEL_PREFIX_TEXT = "Below is an coding test problem. Solve the question."
def generate_prompt(data_point):
return f"<bos><start_of_turn>user {GEMMA_2B_IT_MODEL_PREFIX_TEXT}
I don't know {data_point['title']} problem. give me the insight or appoach.
this is problem's hint.
{data_point['question_hints']}
here are some content of question.
{data_point['question_content']}<end_of_turn>
<start_of_turn>model {data_point['content']}<end_of_turn><eos>"
text_column = [generate_prompt(data_point) for data_point in dataset]
dataset = dataset.add_column("prompt", text_column)
```
### ํ๋ จ
```python
from trl import SFTTrainer
import transformers
import torch
tokenizer.pad_token = tokenizer.eos_token
torch.cuda.empty_cache()
trainer = SFTTrainer(
model=model,
train_dataset=dataset,
dataset_text_field="prompt",
peft_config=lora_config,
data_collator=transformers.DataCollatorForLanguageModeling(tokenizer, mlm=False),
args=transformers.TrainingArguments(
output_dir='out',
bf16=True,
max_steps=100,
warmup_steps=50,
per_device_train_batch_size=1,
gradient_accumulation_steps=1,
optim="paged_adamw_8bit",
logging_steps=20,
report_to='wandb',
),
)
trainer.train()
```
## ํ๊ฐ
๋ชจ๋ธ์ ์ฑ๋ฅ์ ๋ค์๊ณผ ๊ฐ์ด ํ๊ฐ๋์์ต๋๋ค:
| Metric | Value |
|--------------|--------|
| Average | 41.62 |
| ARC | 41.81 |
| HellaSwag | 59.03 |
| MMLU | 37.26 |
| TruthfulQA | 43.45 |
| Winogrande | 59.91 |
| GSM8K | 8.26 |
## ์ ํ ์ฌํญ ๋ฐ ์ค๋ฆฌ์ ๊ณ ๋ ค์ฌํญ
- ๋ชจ๋ธ์ ์ถ๋ ฅ์ ํ์ต ๋ฐ์ดํฐ์ ๊ธฐ๋ฐํ๋ฏ๋ก ํญ์ ์ ํํ์ง ์์ ์ ์์ต๋๋ค.
- ์ค์ํ ๊ฒฐ์ ์ด๋ ์ค์ธ๊ณ ๋ฌธ์ ํด๊ฒฐ์ ๋ชจ๋ธ ์ถ๋ ฅ์ ์ฌ์ฉํ๊ธฐ ์ ์ ๋ฐ๋์ ๊ฒ์ฆ์ด ํ์ํฉ๋๋ค.
|
hwkwon/S-SOLAR-10.7B-SFT-v1.3 | hwkwon | "2024-03-18T04:04:40Z" | 1,108 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"ko",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-18T02:43:52Z" | ---
license: cc-by-nc-4.0
language:
- ko
---
# S-SOLAR-10.7B
<!-- Provide a quick summary of what the model is/does. -->
<!--This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).-->
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model is a fine-tuned version of [yanolja/EEVE-Korean-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0) with DeepSpeed.
### Trained Data
TBA
### Prompt Template
```
### User: User query input
### Assistant:
```
### License
This model is licensed under the cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.
|
gwonny/nox-solar-10.7b-v4-kolon-all-10 | gwonny | "2024-03-27T04:52:06Z" | 1,108 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"ko",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-21T06:15:04Z" | ---
license: cc-by-nc-4.0
language:
- ko
- en
---
## Base Model:
We made a LLM model with davidkim205/nox-solar-10.7b-v4
## Model Description
We use QLoRA(64, 16) and NEFTune on LLM Fine-tuning
lr = 2e-4
## Train Detail
Our private data used, and 10 epoch train
## Others
We are making LLM model for Kolon ! |
juengsi/DT-EQ-SOLAR-10.7B-v0.1 | juengsi | "2024-03-31T16:29:33Z" | 1,108 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ko",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-31T15:44:06Z" | ---
library_name: transformers
language:
- ko
license: cc-by-4.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
- None-Training Model with editing parameters
### Model Description
- Method : Parameters Space Merged
## Model Card Contact
[More Information Needed] |
juengsi/DT-SL-SOLAR-10.7B-v0.1 | juengsi | "2024-03-31T17:25:10Z" | 1,108 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ko",
"arxiv:1910.09700",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-31T16:11:10Z" | ---
library_name: transformers
license: cc-by-4.0
language:
- ko
pipeline_tag: text-generation
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
etri-xainlp/kor-llama2-13b-dpo | etri-xainlp | "2024-04-24T01:59:00Z" | 1,108 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-24T01:44:53Z" | ---
license: cc-by-nc-4.0
---
# etri-xainlp/kor-llama2-13b-dpo
## Model Details
**Model Developers** ETRI xainlp team
**Input** text only.
**Output** text only.
**Model Architecture**
**Base Model** [meta-llama/Llama-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf)
**Training Dataset**
- sft+lora: 1,821 k instruction-following set
- dpo+lora: 221 k user preference set
- We use A100 GPU 80GB * 8, when training. |
NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS | NeverSleep | "2024-05-21T20:37:21Z" | 1,108 | 39 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"not-for-all-audiences",
"nsfw",
"conversational",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-05T15:25:50Z" | ---
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- nsfw
---
## Lumimaid 0.1
<center><div style="width: 100%;">
<img src="https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/d3QMaxy3peFTpSlWdWF-k.png" style="display: block; margin: auto;">
</div></center>
This model uses the Llama3 **prompting format**
Llama3 trained on our RP datasets, we tried to have a balance between the ERP and the RP, not too horny, but just enough.
We also added some non-RP dataset, making the model less dumb overall. It should look like a 40%/60% ratio for Non-RP/RP+ERP data.
This model includes the new Luminae dataset from Ikari.
This model have received the Orthogonal Activation Steering treatment, meaning it will rarely refuse any request.
If you consider trying this model please give us some feedback either on the Community tab on hf or on our [Discord Server](https://discord.gg/MtCVRWTZXY).
## Credits:
- Undi
- IkariDev
## Description
This repo contains FP16 files of Lumimaid-8B-v0.1-OAS.
Switch: [8B](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1) - [70B](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-70B-v0.1) - [70B-alt](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-70B-v0.1-alt) - [8B-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS) - [70B-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-70B-v0.1-OAS)
## Training data used:
- [Aesir datasets](https://huggingface.co/MinervaAI)
- [NoRobots](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt)
- [limarp](https://huggingface.co/datasets/lemonilia/LimaRP) - 8k ctx
- [toxic-dpo-v0.1-sharegpt](https://huggingface.co/datasets/Undi95/toxic-dpo-v0.1-sharegpt)
- [ToxicQAFinal](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal)
- Luminae-i1 (70B/70B-alt) (i2 was not existing when the 70b started training) | Luminae-i2 (8B) (this one gave better results on the 8b) - Ikari's Dataset
- [Squish42/bluemoon-fandom-1-1-rp-cleaned](https://huggingface.co/datasets/Squish42/bluemoon-fandom-1-1-rp-cleaned) - 50% (randomly)
- [NobodyExistsOnTheInternet/PIPPAsharegptv2test](https://huggingface.co/datasets/NobodyExistsOnTheInternet/PIPPAsharegptv2test) - 5% (randomly)
- [cgato/SlimOrcaDedupCleaned](https://huggingface.co/datasets/cgato/SlimOrcaDedupCleaned) - 5% (randomly)
- Airoboros (reduced)
- [Capybara](https://huggingface.co/datasets/Undi95/Capybara-ShareGPT/) (reduced)
## Models used (only for 8B)
- Initial LumiMaid 8B Finetune
- Undi95/Llama-3-Unholy-8B-e4
- Undi95/Llama-3-LewdPlay-8B
## Prompt template: Llama3
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{output}<|eot_id|>
```
## Others
Undi: If you want to support us, you can [here](https://ko-fi.com/undiai).
IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek |
Alphacode-AI/AlphaMist7B-slr-v4-slow | Alphacode-AI | "2024-05-10T06:25:25Z" | 1,108 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"ko",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-10T02:16:33Z" | ---
license: cc-by-nc-4.0
language:
- ko
---
This model is a version of mistralai/Mistral-7B-v0.1 that has been fine-tuned with Our In House CustomData.
Train Spec : We utilized an A100x4 * 1 for training our model with DeepSpeed / HuggingFace TRL Trainer / HuggingFace Accelerate |
trl-internal-testing/tiny-random-idefics2 | trl-internal-testing | "2024-06-18T17:05:42Z" | 1,108 | 0 | transformers | [
"transformers",
"safetensors",
"idefics2",
"pretraining",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | "2024-06-18T16:20:20Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
```python
from transformers import Idefics2Config, AutoProcessor, MistralConfig, Idefics2ForConditionalGeneration
from transformers.models.idefics2.configuration_idefics2 import Idefics2VisionConfig
config = Idefics2Config(
text_config=MistralConfig(
max_position_embeddings=4096 * 8,
vocab_size=32003,
hidden_size=4 * 8,
num_attention_heads=8,
intermediate_size=16,
num_hidden_layers=2,
),
vision_config=Idefics2VisionConfig(
hidden_size=8 * 4,
num_attention_heads=4,
num_hidden_layers=2,
intermediate_size=16,
),
)
model = Idefics2ForConditionalGeneration(config=config)
processor = AutoProcessor.from_pretrained("HuggingFaceM4/idefics2-8b")
model.push_to_hub("trl-internal-testing/tiny-random-idefics2")
processor.push_to_hub("trl-internal-testing/tiny-random-idefics2")
```
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Felladrin/gguf-Qwen2-0.5B-Instruct-llamafy | Felladrin | "2024-06-27T12:07:07Z" | 1,108 | 0 | null | [
"gguf",
"base_model:Minami-su/Qwen2-0.5B-Instruct-llamafy",
"license:apache-2.0",
"region:us"
] | null | "2024-06-27T11:42:24Z" | ---
license: apache-2.0
base_model: Minami-su/Qwen2-0.5B-Instruct-llamafy
---
GGUF version of [Minami-su/Qwen2-0.5B-Instruct-llamafy](https://huggingface.co/Minami-su/Qwen2-0.5B-Instruct-llamafy).
|
Q-bert/Zeus-13B-v1-arithmetic | Q-bert | "2023-10-16T18:55:05Z" | 1,107 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-14T08:21:02Z" | ---
license: llama2
---
|
NeverSleep/Noromaid-20b-v0.1.1 | NeverSleep | "2023-11-21T17:23:58Z" | 1,107 | 39 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-16T02:53:53Z" | ---
license: cc-by-nc-4.0
---
---
# Disclaimer:
## This is a ***TEST*** version, don't expect everything to work!!!
You may use our custom **prompting format**(scroll down to download them!), or simple alpaca. **(Choose which fits best for you!)**
---
# This model is a collab between [IkariDev](https://huggingface.co/IkariDev) and [Undi](https://huggingface.co/Undi95)!
Tired of the same merges everytime? Here it is, the Noromaid-20b-v0.1.1 model. Suitable for RP, ERP and general stuff.
[Recommended settings - No settings yet(Please suggest some over in the Community tab!)]
<!-- description start -->
## Description
<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
This repo contains fp16 files of Noromaid-20b-v0.1.1.
[FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-20b-v0.1.1)
<!-- [GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GGUF)-->
<!-- [GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GPTQ)-->
<!-- [exl2[8bpw-8h] - by AzureBlack](https://huggingface.co/AzureBlack/Echidna-13b-v0.3-8bpw-8h-exl2)-->
<!-- [AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-AWQ)-->
<!-- [fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v4)-->
[GGUF - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-20b-v0.1.1-GGUF)
<!-- [OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v4-GGUF)-->
## Ratings:
Note: We have permission of all users to upload their ratings, we DONT screenshot random reviews without asking if we can put them here!
No ratings yet!
If you want your rating to be here, send us a message over on DC and we'll put up a screenshot of it here. DC name is "ikaridev" and "undi".
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Custom format, or Alpaca
### Custom format:
UPDATED!! SillyTavern config files: [Context](https://files.catbox.moe/ifmhai.json), [Instruct](https://files.catbox.moe/ttw1l9.json).
OLD SillyTavern config files: [Context](https://files.catbox.moe/x85uy1.json), [Instruct](https://files.catbox.moe/ttw1l9.json).
### Alpaca:
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
## Training data used:
- [no_robots dataset](https://huggingface.co/Undi95/Llama2-13B-no_robots-alpaca-lora) let the model have more human behavior, enhances the output.
- [Aesir Private RP dataset] New data from a new and never used before dataset, add fresh data, no LimaRP spam, this is 100% new. Thanks to the [MinvervaAI Team](https://huggingface.co/MinervaAI) and, in particular, [Gryphe](https://huggingface.co/Gryphe) for letting us use it!
## Others
Undi: If you want to support me, you can [here](https://ko-fi.com/undiai).
IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek |
HwiyeolJo/testtt | HwiyeolJo | "2024-01-03T16:43:55Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-03T16:30:03Z" | Entry not found |
hyeogi/SOLAR-10.7B-dpo-v1 | hyeogi | "2024-01-10T00:35:05Z" | 1,107 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"SOLAR-10.7B",
"ko",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-09T23:58:13Z" | ---
language:
- ko
pipeline_tag: text-generation
tags:
- SOLAR-10.7B
license: apache-2.0
---
# SOLAR-10.7B
### Model Details
- Base Model: [beomi/OPEN-SOLAR-KO-10.7B](https://huggingface.co/beomi/OPEN-SOLAR-KO-10.7B)
### Datasets
- sampling and translate [Open-Orca/SlimOrca](https://huggingface.co/datasets/Open-Orca/SlimOrca)
- sampling and translate [Anthropic/hh-rlhf](https://huggingface.co/datasets/Anthropic/hh-rlhf)
### Benchmark |
GAI-LLM/Yi-Ko-6B-mixed-v15 | GAI-LLM | "2024-01-18T12:26:29Z" | 1,107 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-18T02:12:21Z" | ---
license: cc-by-nc-4.0
pipeline_tag: text-generation
---
**The license is `cc-by-nc-4.0`.**
# **GAI-LLM/Yi-Ko-6B-mixed-v15**
## Model Details
**Model Developers** Donghoon Oh, Hanmin Myung, Eunyoung Kim (SK C&C G.AI Eng)
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture**
GAI-LLM/Yi-Ko-6B-mixed-v15 is an auto-regressive language model based on the LLaMA2 transformer architecture.
**Base Model** [beomi/Yi-Ko-6B]
**Training Dataset**
- We combined Open Korean Dateset using mixed-strategy
- We use A100 GPU 80GB * 8, when training.
# **Model Benchmark**
## KO-LLM leaderboard
- Follow up as [Open KO-LLM LeaderBoard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard).
# Implementation Code
```python
### GAI-LLM/Yi-Ko-6B-mixed-v15
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "GAI-LLM/Yi-Ko-6B-mixed-v15"
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)
``` |
cocoirun/AIFT-42dot-PLM-1.3B-ao-instruct-all-v0.4-ff-e1 | cocoirun | "2024-01-19T01:36:35Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:42dot/42dot_LLM-PLM-1.3B",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-19T01:29:44Z" | ---
license: cc-by-nc-4.0
base_model: 42dot/42dot_LLM-PLM-1.3B
tags:
- generated_from_trainer
model-index:
- name: AIFT-42dot_LLM-PLM-1.3B-ao-instruct-all-v0.4-merge-ff-e1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# AIFT-42dot_LLM-PLM-1.3B-ao-instruct-all-v0.4-merge-ff-e1
This model is a fine-tuned version of [42dot/42dot_LLM-PLM-1.3B](https://huggingface.co/42dot/42dot_LLM-PLM-1.3B) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 24
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.0.0
- Tokenizers 0.15.0
|
cocoirun/AIFT-ko-orca-plat-Yi-ko-6b-v1.0 | cocoirun | "2024-01-19T12:18:02Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-19T11:52:40Z" | ---
license: cc-by-sa-4.0
---
<h1>orca-platypus - instruct ๋ชจ๋ธ v1.0</h1>
<b><ํ์ต ๋ฐ์ดํฐ ๊ตฌ์ถ></b>
kyujinpy ๋์ด ๊ณต๊ฐํ์ KOR-OpenOrca-Platypus ๋ฐ์ดํฐ๋ฅผ ์ผ๋ถ ์ญ์ (์ํ๋ง) ๋ฐ ์ ์ ์์
์งํํ์ฌ ํ์ฉ.
๊ทธ ์ดํ ํด๋น ๋ฐ์ดํฐ๋ค์ ๋ณด๋ฉฐ ๊ด๋ จ ํ์คํฌ๋ฅผ ์ถ์ถํ์๊ณ ์ด๋ฅผ ๊ธฐ๋ฐ์ผ๋ก
ํด๋น ํ์คํฌ์ ๋ง์ถฐ์ NLP ๊ด๋ จ ์คํ์์ค ๋ฐ์ดํฐ๋ฅผ ํ์ฉํ์ฌ ํ์ต๋ฐ์ดํฐ๋ฅผ ์์ฒด์ ์ผ๋ก
์ญ์ฌ, ๊ณผํ, ์ํ, ๊ธฐ๊ณ๋
ํด, ๋ฆฌ๋ทฐ ๋ถ์ ๋ฌธ์ ๋ฅผ gpt๋ฅผ ํตํด์ ๊ตฌ์ถํ์๊ณ ,
aihub ์ผ๋ฐ์์ ๋ฐ ๊ธฐ๊ณ๋
ํด ๋ฐ์ดํฐ๋ฅผ ํ์ฉํ์ฌ ์ถ๊ฐ๋ก ํ์ต ๋ฐ์ดํฐ๋ฅผ ๊ตฌ์ถ(ํํ์ ๊ด๋ จ, ๊ธฐ๊ณ๋
ํด ๊ด๋ จ ๋ฐ ์์ฝ)
๊ฐ์ข
๋ธ๋ก๊ทธ์์ ์ญ์ฌ ๋ฐ ์์ ํด์ฆ๋ฅผ ์ฌ๋์ด ์ง์ ํ์ต๋ฐ์ดํฐ ํํ๋ก ๋ณ๊ฒฝ
AI2AI Challenge ๋ฐ์ดํฐ ํํ๋ฅผ ๋ณด๊ณ gpt๋ฅผ ํตํด ์ด๋ฑ ์์ค์ ๊ณผํ ์ํ ๋ฌธ์ ์ ํ์ ์ ์ 500๋ฌธ์
์์ด ๋ฒ์ญ ๋ฐ์ดํฐ ์ํ/ํ์ ๋ฐ์ดํฐ ํ์ต ๋ฐ์ดํฐ๋ก ํ์ฉ ์งํ
์ด ๋ฐ์ดํฐ 4๋ง๊ฐ ์ ๋ ์ฌ์ฉํ์์ต๋๋ค.
<br>
<br>
+ TruthfulQA ๊ด๋ จ ๋ฌธ์ ์ถ๊ฐ๋ฅผ ์งํํ์์ต๋๋ค.(์์ค ๊ด๋ จ ์ฐธ๊ฑฐ์ง ๋ฌธ์ )
+ ๊ธฐ๊ณ๋
ํด ๊ด๋ จ ํ์ต ๋ฐ์ดํฐ๋ฅผ ChatGPT๋ฅผ ํตํด์ ๋ต๋ณ์ ์ป์ด ํ์ต
+ ๋ฌธ๋ฒ๊ด๋ จ ํ์ต ๋ฐ์ดํฐ
<br>
###ํ์ต ๋ฐ์ดํฐ ํ์ผ์ ๋น๊ณต๊ฐ์
๋๋ค.
<br>
<b><ํ์ต></b>
ํ์ต์ LoRA๋ฅผ ์ฌ์ฉํ์ฌ A100 40G *2์์ ํ์ต์ ์งํํ์์ต๋๋ค. |
heavytail/kullm-mistral | heavytail | "2024-01-28T11:40:06Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"ko",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-28T09:03:43Z" | ---
license: apache-2.0
language:
- ko
---
# KULLM project
- base model: mistralai/Mistral-7B-Instruct-v0.2
## datasets
- KULLM dataset
- hand-crafted instruction data
## Implementation Code
```python
from transformers import (
AutoModelForCausalLM,
AutoTokenizer
)
import torch
repo = "heavytail/kullm-mistral"
model = AutoModelForCausalLM.from_pretrained(
repo,
torch_dtype=torch.float16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)
```
Initial upload: 2024/01/28 20:30 |
Edentns/DataVortexS-10.7B-dpo-v1.9 | Edentns | "2024-02-24T18:56:59Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"ko",
"base_model:beomi/OPEN-SOLAR-KO-10.7B",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-30T00:07:45Z" | ---
tags:
- text-generation
license: cc-by-nc-4.0
language:
- ko
base_model: beomi/OPEN-SOLAR-KO-10.7B
pipeline_tag: text-generation
---
# **DataVortexS-10.7B-dpo-v1.9**
<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;">
## Our Team
| Research & Engineering | Product Management |
| :--------------------: | :----------------: |
| Kwangseok Yang | Seunghyun Choi |
| Jeongwon Choi | Hyoseok Choi |
## **Model Details**
### **Base Model**
[beomi/OPEN-SOLAR-KO-10.7B](https://huggingface.co/beomi/OPEN-SOLAR-KO-10.7B)
### **Trained On**
- **OS**: Ubuntu 22.04
- **GPU**: H100 80GB 4ea
- **transformers**: v4.36.2
### **Instruction format**
It follows **Alpaca (Chat)** format.
E.g.
```python
text = """\
### System:
๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค.
### User:
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?
### Assistant:
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค.
### User:
์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?
"""
```
## **Model Benchmark**
### **[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**
| Task | 0-shot | 5-shot | 10-shot | 50-shot |
| :--------------- | -----------: | -----------: | -----------: | -----------: |
| kobest_boolq | 0.902418 | 0.904502 | 0.91804 | 0.915893 |
| kobest_copa | 0.815462 | 0.853789 | 0.855721 | 0.866903 |
| kobest_hellaswag | 0.49901 | 0.488796 | 0.484538 | 0.498009 |
| kobest_sentineg | 0.335008 | 0.977325 | 0.979839 | 0.982364 |
| **Average** | **0.637974** | **0.806103** | **0.809534** | **0.815792** |
### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
| 55.19 | 53.33 | 62.57 | 49.55 | 49.01 | 61.51 |
## **Implementation Code**
This model contains the chat_template instruction format.
You can use the code below.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.9")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.9")
messages = [
{"role": "system", "content": "๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค."},
{"role": "user", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?"},
{"role": "assistant", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค."},
{"role": "user", "content": "์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## **License**
This model is licensed under the [cc-by-nc-4.0](https://creativecommons.org/licenses/by-nc/4.0/). which allows others to share and adapt the model for non-commercial purposes.
<div align="center">
<a href="https://edentns.com/">
<img src="./Logo.png" alt="Logo" style="height: 3em;">
</a>
</div>
|
knlp/KS-SOLAR-10.7B-v0.1 | knlp | "2024-02-14T08:12:16Z" | 1,107 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:kyujinpy/Open-platypus-Commercial",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-05T05:16:59Z" | ---
license: cc-by-4.0
datasets:
- kyujinpy/Open-platypus-Commercial
language:
- en
---
**Model Details**
Model Developers: *SeungJin Lee (knlpscience)*
Base Model: *upstage/SOLAR-10.7B-v1.0*
**Notice**
***hyper params I***
-batch_size : 16
-num_epochs : 1
-micro_batch : 1
-gradient_accumulation_steps : batch_size // micro_batch
***hyper params II***
-cutoff_len : 4096
-lr_scheduler : 'cosine'
-warmup_ratio : 0.06
-learning_rate : 4e-4
-optimizer : 'adamw_torch'
-weight_decay : 0.01
-max_grad_norm : 1.0
***LoRA config***
-lora_r : 64
-lora_alpha : 16
-lora_dropout : 0.05
-lora_target_modules : ["gate_proj", "down_proj", "up_proj"] |
artificialguybr/doodle-redmond-doodle-hand-drawing-style-lora-for-sd-xl | artificialguybr | "2024-02-12T22:45:06Z" | 1,107 | 12 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"drawing",
"style",
"doodle",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:other",
"region:us"
] | text-to-image | "2024-02-12T22:44:59Z" | ---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Rent&allowDerivatives=True&allowDifferentLicense=False
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- drawing
- style
- doodle
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: doodle
widget:
- text: 'A drawing of
husky dog,
, doodle, DoodleRedm
, '
output:
url: >-
6569345.jpeg
- text: 'A drawing of
Pennywise,
, doodle, DoodleRedm
, '
output:
url: >-
6569335.jpeg
- text: 'A drawing of
Shrek,
, doodle, DoodleRedm
, '
output:
url: >-
6569336.jpeg
- text: 'A drawing of
cat wearing sunglasses,
, doodle, DoodleRedm
, '
output:
url: >-
6569337.jpeg
- text: 'A drawing of
A ghost,
, doodle, DoodleRedm
, '
output:
url: >-
6569334.jpeg
- text: 'A drawing of
A owl,
, doodle, DoodleRedm
, '
output:
url: >-
6569340.jpeg
- text: 'A drawing of
A angry police officer,
, doodle, DoodleRedm
, '
output:
url: >-
6569342.jpeg
- text: 'A drawing of
Starbucks coffe cup,
, doodle, DoodleRedm
, '
output:
url: >-
6569341.jpeg
- text: 'A drawing of
alien spaceship,
, doodle, DoodleRedm
, '
output:
url: >-
6569343.jpeg
- text: 'A drawing of
alien, caricature,
, doodle, DoodleRedm
, '
output:
url: >-
6569346.jpeg
---
# Doodle.Redmond - Doodle Hand drawing Style Lora for SD XL
<Gallery />
## Model description
<h1 id="heading-28">Doodle.Redmond is here!</h1><p>I'm grateful for the GPU time from <strong>Redmond.AI</strong> that allowed me to finish this LORA!</p><p>Want to test and have acess to all my AI Stuff? Check my <a target="_blank" rel="ugc" href="https://artificialguy.com/">website</a>!</p><p>This is a <strong>Doodle </strong>LORA fine-tuned on <strong>SD XL 1.0.</strong></p><p>Test all my Loras <a target="_blank" rel="ugc" href="https://huggingface.co/spaces/artificialguybr/artificialguybr-demo-lora">here</a> for free and unlimited. Thanks, HF, for Inference API!</p><p>The LORA has a high capacity to generate Doodle Style in a wide variety of themes.<strong> It's a versatile LORA.</strong></p><p><strong><u>The tag for the model: Doodle, DoodleRedm</u></strong></p><p>I really hope you like the LORA and use it.</p><p>If you like the model and think it's worth it, you can make a donation to my <a target="_blank" rel="ugc" href="https://www.patreon.com/user?u=81570187">Patreon</a> or <a target="_blank" rel="ugc" href="https://ko-fi.com/jvkape">Ko-fi</a>.</p><p>Follow me in my twitter to know before all about new models:</p><p><a target="_blank" rel="ugc" href="https://twitter.com/artificialguybr/"><u>https://twitter.com/artificialguybr/</u></a></p>
## Trigger words
You should use `doodle`, `doodleredm` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/artificialguybr/doodle-redmond-doodle-hand-drawing-style-lora-for-sd-xl/tree/main) them in the Files & versions tab.
## Use it with the [๐งจ diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('artificialguybr/doodle-redmond-doodle-hand-drawing-style-lora-for-sd-xl', weight_name='DoodleRedmond-Doodle-DoodleRedm.safetensors')
image = pipeline('A drawing of
alien, caricature,
, doodle, DoodleRedm
, ').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
|
ENERGY-DRINK-LOVE/leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT | ENERGY-DRINK-LOVE | "2024-03-04T12:33:42Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"generated_from_trainer",
"conversational",
"dataset:generator",
"base_model:LDCC/LDCC-SOLAR-10.7B",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-04T09:01:15Z" | ---
license: cc-by-nc-4.0
base_model: LDCC/LDCC-SOLAR-10.7B
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# leaderboard_inst_v1_LDCC-SOLAR-10.7B_SFT
This model is a fine-tuned version of [LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B) on the generator dataset.
* dataset: leaderboard dataset 1.3 + open-Hermes dataset(ko-mt)
### Framework versions
- Transformers 4.38.1
- Pytorch 2.2.1+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2
|
hwkwon/S-SOLAR-10.7B-v1.1 | hwkwon | "2024-03-06T08:50:16Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"ko",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-06T08:34:50Z" | ---
license: cc-by-nc-4.0
language:
- ko
---
# S-SOLAR-10.7B
<!-- Provide a quick summary of what the model is/does. -->
<!--This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).-->
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model is a fine-tuned version of [yanolja/EEVE-Korean-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0).
### Trained Data
TBA
### Prompt Template
```
### User: User query input
### Assistant:
```
### License
This model is licensed under the cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.
|
Saxo/yunsung-llama-2-koen-13b-linkbricks-sft-basic-v1 | Saxo | "2024-04-23T06:31:04Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"ko",
"en",
"dataset:Saxo/total_ko_train_set_small_basic",
"dataset:beomi/KoAlpaca-v1.1a",
"dataset:kyujinpy/KOR-OpenOrca-Platypus-v2",
"dataset:nlpai-lab/databricks-dolly-15k-ko",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-12T03:19:54Z" | ---
library_name: transformers
license: apache-2.0
basemodel: beomi/llama-2-koen-13b
datasets:
- Saxo/total_ko_train_set_small_basic
- beomi/KoAlpaca-v1.1a
- kyujinpy/KOR-OpenOrca-Platypus-v2
- nlpai-lab/databricks-dolly-15k-ko
language:
- ko
- en
pipeline_tag: text-generation
---
# Model Card for Model ID
<div align="center">
<img src="https://www.linkbricks.com/wp-content/uploads/2022/03/%E1%84%85%E1%85%B5%E1%86%BC%E1%84%8F%E1%85%B3%E1%84%87%E1%85%B3%E1%84%85%E1%85%B5%E1%86%A8%E1%84%89%E1%85%B3%E1%84%85%E1%85%A9%E1%84%80%E1%85%A9-2-1024x804.png" />
</div>
AI ์ ๋น
๋ฐ์ดํฐ ๋ถ์ ์ ๋ฌธ ๊ธฐ์
์ธ Linkbricks์ ๋ฐ์ดํฐ์ฌ์ด์ธํฐ์คํธ์ธ ์ง์ค์ฑ ๋ฐ์ฌ(Saxo)๊ฐ beomi/llama-2-koen-13b ๋ฒ ์ด์ค๋ชจ๋ธ์ GCP์์ A100-40G 4๊ฐ๋ฅผ ํตํด SFT ํ๋ จ์ ํ(2048 Tokens) ์ธ์คํธ๋ญ์
๋ชจ๋ธ.
Accelerate, Deepspeed Zero-3 ๋ผ์ด๋ธ๋ฌ๋ฆฌ๋ฅผ ์ฌ์ฉํ์ผ๋ฉฐ Flash Attention ์ Disable ๋ก ์ค์
Dr. Yunsung Ji (Saxo), a data scientist at Linkbricks, a company specializing in AI and big data analytics, trained the beomi/llama-2-koen-13b base model on 4 A100-40Gs on GCP for 4 hours of instructional training (2048 Tokens).
Accelerate, Deepspeed Zero-3 libraries were used.
www.linkbricks.com, www.linkbricks.vc
## Configuration including BitsandBytes
---
learning_rate = 2e-4
num_epochs = 5
batch_size = 4
block_size = 2048
trainer = "sft"
warmup_ratio = 0.1
weight_decay = 0.01
gradient_accumulation = 4
mixed_precision = "fp16"
peft = True
quantization = "int4"
lora_r = 64
lora_alpha = 16
lora_dropout = 0.1
model_max_length = 2048
---
## Dataset Format
Alpaca Format Prompt Text |
gwonny/nox-solar-10.7b-v4-kolon-all-5 | gwonny | "2024-03-27T04:46:02Z" | 1,107 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"ko",
"en",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-21T02:05:18Z" | ---
license: cc-by-nc-4.0
language:
- ko
- en
---
## Base Model:
We made a LLM model with davidkim205/nox-solar-10.7b-v4
## Model Description
We use QLOR(64, 16) and NEFTune on LLM Fine-tuning
lr = 2e-4,
## Train Detail
Our private data used, and 5 epoch train
## Others
We are making LLM model for Kolon ! |
gemmathon/gemma-2b-ko-dev-pbc432 | gemmathon | "2024-03-25T07:55:48Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"arxiv:1910.09700",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-25T07:51:35Z" | ---
license: other
library_name: transformers
license_name: gemma-terms-of-use
license_link: https://ai.google.dev/gemma/terms
pipeline_tag: text-generation
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
JY623/KoSOLAR-10.7B-merge-v2.0 | JY623 | "2024-04-03T09:00:10Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"base_model:krevas/SOLAR-10.7B",
"base_model:chihoonlee10/T3Q-ko-solar-sft-dpo-v1.0",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-03T08:47:44Z" | ---
base_model:
- krevas/SOLAR-10.7B
- chihoonlee10/T3Q-ko-solar-sft-dpo-v1.0
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# slerp_output_model
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [krevas/SOLAR-10.7B](https://huggingface.co/krevas/SOLAR-10.7B)
* [chihoonlee10/T3Q-ko-solar-sft-dpo-v1.0](https://huggingface.co/chihoonlee10/T3Q-ko-solar-sft-dpo-v1.0)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: krevas/SOLAR-10.7B
layer_range: [0, 48]
- model: chihoonlee10/T3Q-ko-solar-sft-dpo-v1.0
layer_range: [0, 48]
merge_method: slerp
base_model: krevas/SOLAR-10.7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16
``` |
metterian/gemma-pro-ko-10b | metterian | "2024-04-19T07:13:27Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"arxiv:1910.09700",
"license:afl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-14T12:31:18Z" | ---
library_name: transformers
license: afl-3.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
ibbb/LLama-3-tryModel | ibbb | "2024-07-02T07:54:03Z" | 1,107 | 0 | transformers | [
"transformers",
"safetensors",
"gguf",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-06-18T11:37:24Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Fulcrum-AI/Ryze-Q4_K_M-GGUF | Fulcrum-AI | "2024-06-26T07:52:46Z" | 1,107 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:Fulcrum-AI/Ryze",
"license:apache-2.0",
"region:us"
] | null | "2024-06-26T07:50:10Z" | ---
base_model: Fulcrum-AI/Ryze
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# Fulcrum-AI/Ryze-Q4_K_M-GGUF
This model was converted to GGUF format from [`Fulcrum-AI/Ryze`](https://huggingface.co/Fulcrum-AI/Ryze) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Fulcrum-AI/Ryze) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Fulcrum-AI/Ryze-Q4_K_M-GGUF --hf-file ryze-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Fulcrum-AI/Ryze-Q4_K_M-GGUF --hf-file ryze-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Fulcrum-AI/Ryze-Q4_K_M-GGUF --hf-file ryze-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Fulcrum-AI/Ryze-Q4_K_M-GGUF --hf-file ryze-q4_k_m.gguf -c 2048
```
|
flair/upos-multi-fast | flair | "2021-03-02T22:22:55Z" | 1,106 | 4 | flair | [
"flair",
"pytorch",
"token-classification",
"sequence-tagger-model",
"en",
"de",
"fr",
"it",
"nl",
"pl",
"es",
"sv",
"da",
"no",
"fi",
"cs",
"dataset:ontonotes",
"region:us"
] | token-classification | "2022-03-02T23:29:05Z" | ---
tags:
- flair
- token-classification
- sequence-tagger-model
language:
- en
- de
- fr
- it
- nl
- pl
- es
- sv
- da
- no
- fi
- cs
datasets:
- ontonotes
widget:
- text: "Ich liebe Berlin, as they say."
---
## Multilingual Universal Part-of-Speech Tagging in Flair (fast model)
This is the fast multilingual universal part-of-speech tagging model that ships with [Flair](https://github.com/flairNLP/flair/).
F1-Score: **92,88** (12 UD Treebanks covering English, German, French, Italian, Dutch, Polish, Spanish, Swedish, Danish, Norwegian, Finnish and Czech)
Predicts universal POS tags:
| **tag** | **meaning** |
|---------------------------------|-----------|
|ADJ | adjective |
| ADP | adposition |
| ADV | adverb |
| AUX | auxiliary |
| CCONJ | coordinating conjunction |
| DET | determiner |
| INTJ | interjection |
| NOUN | noun |
| NUM | numeral |
| PART | particle |
| PRON | pronoun |
| PROPN | proper noun |
| PUNCT | punctuation |
| SCONJ | subordinating conjunction |
| SYM | symbol |
| VERB | verb |
| X | other |
Based on [Flair embeddings](https://www.aclweb.org/anthology/C18-1139/) and LSTM-CRF.
---
### Demo: How to use in Flair
Requires: **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`)
```python
from flair.data import Sentence
from flair.models import SequenceTagger
# load tagger
tagger = SequenceTagger.load("flair/upos-multi-fast")
# make example sentence
sentence = Sentence("Ich liebe Berlin, as they say. ")
# predict NER tags
tagger.predict(sentence)
# print sentence
print(sentence)
# print predicted NER spans
print('The following NER tags are found:')
# iterate over entities and print
for entity in sentence.get_spans('pos'):
print(entity)
```
This yields the following output:
```
Span [1]: "Ich" [โ Labels: PRON (0.9999)]
Span [2]: "liebe" [โ Labels: VERB (0.9999)]
Span [3]: "Berlin" [โ Labels: PROPN (0.9997)]
Span [4]: "," [โ Labels: PUNCT (1.0)]
Span [5]: "as" [โ Labels: SCONJ (0.9991)]
Span [6]: "they" [โ Labels: PRON (0.9998)]
Span [7]: "say" [โ Labels: VERB (0.9998)]
Span [8]: "." [โ Labels: PUNCT (1.0)]
```
So, the words "*Ich*" and "*they*" are labeled as **pronouns** (PRON), while "*liebe*" and "*say*" are labeled as **verbs** (VERB) in the multilingual sentence "*Ich liebe Berlin, as they say*".
---
### Training: Script to train this model
The following Flair script was used to train this model:
```python
from flair.data import MultiCorpus
from flair.datasets import UD_ENGLISH, UD_GERMAN, UD_FRENCH, UD_ITALIAN, UD_POLISH, UD_DUTCH, UD_CZECH, \
UD_DANISH, UD_SPANISH, UD_SWEDISH, UD_NORWEGIAN, UD_FINNISH
from flair.embeddings import StackedEmbeddings, FlairEmbeddings
# 1. make a multi corpus consisting of 12 UD treebanks (in_memory=False here because this corpus becomes large)
corpus = MultiCorpus([
UD_ENGLISH(in_memory=False),
UD_GERMAN(in_memory=False),
UD_DUTCH(in_memory=False),
UD_FRENCH(in_memory=False),
UD_ITALIAN(in_memory=False),
UD_SPANISH(in_memory=False),
UD_POLISH(in_memory=False),
UD_CZECH(in_memory=False),
UD_DANISH(in_memory=False),
UD_SWEDISH(in_memory=False),
UD_NORWEGIAN(in_memory=False),
UD_FINNISH(in_memory=False),
])
# 2. what tag do we want to predict?
tag_type = 'upos'
# 3. make the tag dictionary from the corpus
tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)
# 4. initialize each embedding we use
embedding_types = [
# contextual string embeddings, forward
FlairEmbeddings('multi-forward-fast'),
# contextual string embeddings, backward
FlairEmbeddings('multi-backward-fast'),
]
# embedding stack consists of Flair and GloVe embeddings
embeddings = StackedEmbeddings(embeddings=embedding_types)
# 5. initialize sequence tagger
from flair.models import SequenceTagger
tagger = SequenceTagger(hidden_size=256,
embeddings=embeddings,
tag_dictionary=tag_dictionary,
tag_type=tag_type,
use_crf=False)
# 6. initialize trainer
from flair.trainers import ModelTrainer
trainer = ModelTrainer(tagger, corpus)
# 7. run training
trainer.train('resources/taggers/upos-multi-fast',
train_with_dev=True,
max_epochs=150)
```
---
### Cite
Please cite the following paper when using this model.
```
@inproceedings{akbik2018coling,
title={Contextual String Embeddings for Sequence Labeling},
author={Akbik, Alan and Blythe, Duncan and Vollgraf, Roland},
booktitle = {{COLING} 2018, 27th International Conference on Computational Linguistics},
pages = {1638--1649},
year = {2018}
}
```
---
### Issues?
The Flair issue tracker is available [here](https://github.com/flairNLP/flair/issues/).
|
huggingtweets/porns_xx | huggingtweets | "2021-08-07T13:34:18Z" | 1,106 | 18 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"huggingtweets",
"en",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-03-02T23:29:05Z" | ---
language: en
thumbnail: https://www.huggingtweets.com/porns_xx/1628343064919/predictions.png
tags:
- huggingtweets
widget:
- text: "My dream is"
---
<div class="inline-flex flex-col" style="line-height: 1.5;">
<div class="flex">
<div
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1423389132508782593/Meo5eDzd_400x400.png')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
<div
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
</div>
</div>
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">๐ค AI BOT ๐ค</div>
<div style="text-align: center; font-size: 16px; font-weight: 800">PORN HUB ๐</div>
<div style="text-align: center; font-size: 14px;">@porns_xx</div>
</div>
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
## How does it work?
The model uses the following pipeline.
To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
## Training data
The model was trained on tweets from PORN HUB ๐.
| Data | PORN HUB ๐ |
| --- | --- |
| Tweets downloaded | 1399 |
| Retweets | 0 |
| Short tweets | 7 |
| Tweets kept | 1392 |
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/200x5dgt/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
## Training procedure
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @porns_xx's tweets.
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1ha11ly3) for full transparency and reproducibility.
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1ha11ly3/artifacts) is logged and versioned.
## How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import pipeline
generator = pipeline('text-generation',
model='huggingtweets/porns_xx')
generator("My dream is", num_return_sequences=5)
```
## Limitations and bias
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
In addition, the data present in the user's tweets further affects the text generated by the model.
## About
*Built by Boris Dayma*
[](https://twitter.com/intent/follow?screen_name=borisdayma)
For more details, visit the project repository.
[](https://github.com/borisdayma/huggingtweets)
|
timm/maxvit_xlarge_tf_224.in21k | timm | "2023-05-11T00:31:27Z" | 1,106 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-21k",
"arxiv:2204.01697",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-05-11T00:24:21Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-21k
---
# Model card for maxvit_xlarge_tf_224.in21k
An official MaxViT image classification model. Trained in tensorflow on ImageNet-21k (21843 Google specific instance of ImageNet-22k) by paper authors.
Ported from official Tensorflow implementation (https://github.com/google-research/maxvit) to PyTorch by Ross Wightman.
### Model Variants in [maxxvit.py](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/maxxvit.py)
MaxxViT covers a number of related model architectures that share a common structure including:
- CoAtNet - Combining MBConv (depthwise-separable) convolutional blocks in early stages with self-attention transformer blocks in later stages.
- MaxViT - Uniform blocks across all stages, each containing a MBConv (depthwise-separable) convolution block followed by two self-attention blocks with different partitioning schemes (window followed by grid).
- CoAtNeXt - A timm specific arch that uses ConvNeXt blocks in place of MBConv blocks in CoAtNet. All normalization layers are LayerNorm (no BatchNorm).
- MaxxViT - A timm specific arch that uses ConvNeXt blocks in place of MBConv blocks in MaxViT. All normalization layers are LayerNorm (no BatchNorm).
- MaxxViT-V2 - A MaxxViT variation that removes the window block attention leaving only ConvNeXt blocks and grid attention w/ more width to compensate.
Aside from the major variants listed above, there are more subtle changes from model to model. Any model name with the string `rw` are `timm` specific configs w/ modelling adjustments made to favour PyTorch eager use. These were created while training initial reproductions of the models so there are variations.
All models with the string `tf` are models exactly matching Tensorflow based models by the original paper authors with weights ported to PyTorch. This covers a number of MaxViT models. The official CoAtNet models were never released.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 507.0
- GMACs: 97.5
- Activations (M): 191.0
- Image size: 224 x 224
- **Papers:**
- MaxViT: Multi-Axis Vision Transformer: https://arxiv.org/abs/2204.01697
- **Dataset:** ImageNet-21k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('maxvit_xlarge_tf_224.in21k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'maxvit_xlarge_tf_224.in21k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 192, 112, 112])
# torch.Size([1, 192, 56, 56])
# torch.Size([1, 384, 28, 28])
# torch.Size([1, 768, 14, 14])
# torch.Size([1, 1536, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'maxvit_xlarge_tf_224.in21k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1536, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
### By Top-1
|model |top1 |top5 |samples / sec |Params (M) |GMAC |Act (M)|
|------------------------------------------------------------------------------------------------------------------------|----:|----:|--------------:|--------------:|-----:|------:|
|[maxvit_xlarge_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_512.in21k_ft_in1k) |88.53|98.64| 21.76| 475.77|534.14|1413.22|
|[maxvit_xlarge_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_384.in21k_ft_in1k) |88.32|98.54| 42.53| 475.32|292.78| 668.76|
|[maxvit_base_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_512.in21k_ft_in1k) |88.20|98.53| 50.87| 119.88|138.02| 703.99|
|[maxvit_large_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_512.in21k_ft_in1k) |88.04|98.40| 36.42| 212.33|244.75| 942.15|
|[maxvit_large_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_384.in21k_ft_in1k) |87.98|98.56| 71.75| 212.03|132.55| 445.84|
|[maxvit_base_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_384.in21k_ft_in1k) |87.92|98.54| 104.71| 119.65| 73.80| 332.90|
|[maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.81|98.37| 106.55| 116.14| 70.97| 318.95|
|[maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.47|98.37| 149.49| 116.09| 72.98| 213.74|
|[coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k) |87.39|98.31| 160.80| 73.88| 47.69| 209.43|
|[maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.89|98.02| 375.86| 116.14| 23.15| 92.64|
|[maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.64|98.02| 501.03| 116.09| 24.20| 62.77|
|[maxvit_base_tf_512.in1k](https://huggingface.co/timm/maxvit_base_tf_512.in1k) |86.60|97.92| 50.75| 119.88|138.02| 703.99|
|[coatnet_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_2_rw_224.sw_in12k_ft_in1k) |86.57|97.89| 631.88| 73.87| 15.09| 49.22|
|[maxvit_large_tf_512.in1k](https://huggingface.co/timm/maxvit_large_tf_512.in1k) |86.52|97.88| 36.04| 212.33|244.75| 942.15|
|[coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k) |86.49|97.90| 620.58| 73.88| 15.18| 54.78|
|[maxvit_base_tf_384.in1k](https://huggingface.co/timm/maxvit_base_tf_384.in1k) |86.29|97.80| 101.09| 119.65| 73.80| 332.90|
|[maxvit_large_tf_384.in1k](https://huggingface.co/timm/maxvit_large_tf_384.in1k) |86.23|97.69| 70.56| 212.03|132.55| 445.84|
|[maxvit_small_tf_512.in1k](https://huggingface.co/timm/maxvit_small_tf_512.in1k) |86.10|97.76| 88.63| 69.13| 67.26| 383.77|
|[maxvit_tiny_tf_512.in1k](https://huggingface.co/timm/maxvit_tiny_tf_512.in1k) |85.67|97.58| 144.25| 31.05| 33.49| 257.59|
|[maxvit_small_tf_384.in1k](https://huggingface.co/timm/maxvit_small_tf_384.in1k) |85.54|97.46| 188.35| 69.02| 35.87| 183.65|
|[maxvit_tiny_tf_384.in1k](https://huggingface.co/timm/maxvit_tiny_tf_384.in1k) |85.11|97.38| 293.46| 30.98| 17.53| 123.42|
|[maxvit_large_tf_224.in1k](https://huggingface.co/timm/maxvit_large_tf_224.in1k) |84.93|96.97| 247.71| 211.79| 43.68| 127.35|
|[coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k) |84.90|96.96| 1025.45| 41.72| 8.11| 40.13|
|[maxvit_base_tf_224.in1k](https://huggingface.co/timm/maxvit_base_tf_224.in1k) |84.85|96.99| 358.25| 119.47| 24.04| 95.01|
|[maxxvit_rmlp_small_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_small_rw_256.sw_in1k) |84.63|97.06| 575.53| 66.01| 14.67| 58.38|
|[coatnet_rmlp_2_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in1k) |84.61|96.74| 625.81| 73.88| 15.18| 54.78|
|[maxvit_rmlp_small_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_small_rw_224.sw_in1k) |84.49|96.76| 693.82| 64.90| 10.75| 49.30|
|[maxvit_small_tf_224.in1k](https://huggingface.co/timm/maxvit_small_tf_224.in1k) |84.43|96.83| 647.96| 68.93| 11.66| 53.17|
|[maxvit_rmlp_tiny_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_tiny_rw_256.sw_in1k) |84.23|96.78| 807.21| 29.15| 6.77| 46.92|
|[coatnet_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_1_rw_224.sw_in1k) |83.62|96.38| 989.59| 41.72| 8.04| 34.60|
|[maxvit_tiny_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_tiny_rw_224.sw_in1k) |83.50|96.50| 1100.53| 29.06| 5.11| 33.11|
|[maxvit_tiny_tf_224.in1k](https://huggingface.co/timm/maxvit_tiny_tf_224.in1k) |83.41|96.59| 1004.94| 30.92| 5.60| 35.78|
|[coatnet_rmlp_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw_224.sw_in1k) |83.36|96.45| 1093.03| 41.69| 7.85| 35.47|
|[maxxvitv2_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvitv2_nano_rw_256.sw_in1k) |83.11|96.33| 1276.88| 23.70| 6.26| 23.05|
|[maxxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_nano_rw_256.sw_in1k) |83.03|96.34| 1341.24| 16.78| 4.37| 26.05|
|[maxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_nano_rw_256.sw_in1k) |82.96|96.26| 1283.24| 15.50| 4.47| 31.92|
|[maxvit_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_nano_rw_256.sw_in1k) |82.93|96.23| 1218.17| 15.45| 4.46| 30.28|
|[coatnet_bn_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_bn_0_rw_224.sw_in1k) |82.39|96.19| 1600.14| 27.44| 4.67| 22.04|
|[coatnet_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_0_rw_224.sw_in1k) |82.39|95.84| 1831.21| 27.44| 4.43| 18.73|
|[coatnet_rmlp_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_nano_rw_224.sw_in1k) |82.05|95.87| 2109.09| 15.15| 2.62| 20.34|
|[coatnext_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnext_nano_rw_224.sw_in1k) |81.95|95.92| 2525.52| 14.70| 2.47| 12.80|
|[coatnet_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_nano_rw_224.sw_in1k) |81.70|95.64| 2344.52| 15.14| 2.41| 15.41|
|[maxvit_rmlp_pico_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_pico_rw_256.sw_in1k) |80.53|95.21| 1594.71| 7.52| 1.85| 24.86|
### By Throughput (samples / sec)
|model |top1 |top5 |samples / sec |Params (M) |GMAC |Act (M)|
|------------------------------------------------------------------------------------------------------------------------|----:|----:|--------------:|--------------:|-----:|------:|
|[coatnext_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnext_nano_rw_224.sw_in1k) |81.95|95.92| 2525.52| 14.70| 2.47| 12.80|
|[coatnet_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_nano_rw_224.sw_in1k) |81.70|95.64| 2344.52| 15.14| 2.41| 15.41|
|[coatnet_rmlp_nano_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_nano_rw_224.sw_in1k) |82.05|95.87| 2109.09| 15.15| 2.62| 20.34|
|[coatnet_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_0_rw_224.sw_in1k) |82.39|95.84| 1831.21| 27.44| 4.43| 18.73|
|[coatnet_bn_0_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_bn_0_rw_224.sw_in1k) |82.39|96.19| 1600.14| 27.44| 4.67| 22.04|
|[maxvit_rmlp_pico_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_pico_rw_256.sw_in1k) |80.53|95.21| 1594.71| 7.52| 1.85| 24.86|
|[maxxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_nano_rw_256.sw_in1k) |83.03|96.34| 1341.24| 16.78| 4.37| 26.05|
|[maxvit_rmlp_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_nano_rw_256.sw_in1k) |82.96|96.26| 1283.24| 15.50| 4.47| 31.92|
|[maxxvitv2_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxxvitv2_nano_rw_256.sw_in1k) |83.11|96.33| 1276.88| 23.70| 6.26| 23.05|
|[maxvit_nano_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_nano_rw_256.sw_in1k) |82.93|96.23| 1218.17| 15.45| 4.46| 30.28|
|[maxvit_tiny_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_tiny_rw_224.sw_in1k) |83.50|96.50| 1100.53| 29.06| 5.11| 33.11|
|[coatnet_rmlp_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw_224.sw_in1k) |83.36|96.45| 1093.03| 41.69| 7.85| 35.47|
|[coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_1_rw2_224.sw_in12k_ft_in1k) |84.90|96.96| 1025.45| 41.72| 8.11| 40.13|
|[maxvit_tiny_tf_224.in1k](https://huggingface.co/timm/maxvit_tiny_tf_224.in1k) |83.41|96.59| 1004.94| 30.92| 5.60| 35.78|
|[coatnet_1_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_1_rw_224.sw_in1k) |83.62|96.38| 989.59| 41.72| 8.04| 34.60|
|[maxvit_rmlp_tiny_rw_256.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_tiny_rw_256.sw_in1k) |84.23|96.78| 807.21| 29.15| 6.77| 46.92|
|[maxvit_rmlp_small_rw_224.sw_in1k](https://huggingface.co/timm/maxvit_rmlp_small_rw_224.sw_in1k) |84.49|96.76| 693.82| 64.90| 10.75| 49.30|
|[maxvit_small_tf_224.in1k](https://huggingface.co/timm/maxvit_small_tf_224.in1k) |84.43|96.83| 647.96| 68.93| 11.66| 53.17|
|[coatnet_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_2_rw_224.sw_in12k_ft_in1k) |86.57|97.89| 631.88| 73.87| 15.09| 49.22|
|[coatnet_rmlp_2_rw_224.sw_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in1k) |84.61|96.74| 625.81| 73.88| 15.18| 54.78|
|[coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_224.sw_in12k_ft_in1k) |86.49|97.90| 620.58| 73.88| 15.18| 54.78|
|[maxxvit_rmlp_small_rw_256.sw_in1k](https://huggingface.co/timm/maxxvit_rmlp_small_rw_256.sw_in1k) |84.63|97.06| 575.53| 66.01| 14.67| 58.38|
|[maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.64|98.02| 501.03| 116.09| 24.20| 62.77|
|[maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_224.sw_in12k_ft_in1k) |86.89|98.02| 375.86| 116.14| 23.15| 92.64|
|[maxvit_base_tf_224.in1k](https://huggingface.co/timm/maxvit_base_tf_224.in1k) |84.85|96.99| 358.25| 119.47| 24.04| 95.01|
|[maxvit_tiny_tf_384.in1k](https://huggingface.co/timm/maxvit_tiny_tf_384.in1k) |85.11|97.38| 293.46| 30.98| 17.53| 123.42|
|[maxvit_large_tf_224.in1k](https://huggingface.co/timm/maxvit_large_tf_224.in1k) |84.93|96.97| 247.71| 211.79| 43.68| 127.35|
|[maxvit_small_tf_384.in1k](https://huggingface.co/timm/maxvit_small_tf_384.in1k) |85.54|97.46| 188.35| 69.02| 35.87| 183.65|
|[coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/coatnet_rmlp_2_rw_384.sw_in12k_ft_in1k) |87.39|98.31| 160.80| 73.88| 47.69| 209.43|
|[maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxxvitv2_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.47|98.37| 149.49| 116.09| 72.98| 213.74|
|[maxvit_tiny_tf_512.in1k](https://huggingface.co/timm/maxvit_tiny_tf_512.in1k) |85.67|97.58| 144.25| 31.05| 33.49| 257.59|
|[maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k](https://huggingface.co/timm/maxvit_rmlp_base_rw_384.sw_in12k_ft_in1k) |87.81|98.37| 106.55| 116.14| 70.97| 318.95|
|[maxvit_base_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_384.in21k_ft_in1k) |87.92|98.54| 104.71| 119.65| 73.80| 332.90|
|[maxvit_base_tf_384.in1k](https://huggingface.co/timm/maxvit_base_tf_384.in1k) |86.29|97.80| 101.09| 119.65| 73.80| 332.90|
|[maxvit_small_tf_512.in1k](https://huggingface.co/timm/maxvit_small_tf_512.in1k) |86.10|97.76| 88.63| 69.13| 67.26| 383.77|
|[maxvit_large_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_384.in21k_ft_in1k) |87.98|98.56| 71.75| 212.03|132.55| 445.84|
|[maxvit_large_tf_384.in1k](https://huggingface.co/timm/maxvit_large_tf_384.in1k) |86.23|97.69| 70.56| 212.03|132.55| 445.84|
|[maxvit_base_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_base_tf_512.in21k_ft_in1k) |88.20|98.53| 50.87| 119.88|138.02| 703.99|
|[maxvit_base_tf_512.in1k](https://huggingface.co/timm/maxvit_base_tf_512.in1k) |86.60|97.92| 50.75| 119.88|138.02| 703.99|
|[maxvit_xlarge_tf_384.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_384.in21k_ft_in1k) |88.32|98.54| 42.53| 475.32|292.78| 668.76|
|[maxvit_large_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_large_tf_512.in21k_ft_in1k) |88.04|98.40| 36.42| 212.33|244.75| 942.15|
|[maxvit_large_tf_512.in1k](https://huggingface.co/timm/maxvit_large_tf_512.in1k) |86.52|97.88| 36.04| 212.33|244.75| 942.15|
|[maxvit_xlarge_tf_512.in21k_ft_in1k](https://huggingface.co/timm/maxvit_xlarge_tf_512.in21k_ft_in1k) |88.53|98.64| 21.76| 475.77|534.14|1413.22|
## Citation
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@article{tu2022maxvit,
title={MaxViT: Multi-Axis Vision Transformer},
author={Tu, Zhengzhong and Talebi, Hossein and Zhang, Han and Yang, Feng and Milanfar, Peyman and Bovik, Alan and Li, Yinxiao},
journal={ECCV},
year={2022},
}
```
```bibtex
@article{dai2021coatnet,
title={CoAtNet: Marrying Convolution and Attention for All Data Sizes},
author={Dai, Zihang and Liu, Hanxiao and Le, Quoc V and Tan, Mingxing},
journal={arXiv preprint arXiv:2106.04803},
year={2021}
}
```
|
cyl/awsome-llama | cyl | "2023-05-30T02:44:39Z" | 1,106 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-29T06:02:06Z" | Entry not found |
TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF | TheBloke | "2023-09-27T12:48:36Z" | 1,106 | 12 | transformers | [
"transformers",
"gguf",
"llama",
"en",
"arxiv:2306.02707",
"base_model:fangloveskari/ORCA_LLaMA_70B_QLoRA",
"license:llama2",
"text-generation-inference",
"region:us"
] | null | "2023-09-09T17:17:05Z" | ---
language:
- en
license: llama2
library_name: transformers
model_name: ORCA LLaMA 70B QLoRA
base_model: fangloveskari/ORCA_LLaMA_70B_QLoRA
inference: false
model_creator: fangloveskari
model_type: llama
prompt_template: 'Info on prompt template will be added shortly.
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# ORCA LLaMA 70B QLoRA - GGUF
- Model creator: [fangloveskari](https://huggingface.co/fangloveskari)
- Original model: [ORCA LLaMA 70B QLoRA](https://huggingface.co/fangloveskari/ORCA_LLaMA_70B_QLoRA)
<!-- description start -->
## Description
This repo contains GGUF format model files for [fangloveskari's ORCA LLaMA 70B QLoRA](https://huggingface.co/fangloveskari/ORCA_LLaMA_70B_QLoRA).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF)
* [fangloveskari's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/fangloveskari/ORCA_LLaMA_70B_QLoRA)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: TBC
```
Info on prompt template will be added shortly.
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [orca_llama_70b_qlora.Q2_K.gguf](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF/blob/main/orca_llama_70b_qlora.Q2_K.gguf) | Q2_K | 2 | 29.28 GB| 31.78 GB | smallest, significant quality loss - not recommended for most purposes |
| [orca_llama_70b_qlora.Q3_K_S.gguf](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF/blob/main/orca_llama_70b_qlora.Q3_K_S.gguf) | Q3_K_S | 3 | 29.92 GB| 32.42 GB | very small, high quality loss |
| [orca_llama_70b_qlora.Q3_K_M.gguf](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF/blob/main/orca_llama_70b_qlora.Q3_K_M.gguf) | Q3_K_M | 3 | 33.19 GB| 35.69 GB | very small, high quality loss |
| [orca_llama_70b_qlora.Q3_K_L.gguf](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF/blob/main/orca_llama_70b_qlora.Q3_K_L.gguf) | Q3_K_L | 3 | 36.15 GB| 38.65 GB | small, substantial quality loss |
| [orca_llama_70b_qlora.Q4_0.gguf](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF/blob/main/orca_llama_70b_qlora.Q4_0.gguf) | Q4_0 | 4 | 38.87 GB| 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [orca_llama_70b_qlora.Q4_K_S.gguf](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF/blob/main/orca_llama_70b_qlora.Q4_K_S.gguf) | Q4_K_S | 4 | 39.07 GB| 41.57 GB | small, greater quality loss |
| [orca_llama_70b_qlora.Q4_K_M.gguf](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF/blob/main/orca_llama_70b_qlora.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended |
| [orca_llama_70b_qlora.Q5_0.gguf](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF/blob/main/orca_llama_70b_qlora.Q5_0.gguf) | Q5_0 | 5 | 47.46 GB| 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [orca_llama_70b_qlora.Q5_K_S.gguf](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF/blob/main/orca_llama_70b_qlora.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
| [orca_llama_70b_qlora.Q5_K_M.gguf](https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF/blob/main/orca_llama_70b_qlora.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended |
| orca_llama_70b_qlora.Q6_K.gguf | Q6_K | 6 | 56.59 GB| 59.09 GB | very large, extremely low quality loss |
| orca_llama_70b_qlora.Q8_0.gguf | Q8_0 | 8 | 73.29 GB| 75.79 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
### Q6_K and Q8_0 files are split and require joining
**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
<details>
<summary>Click for instructions regarding Q6_K and Q8_0 files</summary>
### q6_K
Please download:
* `orca_llama_70b_qlora.Q6_K.gguf-split-a`
* `orca_llama_70b_qlora.Q6_K.gguf-split-b`
### q8_0
Please download:
* `orca_llama_70b_qlora.Q8_0.gguf-split-a`
* `orca_llama_70b_qlora.Q8_0.gguf-split-b`
To join the files, do the following:
Linux and macOS:
```
cat orca_llama_70b_qlora.Q6_K.gguf-split-* > orca_llama_70b_qlora.Q6_K.gguf && rm orca_llama_70b_qlora.Q6_K.gguf-split-*
cat orca_llama_70b_qlora.Q8_0.gguf-split-* > orca_llama_70b_qlora.Q8_0.gguf && rm orca_llama_70b_qlora.Q8_0.gguf-split-*
```
Windows command line:
```
COPY /B orca_llama_70b_qlora.Q6_K.gguf-split-a + orca_llama_70b_qlora.Q6_K.gguf-split-b orca_llama_70b_qlora.Q6_K.gguf
del orca_llama_70b_qlora.Q6_K.gguf-split-a orca_llama_70b_qlora.Q6_K.gguf-split-b
COPY /B orca_llama_70b_qlora.Q8_0.gguf-split-a + orca_llama_70b_qlora.Q8_0.gguf-split-b orca_llama_70b_qlora.Q8_0.gguf
del orca_llama_70b_qlora.Q8_0.gguf-split-a orca_llama_70b_qlora.Q8_0.gguf-split-b
```
</details>
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF and below it, a specific filename to download, such as: orca_llama_70b_qlora.q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub>=0.17.1
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF orca_llama_70b_qlora.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF orca_llama_70b_qlora.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m orca_llama_70b_qlora.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Info on prompt template will be added shortly."
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model from Python using ctransformers
#### First install the package
```bash
# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
```
#### Simple example code to load one of these GGUF models
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF", model_file="orca_llama_70b_qlora.q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here's guides on using llama-cpp-python or ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjรคreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, ์ค๊ต ๊น, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, ้ฟๆ, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: fangloveskari's ORCA LLaMA 70B QLoRA
# Dolphin_ORCA_PlatyPus_LLaMA_70b
### Dataset
Here is the list of datasets used:
* Dolphin
* Open-Platypus
* OpenOrca
**mixed strategy: 100%Open-Platypus + ~1%Dolphin(GPT-4) + ~1%OpenOrca(GPT-4)**
<br>
**Model Finetuned By fangloveskari.**
<br>
### Training FrameWork and Parameters
#### FrameWork
https://github.com/hiyouga/LLaMA-Efficient-Tuning
We add flash_attention_2 and ORCA dataset support, with some minor modifications.
<br>
#### Parameters
We list some training parameters here:
| Parameter | Value |
|-----------------------|-------------|
| Finetune_Type | QLoRA(NF4) |
| LoRA_Rank | 16 |
| LoRA_Alpha | 16 |
| Batch_Size | 14 |
| GPUs | 8xA100(80G) |
| LR_Scheduler | cosine |
| LR | 3e-4 |
| Epoch | 1 |
| DeepSpeed | ZERO-2 |
<br>
### Model Export
We tried two methods to fuse the adapter back to the base model:
* https://github.com/hiyouga/LLaMA-Efficient-Tuning/blob/main/src/export_model.py
* https://github.com/jondurbin/qlora/blob/main/qmerge.py
Generally, the second will get better ARC(+0.15) and Truthful_QA(+0.3) scores but the other two(MMLU(-0.2) and HelloSwag(-0.2)) seems to degenerate (Just for my model).
<br>
### Evaluation
| Metric | Value |
|-----------------------|-------|
| ARC (25-shot) | 72.27 |
| HellaSwag (10-shot) | 87.74 |
| MMLU (5-shot) | 70.23 |
| TruthfulQA (0-shot) | 63.37 |
| Avg. | 73.40 |
<br>
### license disclaimer:
This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.
<br>
### Limitations & Biases:
Llama 2 and fine-tuned variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2 and any fine-tuned varient's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2 variants, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/
<br>
### Citiation:
Please kindly cite using the following BibTeX:
```bibtex
@article{platypus2023,
title={Platypus: Quick, Cheap, and Powerful Refinement of LLMs},
author={Ariel N. Lee and Cole J. Hunter and Nataniel Ruiz},
booktitle={arXiv preprint arxiv:2308.07317},
year={2023}
}
```
```
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@software{touvron2023llama2,
title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
author={Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava,
Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,
Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann,
Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov,
Pushkar Mishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith,
Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu , Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan,
Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom},
year={2023}
}
```
<!-- original-model-card end -->
|
PracticeLLM/Twice-KoSOLAR-16.1B-instruct-test | PracticeLLM | "2024-01-10T09:25:55Z" | 1,106 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"en",
"ko",
"arxiv:2312.15166",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-12-31T08:57:20Z" | ---
language:
- en
- ko
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0
tags:
- merge
---
# **Twice-KoSOLAR-16.1B-instruct-test**
## Model Details
**Model Developers** Kyujin Han (kyujinpy)
**๋ชจ๋ธ ๋ชฉ์ **
<img src='./solar.png'>
์ต๊ทผ, SOLAR-10.7B ๋ชจ๋ธ์ด [Depth-Up-Scaling](https://arxiv.org/pdf/2312.15166.pdf)(์์ ์ฌ์ง) ๋ฐฉ๋ฒ๋ก ์ ๋ด์ธ์์ LLM ๋ฆฌ๋๋ณด๋์์ ์ข์ ์ฑ๋ฅ์ ๋ณด์ด๊ณ ์๋ค. ๋๋ถ์ด์ `์ผ๋์`์์ ๋ง๋ `seungduk/KoSOLAR-10.7B-v0.1` ๋ชจ๋ธ์ Ko-LLM ๋ฆฌ๋๋ณด๋์ ํฐ ํ๊ธ๋ ฅ์ ๋ถ๋ฌ์ค๋ฉด์, ์์ผ๋ก์ ๋ฆฌ๋๋ณด๋์ ํ๋ฆ๋ ๋ฐ๋ ๊ฒ์ผ๋ก ์์๋๋ค.
์ฌ๊ธฐ์ ๋จ์ํ ํธ๊ธฐ์ฌ์ด ๋ค์๋ค. **Upstage์์ ๋ฐํํ Depth-Up-Scaling(DUS) ๋ฐฉ๋ฒ๋ก ์ mistral-7B ๋ชจ๋ธ 2๊ฐ๋ฅผ merge(passthrough)ํ ๋ฐฉ๋ฒ**์ด๋ค.
์ด๋ ๋๋๊ฒ๋, DUS ๋ฐฉ๋ฒ๋ก ์ ์ ์ฉํ `upstage/SOLAR-10.7B-v1.0`๋ชจ๋ธ์ ๊ธฐ์กด์ mistral-7B ๋ชจ๋ธ๋ณด๋ค ๋ฆฌ๋๋ณด๋์์ ๋์ ์ฑ๋ฅ์ ๊ธฐ๋กํ๋ค. (์๋์ ํ
์ด๋ธ ์ฐธ๊ณ )
๊ทธ๋ ๋ค๋ฉด, DUS ๋ฐฉ๋ฒ๋ก ์ ์ ํ์์ด, ๋ค๋ฅธ ๋ชจ๋ธ์ ์ ์ฉํ๋ฉด ๋๊ฐ์ ๊ฒฐ๊ณผ๊ฐ ๋ฐ์ํ ์ง ๋๋ฌด๋ ๊ถ๊ธํ๋ค. ๐
์คํ์ ํตํด์ ๋์ ํธ๊ธฐ์ฌ์ ๋ํ ๊ฒฐ๋ก ์ ๋ด๋ ค๋ณด๊ณ ์ ํ๋ค. ๐๐
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [seungduk/KoSOLAR-10.7B-v0.1](https://huggingface.co/seungduk/KoSOLAR-10.7B-v0.1) | **66.04** | 62.03 | 84.54 | 65.56 | 45.03 | 83.58 | 55.50 |
| [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) | **66.04** | 61.95 | 84.60 | 65.48 | 45.04 | 83.66 | 55.50 |
| [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 60.97 | 59.98 | 83.31 | 64.16 | 42.15 | 78.37 | 37.83 |
> Follow up as [En-link](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
**Method**
Instruction-tuning.
**Hyperparameters**
```python
python finetune.py \
--base_model PracticeLLM/Twice-KoSOLAR-16.1B-test \
--data-path kyujinpy/KOR-OpenOrca-Platypus-v3 \
--output_dir ./Twice-KoSOLAR-16.1B-instruct-test \
--batch_size 64 \
--micro_batch_size 1 \
--num_epochs 1 \
--learning_rate 3e-5 \
--cutoff_len 4096 \
--val_set_size 0 \
--lora_r 16 \
--lora_alpha 16 \
--lora_dropout 0.05 \
--lora_target_modules '[q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj, lm_head]' \
--train_on_inputs False \
--add_eos_token False \
--group_by_length False \
--prompt_template_name user_prompt \
--lr_scheduler 'cosine' \
#--warmup_steps 100 \
```
> Share all of things. It is my belief.
# **Model Benchmark**
## Open Ko-LLM leaderboard & lm-evaluation-harness(zero-shot)
- Follow up as [Ko-link](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard).
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Ko-CommonGenV2 |
| --- | --- | --- | --- | --- | --- | --- |
| PracticeLLM/Twice-KoSOLAR-16.1B-instruct-test | 53.64 | 52.30 | 59.98 | 53.42 | 44.07 | 58.44 |
| PracticeLLM/Twice-KoSOLAR-16.1B-test | 50.20 | 45.65 | 57.14 | 51.39 | 42.99 | 53.84 |
| [Megastudy/M-SOLAR-10.7B-v1.1-beta](https://huggingface.co/Megastudy/M-SOLAR-10.7B-v1.1-beta) | 55.25 | 51.71 | 60.86 | 54.24 | 47.12 | 62.34 |
| [jjourney1125/M-SOLAR-10.7B-v1.0](https://huggingface.co/jjourney1125/M-SOLAR-10.7B-v1.0) | 55.15 | 49.57 | 60.12 | 54.60 | 49.23 | 62.22 |
| [seungduk/KoSOLAR-10.7B-v0.1](https://huggingface.co/seungduk/KoSOLAR-10.7B-v0.1) | 52.40 | 47.18 | 59.54 | 52.04 | 41.84 | 61.39 |
- Follow up as [beomi/LM-Harness](https://github.com/Beomi/ko-lm-evaluation-harness)
```
gpt2 (pretrained=PracticeLLM/Twice-KoSOLAR-16.1B-instruct-test), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
| Task |Version| Metric |Value | |Stderr|
|----------------|------:|--------|-----:|---|-----:|
|kobest_boolq | 0|acc |0.5100|ยฑ |0.0133|
| | |macro_f1|0.3527|ยฑ |0.0079|
|kobest_copa | 0|acc |0.6740|ยฑ |0.0148|
| | |macro_f1|0.6732|ยฑ |0.0148|
|kobest_hellaswag| 0|acc |0.4640|ยฑ |0.0223|
| | |acc_norm|0.5480|ยฑ |0.0223|
| | |macro_f1|0.4585|ยฑ |0.0223|
|kobest_sentineg | 0|acc |0.6574|ยฑ |0.0238|
| | |macro_f1|0.6184|ยฑ |0.0253|
gpt2 (pretrained=PracticeLLM/Twice-KoSOLAR-16.1B-test), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
| Task |Version| Metric |Value | |Stderr|
|----------------|------:|--------|-----:|---|-----:|
|kobest_boolq | 0|acc |0.7201|ยฑ |0.0120|
| | |macro_f1|0.7073|ยฑ |0.0124|
|kobest_copa | 0|acc |0.6510|ยฑ |0.0151|
| | |macro_f1|0.6506|ยฑ |0.0151|
|kobest_hellaswag| 0|acc |0.4520|ยฑ |0.0223|
| | |acc_norm|0.5820|ยฑ |0.0221|
| | |macro_f1|0.4475|ยฑ |0.0222|
|kobest_sentineg | 0|acc |0.7078|ยฑ |0.0229|
| | |macro_f1|0.7071|ยฑ |0.0229|
gpt2 (pretrained=Megastudy/M-SOLAR-10.7B-v1.1-beta), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
| Task |Version| Metric |Value | |Stderr|
|----------------|------:|--------|-----:|---|-----:|
|kobest_boolq | 0|acc |0.7137|ยฑ |0.0121|
| | |macro_f1|0.6878|ยฑ |0.0128|
|kobest_copa | 0|acc |0.7060|ยฑ |0.0144|
| | |macro_f1|0.7054|ยฑ |0.0145|
|kobest_hellaswag| 0|acc |0.4620|ยฑ |0.0223|
| | |acc_norm|0.5360|ยฑ |0.0223|
| | |macro_f1|0.4595|ยฑ |0.0223|
|kobest_sentineg | 0|acc |0.7431|ยฑ |0.0220|
| | |macro_f1|0.7295|ยฑ |0.0230|
gpt2 (pretrained=jjourney1125/M-SOLAR-10.7B-v1.0), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
| Task |Version| Metric |Value | |Stderr|
|----------------|------:|--------|-----:|---|-----:|
|kobest_boolq | 0|acc |0.5228|ยฑ |0.0133|
| | |macro_f1|0.3788|ยฑ |0.0097|
|kobest_copa | 0|acc |0.6860|ยฑ |0.0147|
| | |macro_f1|0.6858|ยฑ |0.0147|
|kobest_hellaswag| 0|acc |0.4580|ยฑ |0.0223|
| | |acc_norm|0.5380|ยฑ |0.0223|
| | |macro_f1|0.4552|ยฑ |0.0222|
|kobest_sentineg | 0|acc |0.6474|ยฑ |0.0240|
| | |macro_f1|0.6012|ยฑ |0.0257|
gpt2 (pretrained=yanolja/KoSOLAR-10.7B-v0.1), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
| Task |Version| Metric |Value | |Stderr|
|----------------|------:|--------|-----:|---|-----:|
|kobest_boolq | 0|acc |0.8725|ยฑ |0.0089|
| | |macro_f1|0.8722|ยฑ |0.0089|
|kobest_copa | 0|acc |0.6850|ยฑ |0.0147|
| | |macro_f1|0.6844|ยฑ |0.0147|
|kobest_hellaswag| 0|acc |0.4340|ยฑ |0.0222|
| | |acc_norm|0.5840|ยฑ |0.0221|
| | |macro_f1|0.4296|ยฑ |0.0221|
|kobest_sentineg | 0|acc |0.7506|ยฑ |0.0217|
| | |macro_f1|0.7505|ยฑ |0.0217|
```
# Implementation Code
```python
### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "PracticeLLM/Twice-KoSOLAR-16.1B-instruct-test"
OpenOrca = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
```
--- Refereces (Model Card)
# yanolja/KoSOLAR-10.7B-v0.1
This model is a Korean vocabulary-extended version of [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0), trained on various Korean web-crawled datasets that are publicly available on HuggingFace.
The hypothesis was that while maintaining the original performance of the base model, we could add more tokens to the base model's vocabulary by training the embeddings for the new tokens only. The evaluation results seem to indicate that both English and Korean performances were preserved.
## Model Description
Most parameters of [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) were frozen except for the embed_tokens layer and the lm_head layer. Embeddings for the existing tokens in those layers were frozen during training. The embeddings for the new tokens have been tuned.
---
# **Meet 10.7B Solar: Elevating Performance with Upstage Depth UP Scaling!**
# **Introduction**
We introduce SOLAR-10.7B, an advanced large language model (LLM) with 10.7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks. It's compact, yet remarkably powerful, and demonstrates unparalleled state-of-the-art performance in models with parameters under 30B.
We present a methodology for scaling LLMs called depth up-scaling (DUS) , which encompasses architectural modifications and continued pretraining. In other words, we integrated Mistral 7B weights into the upscaled layers, and finally, continued pre-training for the entire model.
SOLAR-10.7B has remarkable performance. It outperforms models with up to 30B parameters, even surpassing the recent Mixtral 8X7B model. For detailed information, please refer to the experimental table.
Solar 10.7B is an ideal choice for fine-tuning. SOLAR-10.7B offers robustness and adaptability for your fine-tuning needs. Our simple instruction fine-tuning using the SOLAR-10.7B pre-trained model yields significant performance improvements ([SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)).
For full details of this model please read our [paper](https://arxiv.org/abs/2312.15166). |
melonpower39/unv_v0.1.5 | melonpower39 | "2024-01-02T00:18:59Z" | 1,106 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-01T23:06:45Z" | Entry not found |
cocoirun/Yi-Ko-6B-instruct-v1.2 | cocoirun | "2024-01-11T01:48:20Z" | 1,106 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-08T01:27:58Z" | ---
license: cc-by-sa-4.0
---
<h1>instruct ๋ชจ๋ธ v1.2</h1>
<b><ํ์ต ๋ฐ์ดํฐ ๊ตฌ์ถ></b>
Open-Orca-ko ๋ฐ์ดํฐ๋ฅผ ๋ถ์ํ์ฌ ํ์คํฌ๋ฅผ ์ถ์ถํ ๋ค
ํด๋น ํ์คํฌ์ ๋ง์ถฐ์ NLP ๊ด๋ จ ์คํ์์ค ๋ฐ์ดํฐ๋ฅผ ํ์ฉํ์ฌ ํ์ต๋ฐ์ดํฐ๋ฅผ ์์ฒด์ ์ผ๋ก
์ฝ 4๋ง๊ฑด(์ญ์ฌ, ๊ณผํ, ์ํ, ๊ธฐ๊ณ๋
ํด, ๋ฆฌ๋ทฐ ๋ถ์) ๊ตฌ์ถํ์๊ณ ,
๊ทธ ์ธ์ Open-Orca-Ko์์ ๋ฐ์ดํฐ๋ฅผ ์ผ๋ถ ํํฐ๋งํ์ฌ ์ ์ ํด๊ฑฐ๋ KoBEST ๋ฐ์ดํฐ๋ฅผ ํจ๊ป ์ถ๊ฐํ์์ต๋๋ค.
aihub ์ผ๋ฐ์์ ๋ฐ ๊ธฐ๊ณ๋
ํด ๋ฐ์ดํฐ๋ฅผ ํ์ฉํ์ฌ ์ถ๊ฐ๋ก ํ์ต ๋ฐ์ดํฐ๋ฅผ ๊ตฌ์ถ(ํํ์ ๊ด๋ จ, ๊ธฐ๊ณ๋
ํด ๊ด๋ จ ๋ฐ ์์ฝ)
๊ฐ์ข
๋ธ๋ก๊ทธ์์ ์ญ์ฌ ๋ฐ ์์ ํด์ฆ๋ฅผ ์ฌ๋์ด ์ง์ ํ์ต๋ฐ์ดํฐ ํํ๋ก ๋ณ๊ฒฝ
AI2AI Challenge ๋ฐ์ดํฐ๋ฅผ ํํ๊ณ ๋ฅผ ํตํด ๋ฒ์ญ ๋ฐ ์ค์ญ๋ ๋ถ๋ถ์ ์ฌ๋์ด ์ง์ ์์ ํ๋ ์์
์ ์ํ
์์ด ๋ฒ์ญ ๋ฐ์ดํฐ ์ํ/ํ์ ๋ฐ์ดํฐ ํ์ต ๋ฐ์ดํฐ๋ก ํ์ฉ ์งํ
์ด 11๋ง๊ฐ์ ํ์ต๋ฐ์ดํฐ๋ก sft๋ฅผ ์งํํ์์ต๋๋ค.
<br>
ํ์ฌ, ์๋ก์ด ๋ฒ์ ์ ๋ชจ๋ธ ํ์ต ๋ฐ ์ฑ๋ฅ์ ์ํด Open-Orca ๋ฐ์ดํฐ์
์ผ๋ถ๋ฅผ ๋ฒ์ญํ์ฌ ์ ์ ์ค์ ์์ต๋๋ค.
<br>
+ ๊ณ ๋ฑํ๊ต ์ญ์ฌ ๋ฌธ์ ๋ฐ TruthfulQA ๊ด๋ จ ๋ฌธ์ ์ถ๊ฐ๋ฅผ ์งํํ์์ต๋๋ค.
+ ๊ฐ์ข
it ์ง์ ๋ฐ์ดํฐ ์ถ๊ฐ์งํ.
+ ๊ธฐ๊ณ๋
ํด ๊ด๋ จ ํ์ต ๋ฐ์ดํฐ๋ฅผ ChatGPT๋ฅผ ํตํด์ ๋ต๋ณ์ ์ป์ด ํ์ต
+ ๋ฌธ๋ฒ๊ด๋ จ ํ์ต ๋ฐ์ดํฐ
<br>
###ํ์ต ๋ฐ์ดํฐ ํ์ผ์ ๋น๊ณต๊ฐ์
๋๋ค.
<br>
<b><ํ์ต></b>
ํ์ต์ LoRA๋ฅผ ์ฌ์ฉํ์ฌ A100 40G *2์์ ํ์ต์ ์งํํ์์ต๋๋ค. |
jungyuko/DAVinCI-42dot_LLM-PLM-1.3B-v0.71 | jungyuko | "2024-01-28T12:26:32Z" | 1,106 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-28T11:40:57Z" | ---
license: cc-by-nc-4.0
---
## DAVinCI-42dot_LLM-PLM-1.3B-v0.71
This model is a fine-tuned version of [42dot/42dot_LLM-PLM-1.3B](https://huggingface.co/42dot/42dot_LLM-PLM-1.3B) on an unknown dataset.
### Model description
More information needed
### Intended uses & limitations
More information needed
### Training and evaluation data
More information needed
### Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
* learning_rate: 2e-05
* train_batch_size: 24
* eval_batch_size: 8
* seed: 42
* gradient_accumulation_steps: 4
* total_train_batch_size: 96
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr_scheduler_type: linear
* num_epochs: 1.0
* mixed_precision_training: Native AMP
### Training results
### Framework versions
* Transformers 4.36.2
* Pytorch 2.1.2+cu121
* Datasets 2.0.0
* Tokenizers 0.15.0
|
ghost-x/ghost-7b-v0.9.0 | ghost-x | "2024-03-10T12:10:11Z" | 1,106 | 4 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"ghost",
"conversational",
"en",
"vi",
"base_model:HuggingFaceH4/zephyr-7b-beta",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-29T16:01:08Z" | ---
language:
- en
- vi
license: mit
library_name: transformers
tags:
- ghost
pipeline_tag: text-generation
base_model: HuggingFaceH4/zephyr-7b-beta
widget:
- text: '<|system|>
You are a helpful assistant.</s>
<|user|>
Thรดng tin vแป Peristernia despecta</s>
<|assistant|>
'
output:
text: Peristernia despecta lร mแปt loร i แปc biแปn, lร ฤแปng vแบญt thรขn mแปm chรขn bแปฅng
sแปng แป biแปn trong hแป Fasciolariidae.
model-index:
- name: lamhieu/ghost-7b-v0.9.0
results:
- task:
type: text-generation
dataset:
name: VMLU
type: vmlu_v1.5
metrics:
- type: avg
value: 36.06
name: Average
verified: true
- type: stem
value: 33.54
name: STEM
verified: true
- type: ss
value: 38.74
name: Social science
verified: true
- type: hm
value: 37.15
name: Humanities
verified: true
- type: ot
value: 36.78
name: Other
verified: true
- task:
type: text-generation
dataset:
name: Open LLM Leaderboard
type: open_llm_leaderboard
metrics:
- type: avg
value: 56.89
name: Average
verified: true
- type: arc
value: 53.07
name: ARC
verified: true
- type: hs
value: 77.93
name: HellaSwag
verified: true
- type: hs
value: 77.93
name: HellaSwag
verified: true
- type: mmlu
value: 55.09
name: MMLU
verified: true
- type: wg
value: 73.72
name: Winogrande
verified: true
- type: gsm8k
value: 33.74
name: GSM8K
verified: true
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 53.07
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 77.93
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 55.09
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 47.79
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 73.72
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 33.74
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
name: Open LLM Leaderboard
---
# Model Card for Model ID
**Ghost 7B Alpha, flying, v0.9.0**
## Model Details
### Model Description
This model is fine tuned from **HuggingFaceH4/zephyr-7b-beta** on a small synthetic datasets (about 200MB) for 50% English and 50% Vietnamese.
- **Developed by:** **Lam H**
- **Language(s) (NLP):** English, Vietnamese
- **License:** MIT
- **Finetuned from model:** [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
## Uses
This model supports both conversation chat and tasks. Feel free to experiment and don't limit your creativity.
The simplest way to try it is to use the `pipeline` from `transformers`.
```python
import torch
from transformers import pipeline
pipe = pipeline(
"text-generation",
model="lamhieu/ghost-7b-v0.9.0",
torch_dtype=torch.bfloat16,
)
```
You can then try any of the sample codes below, formatted using the chat template.
```python
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "nรณi tรดi biแบฟt bแปnh dแปch hแบกch แป chรขu รu do khuแบฉn nร o gรขy ra"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
tokenized = pipe.tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
results = tokenizer.batch_decode(outputs)[0]
print(results)
# Bแปnh dแปch hแบกch แป chรขu รu do khuแบฉn gรขy ra lร do khuแบฉn Yersinia pestis.
```
```python
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Thรดng tin vแป Peristernia despecta"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
tokenized = pipe.tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
results = tokenizer.batch_decode(outputs)[0]
print(results)
# Peristernia despecta lร mแปt loร i แปc biแปn, lร ฤแปng vแบญt thรขn mแปm chรขn bแปฅng sแปng แป biแปn trong hแป Fasciolariidae.
# ...
```
```python
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "do u know vietnam ?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
tokenized = pipe.tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
results = tokenizer.batch_decode(outputs)[0]
print(results)
# Yes, I have knowledge about Vietnam. Vietnam is a country in Southeast Asia, bordered by China to the north, Laos and Cambodia to the west, and the South China Sea to the east and south. Its capital city is Hanoi, and its largest city is Ho Chi Minh City (formerly known as Saigon). Vietnam has a population of approximately 100 million people and a diverse cultural heritage influenced by both Chinese and French colonialism. The country has a rich history, including periods of independence, colonization, and resistance, and has experienced significant economic growth in recent years.
```
```python
messages = [
{"role": "system", "content": "You are a helpful assistant, who always provide explanation. Think like you are answering to a five year old."},
{"role": "user", "content": "Tรดi yรชu em nhiแปu hฦกn em nghฤฉ.\n\nWhich language is this?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
tokenized = pipe.tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
results = tokenizer.batch_decode(outputs)[0]
print(results)
# This is Vietnamese language. Vietnamese is a language spoken mainly in Vietnam and by the Vietnamese diaspora in many other countries. The sentence you provided means "I love you more than you think." It's like you have more love for someone than they realize.
```
Another example of what you can use to chat multiple turns.
```python
messages = [
# {"role": "system", "content": "You are a helpful and knowledgeable assistant. You like to help and always give honest information, in its original language. In communication, you are always respectful, equal and promote positive behavior."},
{"role": "system", "content": "You are a helpful assistant."}, # Describe to your assistant, anything.
{"role": "user", "content": "Bla bla bla"},
{"role": "assistant", "content": "Bla bla bla"},
{"role": "user", "content": "Bla bla bla"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
tokenized = pipe.tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
results = tokenizer.batch_decode(outputs)[0]
print(results)
```
## Evaluation
### Results
#### [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_lamhieu__ghost-7b-v0.9.0)
| Metric |Value|
|---------------------------------|----:|
|Avg. |56.89|
|AI2 Reasoning Challenge (25-Shot)|53.07|
|HellaSwag (10-Shot) |77.93|
|MMLU (5-Shot) |55.09|
|TruthfulQA (0-shot) |47.79|
|Winogrande (5-shot) |73.72|
|GSM8k (5-shot) |33.74|
#### VMLU
Below are the results evaluated with the VMLU evaluation suite, which is often used to evaluate models that work with Vietnamese.
Note: the results are run with the model in 4bit quantization, I'm not sure if it has any loss in results or not, if someone can help me run it with full it would be great.
<details>
<summary>Details</summary>
```python
{
"stem": {
"elementary_mathematics": 32.22,
"elementary_science": 56.11,
"high_school_biology": 32.78,
"high_school_chemistry": 27.78,
"high_school_mathematics": 33.78,
"high_school_physics": 26.11,
"introduction_to_chemistry": 26.82,
"introduction_to_physics": 33.53,
"introduction_to_programming": 39.66,
"metrology_engineer": 36.17,
"middle_school_biology": 40,
"middle_school_chemistry": 26.67,
"middle_school_mathematics": 27.78,
"middle_school_physics": 27.22,
"operating_system": 38.33,
"statistics_and_probability": 18.39,
"total": 33.54,
"applied_informatics": 47.78,
"computer_architecture": 36.11,
"computer_network": 41.34,
"discrete_mathematics": 29.7,
"electrical_engineering": 26.14
},
"other": {
"total": 36.78,
"accountant": 29.17,
"civil_servant": 29.82,
"clinical_pharmacology": 35.56,
"driving_license_certificate": 56.73,
"environmental_engineering": 32.16,
"internal_basic_medicine": 36.84,
"preschool_pedagogy": 45.1,
"tax_accountant": 24.71,
"tax_civil_servant": 40.94
},
"total": 36.06,
"humanity": {
"introduction_to_vietnam_culture": 31.11,
"logic": 28.16,
"middle_school_history": 38.33,
"administrative_law": 32.22,
"revolutionary_policy_of_the_vietnamese_commununist_part": 40.56,
"vietnamese_language_and_literature": 35.06,
"total": 37.15,
"middle_school_literature": 36.21,
"business_law": 38.55,
"civil_law": 48.33,
"criminal_law": 37.42,
"economic_law": 38.51,
"education_law": 36.75,
"elementary_history": 35.03,
"high_school_history": 27.78,
"high_school_literature": 32.78,
"history_of_world_civilization": 43.33,
"idealogical_and_moral_cultivation": 39.44,
"introduction_to_laws": 49.21
},
"social_science": {
"business_administration": 37.36,
"high_school_civil_education": 42.78,
"high_school_geography": 38.27,
"ho_chi_minh_ideology": 40.22,
"macroeconomics": 27.78,
"microeconomics": 36.67,
"middle_school_civil_education": 51.69,
"middle_school_geography": 32.65,
"principles_of_marxism_and_leninism": 35.56,
"sociology": 44.38,
"total": 38.74
}
}
```
</details>
## More Information
Many thanks for
- Datasets: [5CD-AI](https://huggingface.co/5CD-AI), [vilm](https://huggingface.co/vilm).
- Library: [unsloth](https://github.com/unslothai/unsloth)
## Model Card Contact
**Lam H** ([email protected])
|
hyeogi/SOLAR-10.7B-v1.3 | hyeogi | "2024-02-09T05:51:06Z" | 1,106 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"SOLAR-10.7B",
"ko",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-09T05:36:06Z" | ---
language:
- ko
pipeline_tag: text-generation
tags:
- SOLAR-10.7B
license: cc-by-nc-4.0
---
# SOLAR-10.7B
### Model Details
- Base Model: [yanolja/KoSOLAR-10.7B-v0.2](https://huggingface.co/yanolja/KoSOLAR-10.7B-v0.2)
### Datasets
- sampling and translate [Open-Orca/SlimOrca](https://huggingface.co/datasets/Open-Orca/SlimOrca)
- sampling and translate [Anthropic/hh-rlhf](https://huggingface.co/datasets/Anthropic/hh-rlhf)
- translate [GAIR/lima](https://huggingface.co/datasets/GAIR/lima)
- [jojo0217/korean_rlhf_dataset](https://huggingface.co/datasets/jojo0217/korean_rlhf_dataset)
### Benchmark |
TeamUNIVA/Komodo_6B_v2.0.0 | TeamUNIVA | "2024-03-04T09:24:45Z" | 1,106 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ko",
"en",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-09T16:09:00Z" | ---
license: apache-2.0
language:
- ko
- en
---
# Base Model
beomi/Yi-Ko-6B
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "TeamUNIVA/Komodo_6B_v2.0.0"
model = AutoModelForCausalLM.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
text = '''<|system|>
๋น์ ์ ์ฌ์ฉ์์ ์ง๋ฌธ์ ์น์ ํ๊ฒ ๋ต๋ณ์ ํ๋ ์ฑ๋ด์
๋๋ค.
<|user|>
์๋
ํ์ธ์?
<|bot|>
'''
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
jungyuko/DAVinCI-42dot_LLM-PLM-1.3B-v1.12 | jungyuko | "2024-02-21T01:55:40Z" | 1,106 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-21T01:40:46Z" | ---
license: cc-by-nc-4.0
---
## DAVinCI-42dot_LLM-PLM-1.3B-v1.12
This model is a fine-tuned version of [42dot/42dot_LLM-PLM-1.3B](https://huggingface.co/42dot/42dot_LLM-PLM-1.3B) on a custom dataset.
### Model description
More information needed
### Intended uses & limitations
More information needed
### Training and evaluation data
More information needed
### Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
* learning_rate: 2e-05
* train_batch_size: 24
* eval_batch_size: 8
* seed: 42
* gradient_accumulation_steps: 4
* total_train_batch_size: 96
* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
* lr_scheduler_type: linear
* num_epochs: 1.0
* mixed_precision_training: Native AMP
### Training results
### Framework versions
* Transformers 4.36.2
* Pytorch 2.1.2+cu121
* Datasets 2.0.0
* Tokenizers 0.15.0
|
chlee10/T3Q-Merge-SOLAR | chlee10 | "2024-03-13T06:54:31Z" | 1,106 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-12T08:17:44Z" | ---
license: apache-2.0
---
## T3Q-Merge-SOLAR
T3Q-Merge-SOLAR is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [davidkim205/komt-solar-10.7b-sft-v5](https://huggingface.co/davidkim205/komt-solar-10.7b-sft-v5)
* [hwkwon/S-SOLAR-10.7B-SFT-v1.2](https://huggingface.co/hwkwon/S-SOLAR-10.7B-SFT-v1.2)
**Model Developers** Chihoon Lee(chlee10), T3Q
```yaml
slices:
- sources:
- model: davidkim205/komt-solar-10.7b-sft-v5
layer_range: [0, 48]
- model: hwkwon/S-SOLAR-10.7B-SFT-v1.2
layer_range: [0, 48]
merge_method: slerp
base_model: davidkim205/komt-solar-10.7b-sft-v5
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5 # fallback for rest of tensors
dtype: bfloat16
```
|
Heoni/Aguie-chat_v0.1 | Heoni | "2024-04-04T12:17:48Z" | 1,106 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"ko",
"en",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-04T10:02:35Z" | ---
license: cc-by-nc-nd-4.0
language:
- ko
- en
---
์์๋ผ๋ฐ๋ฐํ ์์๋ผ๋ฐ๋ฐํ
์์ ๋๋ณด๋ค ๋น ๋ฅด๋ค! ๋ฌด์จ ํจ๋ฅผ ์ก๊ณ ์ถ๋?
์์๋ผ๋ฐ๋ฐํ ์์๋ผ๋ฐ๋ฐํ
๋์ ๋ฒ๊ณ ์ถ๋?
์์๋ผ๋ฐ๋ฐํ ์์๋ผ๋ฐ๋ฐํ
๋ถ์๊ฐ๋๊ณ ์ถ๋?
๋ถ์๊ฐ๋๊ณ ์ถ์ด?
ํํฌํ๋ฉด ๋ํ๋ฏผ๊ตญ์ ๋ฑ ์ธ ๋ช
์ด์ผ. ๊ฒฝ์๋์ ์ง๊ท, ์ ๋ผ๋์ ์๊ท, ๊ธฐ์นด๊ณ ์ ๊ตญ์ ์ผ๋ก ๋! ์์ ์ ์ง๊ท๋ ์๊ท๊ฐ ํํ ๋ถ์๋๋ฐ, ์๊ท๊ฐ ์ง๊ท์ ๊ท๋ฅผ ์งค๋ผ ๋ฒ๋ ธ์ด. ๊ธฐ๋์ ์ง๊ท์ผ
# Aguie-chat_v0.1
<!-- Provide a quick summary of what the model is/does. -->
<!--This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).-->
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model is a continual learning version of Aguie_v0.1
### Trained Data
- 3,000,000 inst data
### License
This model is licensed under the cc-by-nc-nd-4.0. |
QuantumIntelligence/QI-mistral-7B-slerp | QuantumIntelligence | "2024-04-11T11:58:19Z" | 1,106 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"Korean",
"Mistral-7B",
"LLM",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-09T04:11:06Z" | ---
license: apache-2.0
tags:
- merge
- Korean
- Mistral-7B
- LLM
---
# QI-mistral-7B-slerp
This model is based on the mistral model and merged several DPO fine-tuned models with SLERP.
It processes Korean language relatively well, so it is useful when creating various applications.
QI-mistral-7B-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
## ๐งฉ Configuration
```yaml
slices:
- sources:
- model: OpenPipe/mistral-ft-optimized-1218
layer_range: [0, 32]
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
### Basic Usage
```
from transformers import AutoModelForCausalLM, AutoTokenizer, GPTQConfig
import transformers
import torch
model_id = "QuantumIntelligence/QI-mistral-7B-slerp"
tokenizer = AutoTokenizer.from_pretrained(model_id)
# model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_8bit=True) # quantization
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
tokenizer=tokenizer,
)
prompt = """Classify the text into neutral, negative or positive.
Text: This movie is definitely one of my favorite movies of its kind. The interaction between respectable and morally strong characters is an ode to chivalry and the honor code amongst thieves and policemen.
Sentiment:
"""
outputs = pipeline(prompt, max_new_tokens=6)
print(outputs[0]["generated_text"])
```
### Using Korean
- Sentiment
```
# prompt = """
# ๋ค์ ํ
์คํธ๋ฅผ ์ค๋ฆฝ, ๋ถ์ , ๊ธ์ ์ผ๋ก ๋ถ๋ฅํด์ค.
# ํ
์คํธ: ํ๋์ ๋ณด๋ ๋น๊ฐ ์ฌ๋ฏ ํ๋ค. ์ฐ์ธํ ๊ธฐ๋ถ์ด ๋ค์ด์ ์ ์ ํ์ ํ ๊น ๊ณ ๋ฏผ์ค์ธ๋ฐ ๊ฐ์ด ๋ง์ค ์ฌ๋์ด ์๋ค.
# ๊ฐ์ :
# """
outputs = pipeline(prompt, max_new_tokens=6)
print(outputs[0]["generated_text"])
#
```
- Summarization
```
prompt = """
์ด์์ (ํ๊ตญ ํ์: ๆ่่ฃ, 1545๋
4์ 28์ผ (์๋ ฅ 3์ 8์ผ) ~ 1598๋
12์ 16์ผ (์๋ ฅ 11์ 19์ผ))์ ์กฐ์ ์ค๊ธฐ์ ๋ฌด์ ์ด์๋ค. ๋ณธ๊ด์ ๋์(ๅพทๆฐด), ์๋ ์ฌํด(ๆฑ่ซง), ์ํธ๋ ์ถฉ๋ฌด(ๅฟ ๆญฆ)์์ผ๋ฉฐ, ํ์ฑ ์ถ์ ์ด์๋ค. ๋ฌธ๋ฐ ๊ฐ๋ฌธ ์ถ์ ์ผ๋ก 1576๋
(์ ์กฐ 9๋
) ๋ฌด๊ณผ(ๆญฆ็ง)์ ๊ธ์ [2]ํ์ฌ ๊ทธ ๊ด์ง์ด ๋๊ตฌ๋น๋ณด ๊ถ๊ด, ํ๋ จ์ ๋ด์ฌ, ๋ฐํฌ์ง ์๊ตฐ๋งํธ, ์กฐ์ฐ๋ณด ๋งํธ, ์ ๋ผ๋จ๋์์ฌ๋ฅผ ๊ฑฐ์ณ ์ ํ๋๋ถ ์ผ๋์๊ตฐํต์ ์ฌ์ ์ด๋ฅด๋ ๋ค.
ํจ๊ฒฝ๋ ๋๊ตฌ๋น๋ณด๊ถ๊ด(่ฃไป้ๅ กๆฌ็ฎก), 1581๋
๋ฐํฌ ์๊ตฐ๋งํธ(้ขๆตฆๆฐด่ป่ฌๆถ)๊ฐ ๋์๋ค๊ฐ ์ ๋ผ๋จ์์์ ์ค๋๋๋ฌด๋ฅผ ๋ฒ ๊ธฐ๋ฅผ ๊ฑฐ์ ํ์ฌ ์ข์์ฌ ์ฑ๋ฐ์ ๋ฏธ์์ ๋ฐ๊ธฐ๋ ํ๋ค. ์ดํ 1584๋
๋จ๋ณ์ฌ์ ๊ตฐ๊ด๊ณผ ๊ฑด์๋ณด๊ถ๊ด, ํ๋ จ์์ฐธ๊ตฐ, 1586๋
์ฌ๋ณต์์ฃผ๋ถ๋ฅผ ๊ฑฐ์ณ ์กฐ์ฐ๋ณด๋งํธ ๊ฒธ ๋
น๋๋์ ์ฌ์(้ ๅฑฑๅ ก่ฌๆถๅ
ผ้นฟๅณถๅฑฏ็ฐไบๅฎ)๋ก ๋ถ์ํ๋ค. ์กฐ์ฐ๋งํธ ๊ฒธ ๋
น๋๋์ฌ์ ์ฌ์ง ์ค 1587๋
(์ ์กฐ 20๋
) 9์์ ์ฌ์ง์กฑ์ ์ฌ์ ๊ธฐ์ต๊ณต๊ฒฉ์ผ๋ก ๋ฒ์ด์ง ๋
น๋๋์ ํฌ์์ ์ด๊ฒผ์ง๋ง ํผํด๊ฐ ์ปค์, ๋ถ๋ณ์ฌ ์ด์ผ์ ํํต์ ๋ฐ๊ณ ๋ฐฑ์์ข
๊ตฐ(็ฝ่กฃๅพ่ป)ํ๋ ์์น์ ์๊ธฐ๋ ํ๋ค. ๊ทธ ๋ค ๋๋ฒ์งธ ์ฌ์ง์กฑ๊ณผ์ ๊ต์ ์์ ์น์ , ๋ณต์งํ์๋ค. ๊ทธ ๋ค ์ ๋ผ๊ด์ฐฐ์ฌ ์ด๊ด(ๆๆดธ)์๊ฒ ๋ฐํ๋์ด ์ ๋ผ๋ ์กฐ๋ฐฉ์ฅ, ์ ์ ๊ด ๋ฑ์ ์ญ์ํ๋ค. 1589๋
์ ์ํ๊ฐ ์ฌ์ง ์ค ๋ฅ์ฑ๋ฃก์ ์ถ์ฒ์ผ๋ก ๊ณ ์ฌ๋ฆฌ์ฒจ์ฌ(้ซๆฒ้ๅไฝฟ)๊ฐ ๋๊ณ , ์ ์ถฉ์ฅ๊ตฐ(ๆ่กๅฐ่ป), ๋งํฌ์ง์ฒจ์ฌ(ๆปฟๆตฆ้ญๅไฝฟ), ์ง๋๊ตฐ์ ๋ฑ์ ๊ฑฐ์ณ ์ ๋ผ์ข๋์๊ตฐ์ ๋์ฌ๊ฐ ๋์ด ์์ง์๋์ ๋ง๋๊ฒ ๋์๋ค.
์์ง์๋ ๋ ์กฐ์ ์ ์ผ๋์๊ตฐํต์ ์ฌ๊ฐ ๋์ด ๋ถํ๋ค์ ํต์ํ๋ ์ง๋๋ ฅ, ๋ฐ์ด๋ ์ง๋ต, ๊ทธ๋ฆฌ๊ณ ํ์ํ ์ ๋ต๊ณผ ๋ฅ์๋ฅ๋ํ ์ ์ ๋ก ์ผ๋ณธ ์๊ตฐ๊ณผ์ ํด์ ์์ ์ฐ์ ์ฐ์นํด ๋๋ผ๋ฅผ ๊ตฌํ ์ฑ์
(่้)์ผ๋ก ์ถ์๋ฐ๊ณ ์๋ค. ๋
ธ๋ ํด์ ์์ ์ ์ฌํ ๋ค ์ ๋ฌด๊ณต์ 1๋ฑ๊ด์ ์ถ๋ก๋๊ณ ์ฆ ์์ ๋ถ์ฐ์์ ์ ์ถ์ฆ๋๊ณ ๋ํ๊ตฐ์ ์ถ๋ด๋์๋ค๊ฐ, ๊ดํด๊ตฐ ๋ ๋ค์ ์ฆ ์์ ๋ถ์ข์์ ์ ์ถ์ฆ๋๊ณ ๋ํ๋ถ์๊ตฐ์ ์ถ๋ด๋์๊ณ , ์ ์กฐ ๋์๋ ์ฆ ์์ ๋ถ์์์ ์ผ๋ก ๊ฐ์ฆ(ๅ ่ด)๋์๋ค.
๊ณ ๋ ค ๋ ์ 5ํ ์ค๋์ฅ(ไธญ้ๅฐ)์ ์ง๋ธ ๋์ ์ด์จ์ ์์กฐ ์ด๋์(ๆๆฆๅฎ)์ 12๋์์ด๋ฉฐ, ์กฐ์ ์ด ์์ค์ถ๋ถ์ฌ(้ ไธญๆจๅบไบ)๋ฅผ ์ง๋ธ ์ด๋ณ(ๆ้)[3]์ ํ์์ด๋ค. ์ธ๊ฐ๋ ์ด๊ณ ๋ณ์จ(ๅๆฐ), ์ฒ๊ฐ๋ ์จ์ ๋ฐฉ์จ(ๆนๆฐ, ๋น์์๋ ์์ฃผ ๋ฐฉ์จ)์ด๋ค. ๊ทธ์ ๋ฌ๋ ์ถฉ์ฒญ๋จ๋ ์์ฐ์์ ์๋ค.
์ ๋ฌธ์ฅ์ 300์๋ด๋ก ์์ฝํด์ค.
์์ฝ:
"""
outputs = pipeline(prompt, max_new_tokens=300, do_sample=True, top_k=50, return_full_text = False)
print(outputs[0]["generated_text"])
```
- Question answering
```
prompt = """
๋ค์ ๋ฌธ๋งฅ์ ๋ํด ์๋ ์ง๋ฌธ์ ๋ํด ๋ตํด์ค.
๋ฌธ๋งฅ: 1565๋
์ด์์ ์ ๋ฐฉ์จ(ๆนๆฐ)์ ํผ์ธํ๊ณ ๋ณด์ฑ๊ตฐ์๋ฅผ ์ง๋ธ ์ฅ์ธ ๋ฐฉ์ง์ ํ์์ผ๋ก ๋ณํ์ ๋ฐฐ์ฐ๋ฉด์ ๋ฌด๊ณผ(ๆญฆ็ง)๋ฅผ ์ค๋นํ์๋ค. 28์ด์ด๋ 1572๋
(์ ์กฐ 5๋
) ํ๋ จ์ ๋ณ๊ณผ(่จ้ฌ้ข ๅฅ็ง)์ ์์ํ์ผ๋ ์ํ์ ๋ณด๋ ์ค, ๋ง์์ ๋๋งํ์ฌ ์ฃผ๋ณ ์ฌ๋๋ค์ด ๊ธฐ์ ํ ์ค ์์์ผ๋ ์์ ์๋ ๋ฒ๋๋๋ฌด ๊ป์ง์ ๋ฒ๊ฒจ ๋ค๋ฆฌ๋ฅผ ๋์ฌ๋งค๊ณ ์ํ์ ๋๊น์ง ์น๋ ๋ค. ํ์ง๋ง ๊ฒฐ๊ตญ ์ํ์์๋ ๋๋ฐฉํ๊ณ ๋ง๋ค.
์ง๋ฌธ: ์ด์์ ์ 28์ด์ ๋ฌด๊ณผ์ ํฉ๊ฒฉํ๋๊ฐ?
๋๋ต:
"""
outputs = pipeline(prompt, max_new_tokens=30, do_sample=True, top_k=50, return_full_text = False)
generated_text = outputs[0]["generated_text"]
print(generated_text)
# ์๋์, 28์ด์ ๋ฌด๊ณผ์ ํฉ๊ฒฉํ์ง ๋ชปํ์๋ค.
```
- Chatbot style
```
messages = [{"role": "user", "content": "์ข์ ์ทจ๋ฏธ๋ฅผ ๊ฐ์ง๋ ค๋ฉด ์ด๋ป๊ฒ ํ๋์?"}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=512, do_sample=True, temperature=0.7, top_k=50, top_p=0.95, return_full_text = False)
generated_text = outputs[0]["generated_text"]
print(generated_text)
```
### For Development
The support of GPU computing resource is required for the development and implementation of state-of-the-art models.
I would appreciate if anyone could help.
Email: [email protected] |
Habana/albert-large-v2 | Habana | "2024-02-20T23:53:51Z" | 1,105 | 0 | null | [
"optimum_habana",
"license:apache-2.0",
"region:us"
] | null | "2022-04-22T18:05:07Z" | ---
license: apache-2.0
---
[Optimum Habana](https://github.com/huggingface/optimum-habana) is the interface between the Hugging Face Transformers and Diffusers libraries and Habana's Gaudi processor (HPU).
It provides a set of tools enabling easy and fast model loading, training and inference on single- and multi-HPU settings for different downstream tasks.
Learn more about how to take advantage of the power of Habana HPUs to train and deploy Transformers and Diffusers models at [hf.co/hardware/habana](https://huggingface.co/hardware/habana).
## ALBERT Large model HPU configuration
This model only contains the `GaudiConfig` file for running the [albert-large-v2](https://huggingface.co/albert-large-v2) model on Habana's Gaudi processors (HPU).
**This model contains no model weights, only a GaudiConfig.**
This enables to specify:
- `use_torch_autocast`: whether to use PyTorch's autocast mixed precision
- `use_fused_adam`: whether to use Habana's custom AdamW implementation
- `use_fused_clip_norm`: whether to use Habana's fused gradient norm clipping operator
## Usage
The model is instantiated the same way as in the Transformers library.
The only difference is that there are a few new training arguments specific to HPUs.
[Here](https://github.com/huggingface/optimum-habana/blob/main/examples/question-answering/run_qa.py) is a question-answering example script to fine-tune a model on SQuAD. You can run it with ALBERT Large with the following command:
```bash
python run_qa.py \
--model_name_or_path albert-large-v2 \
--gaudi_config_name Habana/albert-large-v2 \
--dataset_name squad \
--do_train \
--do_eval \
--per_device_train_batch_size 32 \
--per_device_eval_batch_size 4 \
--learning_rate 5e-5 \
--num_train_epochs 2 \
--max_seq_length 384 \
--doc_stride 128 \
--output_dir /tmp/squad/ \
--use_habana \
--use_lazy_mode \
--throughput_warmup_steps 3 \
--bf16
```
Check the [documentation](https://huggingface.co/docs/optimum/habana/index) out for more advanced usage and examples.
|
stablediffusionapi/realistic-vision-v13 | stablediffusionapi | "2023-09-08T09:12:25Z" | 1,105 | 10 | diffusers | [
"diffusers",
"stablediffusionapi.com",
"stable-diffusion-api",
"text-to-image",
"ultra-realistic",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-02-01T19:53:20Z" | ---
license: creativeml-openrail-m
tags:
- stablediffusionapi.com
- stable-diffusion-api
- text-to-image
- ultra-realistic
pinned: true
---
# API Inference
## Get API Key
Get API key from [Stable Diffusion API](http://stablediffusionapi.com/), No Payment needed.
Replace Key in below code, change **model_id** to "realistic-vision-v13"
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://stablediffusionapi.com/docs)
Model link: [View model](https://stablediffusionapi.com/models/realistic-vision-v13)
Credits: [View credits](https://civitai.com/?query=model_search)
View all models: [View Models](https://stablediffusionapi.com/models)
```python
import requests
import json
url = "https://stablediffusionapi.com/api/v4/dreambooth"
payload = json.dumps({
"key": "Your_API_key",
"model_id": "realistic-vision-v13",
"prompt": "actual 8K portrait photo of gareth person, portrait, happy colors, bright eyes, clear eyes, warm smile, smooth soft skin, big dreamy eyes, beautiful intricate colored hair, symmetrical, anime wide eyes, soft lighting, detailed face, by makoto shinkai, stanley artgerm lau, wlop, rossdraws, concept art, digital painting, looking into camera",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"safety_checker": "no",
"enhance_prompt": "yes",
"seed": None,
"guidance_scale": 7.5,
"multi_lingual": "no",
"panorama": "no",
"self_attention": "no",
"upscale": "no",
"embeddings": "embeddings_model_id",
"lora": "lora_model_id",
"webhook": None,
"track_id": None
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
Use this coupon code to get 25% off DMGG0RBN
|
larryvrh/Yi-34B-200K-Llamafied | larryvrh | "2024-06-25T16:51:55Z" | 1,105 | 14 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"zh",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-07T01:21:36Z" | ---
language:
- zh
- en
license: apache-2.0
---
Llamafied version of 01-ai's [Yi-34B-200k](https://huggingface.co/01-ai/Yi-34B-200K) for ease of use.
## Model Performance
| Model | MMLU | CMMLU | C-Eval | GAOKAO | BBH | Common-sense Reasoning | Reading Comprehension | Math & Code |
| :------------ | :------: | :------: | :------: | :------: | :------: | :--------------------: | :-------------------: | :---------: |
| | 5-shot | 5-shot | 5-shot | 0-shot | 3-shot@1 | - | - | - |
| LLaMA2-34B | 62.6 | - | - | - | 44.1 | 69.9 | 68.0 | 26.0 |
| LLaMA2-70B | 68.9 | 53.3 | - | 49.8 | 51.2 | 71.9 | 69.4 | 36.8 |
| Baichuan2-13B | 59.2 | 62.0 | 58.1 | 54.3 | 48.8 | 64.3 | 62.4 | 23.0 |
| Qwen-14B | 66.3 | 71.0 | 72.1 | 62.5 | 53.4 | 73.3 | 72.5 | **39.8** |
| Skywork-13B | 62.1 | 61.8 | 60.6 | 68.1 | 41.7 | 72.4 | 61.4 | 24.9 |
| InternLM-20B | 62.1 | 59.0 | 58.8 | 45.5 | 52.5 | 78.3 | - | 30.4 |
| Aquila-34B | 67.8 | 71.4 | 63.1 | - | - | - | - | - |
| Falcon-180B | 70.4 | 58.0 | 57.8 | 59.0 | 54.0 | 77.3 | 68.8 | 34.0 |
| Yi-6B | 63.2 | 75.5 | 72.0 | 72.2 | 42.8 | 72.3 | 68.7 | 19.8 |
| Yi-6B-200K | 64.0 | 75.3 | 73.5 | 73.9 | 42.0 | 72.0 | 69.1 | 19.0 |
| **Yi-34B** | **76.3** | **83.7** | 81.4 | 82.8 | **54.3** | **80.1** | 76.4 | 37.1 |
| Yi-34B-200K | 76.1 | 83.6 | **81.9** | **83.4** | 52.7 | 79.7 | **76.6** | 36.3 |
While benchmarking open-source models, we have observed a disparity between the
results generated by our pipeline and those reported in public sources (e.g.
OpenCompass). Upon conducting a more in-depth investigation of this difference,
we have discovered that various models may employ different prompts,
post-processing strategies, and sampling techniques, potentially resulting in
significant variations in the outcomes. Our prompt and post-processing strategy
remains consistent with the original benchmark, and greedy decoding is employed
during evaluation without any post-processing for the generated content. For
scores that were not reported by the original authors (including scores reported
with different settings), we try to get results with our pipeline.
To evaluate the model's capability extensively, we adopted the methodology
outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande,
ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ
were incorporated to evaluate reading comprehension. CSQA was exclusively tested
using a 7-shot setup, while all other tests were conducted with a 0-shot
configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1),
HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Due
to technical constraints, we did not test Falcon-180 on QuAC and OBQA; the score
is derived by averaging the scores on the remaining tasks. Since the scores for
these two tasks are generally lower than the average, we believe that
Falcon-180B's performance was not underestimated.
## Usage
Please visit our [github repository](https://github.com/01-ai/Yi) for general
guidance on how to use this model.
## Disclaimer
Although we use data compliance checking algorithms during the training process
to ensure the compliance of the trained model to the best of our ability, due to
the complexity of the data and the diversity of language model usage scenarios,
we cannot guarantee that the model will generate correct and reasonable output
in all scenarios. Please be aware that there is still a risk of the model
producing problematic outputs. We will not be responsible for any risks and
issues resulting from misuse, misguidance, illegal usage, and related
misinformation, as well as any associated data security concerns.
## License
The Yi series models are fully open for academic research and free commercial
usage with permission via applications. All usage must adhere to the [Model
License Agreement 2.0](https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE). To
apply for the official commercial license, please contact us
([[email protected]](mailto:[email protected])). |
athirdpath/Nethena-20b-Glued | athirdpath | "2023-11-14T09:19:59Z" | 1,105 | 4 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-12T06:43:09Z" | ---
license: cc-by-nc-4.0
---
This is [NeverSleep/Nethena-20B](https://huggingface.co/NeverSleep/Nethena-20B) with [athirdpath/Nethena-20b-Glue-LORA](https://huggingface.co/athirdpath/Nethena-20b-Glue-LORA) applied.
athirdpath/Nethena-20b-Glue-LORA is a 128 rank LORA for RP, trained on a private dataset. It is unalligned and NSFW-oriented.
This is a test, exploring the effects of "gluing" the components of the 20b model together to reduce the iconic word replacement errors, increase lucidity, and improve recall.
The private ~500k token dataset used to train the LORA was Alpaca formatted and focused on 4 primary categories:
- Medical texts (on psychology, reproductive organs, anatomy, and pregnancy). These are formatted so the model, in character as a doctor or therapist, answers a patient's question in short to medium form.
- Excerpts from short stories and novellas (erotic and romantic) centered around both realistic and fantastic situations, covering several fetishes as well. These are sliced into ~2048 token chunks, and these long-form responses are all tied to the command โEnter narrator mode.โ in the instructions.
- A selection from PIPPA, using a wide keyword search for tokens associated with low quality human or AI data to remove those responses, then a positive search was done for words and phrases associated with a higher reading level. These are converted to Alpaca with โEnter RP mode.โ in all the instruction fields.
- ~18k tokens of GPT-4 generated data on role-playing from various charactersโ perspectives, focusing on different situations and emotions. Includes many multi-turn conversations.
So far it is passing subjective testing with flying colors, objective numbers coming soon.
Trained with Alpaca-style prompts. |
Edentns/DataVortexM-7B-Instruct-v0.1 | Edentns | "2024-02-24T14:19:16Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"ko",
"dataset:beomi/KoAlpaca-v1.1a",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-04T00:21:22Z" | ---
tags:
- text-generation
license: cc-by-nc-sa-4.0
language:
- ko
base_model: mistralai/Mistral-7B-Instruct-v0.2
pipeline_tag: text-generation
datasets:
- beomi/KoAlpaca-v1.1a
---
# **DataVortexM-7B-Instruct-v0.1**
<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;">
## Our Team
| Research & Engineering | Product Management |
| :--------------------: | :----------------: |
| Kwangseok Yang | Seunghyun Choi |
| Jeongwon Choi | Hyoseok Choi |
## **Model Details**
### **Base Model**
[mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
### **Trained On**
- **OS**: Ubuntu 20.04
- **GPU**: H100 80GB 4ea
- **transformers**: v4.36.2
### **Dataset**
- [beomi/KoAlpaca-v1.1a](https://huggingface.co/datasets/beomi/KoAlpaca-v1.1a)
### **Instruction format**
It follows **Alpaca** format.
E.g.
```python
text = """\
๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค.
### Instruction:
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?
### Response:
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค.
### Instruction:
์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?
"""
```
## **Model Benchmark**
### **[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**
On Benchmarking ...
| Task | 0-shot | 5-shot | 10-shot | 50-shot |
| :--------------- | -----: | -----: | ------: | ------: |
| kobest_boolq | 0.0 | 0.0 | 0.0 | 0.0 |
| kobest_copa | 0.0 | 0.0 | 0.0 | 0.0 |
| kobest_hellaswag | 0.0 | 0.0 | 0.0 | 0.0 |
| kobest_sentineg | 0.0 | 0.0 | 0.0 | 0.0 |
### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
| 39.81 | 34.13 | 42.35 | 38.73 | 45.46 | 38.37 |
## **Implementation Code**
This model contains the chat_template instruction format.
You can use the code below.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexM-7B-Instruct-v0.1")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexM-7B-Instruct-v0.1")
messages = [
{"role": "system", "content": "๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค."},
{"role": "user", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?"},
{"role": "assistant", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค."},
{"role": "user", "content": "์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## **License**
The model is licensed under the [cc-by-nc-sa-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license, which allows others to copy, modify, and share the work non-commercially, as long as they give appropriate credit and distribute any derivative works under the same license.
<div align="center">
<a href="https://edentns.com/">
<img src="./Logo.png" alt="Logo" style="height: 3em;">
</a>
</div>
|
kodonho/llama2-chat-koalpaca | kodonho | "2024-01-12T01:54:43Z" | 1,105 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"ko",
"dataset:beomi/KoAlpaca-v1.1a",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-06T11:00:56Z" | ---
license: llama2
datasets:
- beomi/KoAlpaca-v1.1a
language:
- ko
---
# Llama2 based model with koalapaca dataset
This is an English, Korean Model based on
* [meta-llama/Llama-2-7b-chat-hf] |
cocoirun/Yi-Ko-6B-instruct-v2.0 | cocoirun | "2024-01-18T09:09:54Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-18T08:50:35Z" | ---
license: cc-by-sa-4.0
---
<h1>instruct ๋ชจ๋ธ v2.0</h1>
<b><ํ์ต ๋ฐ์ดํฐ ๊ตฌ์ถ></b>
Open-Orca-ko ๋ฐ์ดํฐ๋ฅผ ๋ถ์ํ์ฌ ํ์คํฌ๋ฅผ ์ถ์ถํ ๋ค
ํด๋น ํ์คํฌ์ ๋ง์ถฐ์ NLP ๊ด๋ จ ์คํ์์ค ๋ฐ์ดํฐ๋ฅผ ํ์ฉํ์ฌ ํ์ต๋ฐ์ดํฐ๋ฅผ ์์ฒด์ ์ผ๋ก
์ฝ 4๋ง๊ฑด(์ญ์ฌ, ๊ณผํ, ์ํ, ๊ธฐ๊ณ๋
ํด, ๋ฆฌ๋ทฐ ๋ถ์) ๊ตฌ์ถํ์๊ณ ,
๊ทธ ์ธ์ Open-Orca-Ko์์ ๋ฐ์ดํฐ๋ฅผ ์ผ๋ถ ํํฐ๋งํ์ฌ ์ ์ ํด๊ฑฐ๋ KoBEST ๋ฐ์ดํฐ๋ฅผ ํจ๊ป ์ถ๊ฐํ์์ต๋๋ค.
aihub ์ผ๋ฐ์์ ๋ฐ ๊ธฐ๊ณ๋
ํด ๋ฐ์ดํฐ๋ฅผ ํ์ฉํ์ฌ ์ถ๊ฐ๋ก ํ์ต ๋ฐ์ดํฐ๋ฅผ ๊ตฌ์ถ(ํํ์ ๊ด๋ จ, ๊ธฐ๊ณ๋
ํด ๊ด๋ จ ๋ฐ ์์ฝ)
๊ฐ์ข
๋ธ๋ก๊ทธ์์ ์ญ์ฌ ๋ฐ ์์ ํด์ฆ๋ฅผ ์ฌ๋์ด ์ง์ ํ์ต๋ฐ์ดํฐ ํํ๋ก ๋ณ๊ฒฝ
AI2AI Challenge ๋ฐ์ดํฐ๋ฅผ ํํ๊ณ ๋ฅผ ํตํด ๋ฒ์ญ ๋ฐ ์ค์ญ๋ ๋ถ๋ถ์ ์ฌ๋์ด ์ง์ ์์ ํ๋ ์์
์ ์ํ
์์ด ๋ฒ์ญ ๋ฐ์ดํฐ ์ํ/ํ์ ๋ฐ์ดํฐ ํ์ต ๋ฐ์ดํฐ๋ก ํ์ฉ ์งํ
์ด 11๋ง๊ฐ์ ํ์ต๋ฐ์ดํฐ๋ก sft๋ฅผ ์งํํ์์ต๋๋ค.
<br>
ํ์ฌ, ์๋ก์ด ๋ฒ์ ์ ๋ชจ๋ธ ํ์ต ๋ฐ ์ฑ๋ฅ์ ์ํด Open-Orca ๋ฐ์ดํฐ์
์ผ๋ถ๋ฅผ ๋ฒ์ญํ์ฌ ์ ์ ์ค์ ์์ต๋๋ค.
<br>
+ ๊ณ ๋ฑํ๊ต ์ญ์ฌ ๋ฌธ์ ๋ฐ TruthfulQA ๊ด๋ จ ๋ฌธ์ ์ถ๊ฐ๋ฅผ ์งํํ์์ต๋๋ค.
+ ๊ฐ์ข
it ์ง์ ๋ฐ์ดํฐ ์ถ๊ฐ์งํ.
+ ๊ธฐ๊ณ๋
ํด ๊ด๋ จ ํ์ต ๋ฐ์ดํฐ๋ฅผ ChatGPT๋ฅผ ํตํด์ ๋ต๋ณ์ ์ป์ด ํ์ต
+ ๋ฌธ๋ฒ๊ด๋ จ ํ์ต ๋ฐ์ดํฐ
<br>
###ํ์ต ๋ฐ์ดํฐ ํ์ผ์ ๋น๊ณต๊ฐ์
๋๋ค.
<br>
<b><ํ์ต></b>
ํ์ต์ LoRA๋ฅผ ์ฌ์ฉํ์ฌ A100 40G *2์์ ํ์ต์ ์งํํ์์ต๋๋ค. |
DopeorNope/Mistralopithecus-v0.1-10.8B | DopeorNope | "2024-01-20T03:03:26Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-19T17:05:44Z" | ---
license: cc-by-nc-sa-4.0
---
## Model Details
**Model Developers** Seungyoo Lee (DopeorNope)
์ด ๋ชจ๋ธ์ Mistral Base์ ์๋ก์ด ์ํคํ
์ณ์ด๋ฉฐ, 10.7B์ ํ๋ผ๋ฏธํฐ๋ก ๊ตฌ์ฑ๋์์ต๋๋ค. (Solar๋, ์๋ํธ๋ผ ๋ฒ ์ด์ค ๋ชจ๋ธ์ด ์๋๋๋ค.)
์ฝ 1.5B์ ํ ํฐ์ผ๋ก pretrain ๋์์ผ๋, ์คํ๋จ๊ณ๋ก ํฅํ ๋ค์ ํ๋ จ๋์ด ์๋กญ๊ฒ ๋์ฌ ์์ ์
๋๋ค.
ํ
์คํธ์ฉ์ผ๋ก ์ฌ๋ ค๋ด
๋๋ค.
Context length๊ฐ 32k ๊น์ง์ง์ ๊ฐ๋ฅํ ๋ชจ๋ธ์ด๋ฉฐ, ํฅํ ๋ ์๋ฒฝํ๊ฒ ์ค๊ณํ์ฌ ์ฌ๋ฆฌ๋๋ก ํ๊ฒ ์ต๋๋ค.
|
GAI-LLM/OPEN-SOLAR-KO-10.7B-mixed-v15 | GAI-LLM | "2024-01-23T07:01:56Z" | 1,105 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"ko",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-23T02:15:59Z" | ---
license: cc-by-nc-4.0
language:
- ko
library_name: transformers
pipeline_tag: text-generation
---
**The license is `cc-by-nc-4.0`.**
# **GAI-LLM/OPEN-SOLAR-KO-10.7B-mixed-v15**
## Model Details
**Model Developers** Donghoon Oh, Hanmin Myung, Eunyoung Kim (SK C&C G.AI Eng)
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture**
GAI-LLM/OPEN-SOLAR-KO-10.7B-mixed-v15 is an auto-regressive language model based on the LLaMA2 transformer architecture.
**Base Model** [beomi/OPEN-SOLAR-KO-10.7B](https://huggingface.co/beomi/OPEN-SOLAR-KO-10.7B)
**Training Dataset**
- We combined Open Korean Dateset using mixed-strategy
- We use A100 GPU 80GB * 8, when training.
# **Model Benchmark**
## KO-LLM leaderboard
- Follow up as [Open KO-LLM LeaderBoard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard).
# Implementation Code
```python
### GAI-LLM/OPEN-SOLAR-KO-10.7B-mixed-v15
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "GAI-LLM/OPEN-SOLAR-KO-10.7B-mixed-v15"
model = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)
``` |
ITT-AF/ITT-42dot_LLM-PLM-1.3B-v1.0 | ITT-AF | "2024-02-14T06:34:36Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-25T16:25:47Z" | ---
license: cc-by-nc-4.0
---
# ITT-AF/ITT-42dot_LLM-PLM-1.3B-v1.0
This model is a fine-tuned version of [42dot/42dot_LLM-PLM-1.3B](https://huggingface.co/42dot/42dot_LLM-PLM-1.3B) on an custom dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 24
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.0.0
- Tokenizers 0.15.0 |
Edentns/DataVortexS-10.7B-dpo-v1.4 | Edentns | "2024-02-24T14:17:27Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"ko",
"base_model:yanolja/Bookworm-10.7B-v0.4-DPO",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-26T00:47:24Z" | ---
tags:
- text-generation
license: cc-by-nc-4.0
language:
- ko
base_model: yanolja/Bookworm-10.7B-v0.4-DPO
pipeline_tag: text-generation
---
# **DataVortexS-10.7B-dpo-v1.4**
<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;">
## Our Team
| Research & Engineering | Product Management |
| :--------------------: | :----------------: |
| Kwangseok Yang | Seunghyun Choi |
| Jeongwon Choi | Hyoseok Choi |
## **Model Details**
### **Base Model**
[yanolja/Bookworm-10.7B-v0.4-DPO](https://huggingface.co/yanolja/Bookworm-10.7B-v0.4-DPO)
### **Trained On**
- **OS**: Ubuntu 22.04
- **GPU**: H100 80GB 4ea
- **transformers**: v4.36.2
### **Instruction format**
It follows **ChatML** format.
E.g.
```python
text = """\
<|im_start|>system
๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค.<|im_end|>
<|im_start|>user
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?<|im_end|>
<|im_start|>assistant
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค.<|im_end|>
<|im_start|>user
์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?<|im_end|>
<|im_start|>assistant
"""
```
## **Model Benchmark**
### **[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**
| Task | 0-shot | 5-shot | 10-shot | 50-shot |
| :--------------- | -----------: | -----------: | -----------: | -----------: |
| kobest_boolq | 0.757911 | 0.907177 | 0.924496 | 0.605075 |
| kobest_copa | 0.740605 | 0.801886 | 0.831886 | 0.849978 |
| kobest_hellaswag | 0.445176 | 0.454788 | 0.468654 | 0.45218 |
| kobest_sentineg | 0.415445 | 0.95214 | 0.962217 | 0.967254 |
| **Average** | **0.589784** | **0.778998** | **0.796813** | **0.718622** |
### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
| 53.81 | 52.05 | 62.93 | 53.59 | 50.42 | 50.06 |
## **Implementation Code**
This model contains the chat_template instruction format.
You can use the code below.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.4")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.4")
messages = [
{"role": "system", "content": "๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค."},
{"role": "user", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?"},
{"role": "assistant", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค."},
{"role": "user", "content": "์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## **License**
This model is licensed under the [cc-by-nc-4.0](https://creativecommons.org/licenses/by-nc/4.0/). which allows others to share and adapt the model for non-commercial purposes.
<div align="center">
<a href="https://edentns.com/">
<img src="./Logo.png" alt="Logo" style="height: 3em;">
</a>
</div>
|
Edentns/DataVortexS-10.7B-dpo-v1.10 | Edentns | "2024-02-24T14:16:33Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"ko",
"base_model:beomi/OPEN-SOLAR-KO-10.7B",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-01T07:02:25Z" | ---
tags:
- text-generation
license: cc-by-nc-4.0
language:
- ko
base_model: beomi/OPEN-SOLAR-KO-10.7B
pipeline_tag: text-generation
---
# **DataVortexS-10.7B-dpo-v1.10**
<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;">
## Our Team
| Research & Engineering | Product Management |
| :--------------------: | :----------------: |
| Kwangseok Yang | Seunghyun Choi |
| Jeongwon Choi | Hyoseok Choi |
## **Model Details**
### **Base Model**
[beomi/OPEN-SOLAR-KO-10.7B](https://huggingface.co/beomi/OPEN-SOLAR-KO-10.7B)
### **Trained On**
- **OS**: Ubuntu 22.04
- **GPU**: H100 80GB 4ea
- **transformers**: v4.36.2
### **Instruction format**
It follows **Alpaca (Chat)** format.
E.g.
```python
text = """\
### System:
๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค.
### User:
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?
### Assistant:
๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค.
### User:
์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?
"""
```
## **Model Benchmark**
### **[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)**
| Task | 0-shot | 5-shot | 10-shot | 50-shot |
| :--------------- | -----------: | -----------: | -----------: | -----------: |
| kobest_boolq | 0.874261 | 0.897165 | 0.904985 | 0.907857 |
| kobest_copa | 0.807479 | 0.845701 | 0.860809 | 0.8719 |
| kobest_hellaswag | 0.504865 | 0.502074 | 0.50717 | 0.51609 |
| kobest_sentineg | 0.409404 | 0.967251 | 0.992443 | 0.982367 |
| **Average** | **0.649002** | **0.803048** | **0.816352** | **0.819553** |
### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
| 56.32 | 54.27 | 63.16 | 49.95 | 55.08 | 59.15 |
## **Implementation Code**
This model contains the chat_template instruction format.
You can use the code below.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.10")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.10")
messages = [
{"role": "system", "content": "๋น์ ์ ์ฌ๋๋ค์ด ์ ๋ณด๋ฅผ ์ฐพ์ ์ ์๋๋ก ๋์์ฃผ๋ ์ธ๊ณต์ง๋ฅ ๋น์์
๋๋ค."},
{"role": "user", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์ด๋์ผ?"},
{"role": "assistant", "content": "๋ํ๋ฏผ๊ตญ์ ์๋๋ ์์ธ์
๋๋ค."},
{"role": "user", "content": "์์ธ ์ธ๊ตฌ๋ ์ด ๋ช ๋ช
์ด์ผ?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## **License**
This model is licensed under the [cc-by-nc-4.0](https://creativecommons.org/licenses/by-nc/4.0/). which allows others to share and adapt the model for non-commercial purposes.
<div align="center">
<a href="https://edentns.com/">
<img src="./Logo.png" alt="Logo" style="height: 3em;">
</a>
</div>
|
mu0gum/AIFT-polyglot-ko-1.3b-ao-instruct-v0.91 | mu0gum | "2024-02-14T06:28:51Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"gpt_neox",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-08T17:09:40Z" | ---
license: cc-by-nc-4.0
---
# AIFT-polyglot-ko-1.3b-ao-instruct-v0.91
๋ฒ ์ด์ค ๋ชจ๋ธ : EleutherAI/polyglot-ko-1.3b
ํ์ต ๋ฐ์ดํฐ : ์์ฒด ์ ์ํ Open Orca ์คํ์ผ ๋ฐ์ดํฐ์
์ฝ 48,000๊ฑด (์ค๋ณต ์ ๊ฑฐ ๋ฐ ๋ฐ์ดํฐ ๋ถํฌ ์กฐ์ )
ํ์ต ๋ฐฉ๋ฒ : Full finetuning
epoch : 3
## ko-lm-evaluation-harness(5-shot)
|kobest_boolq|kobest_copa|kobest_hellaswag|pawsx_ko|
|--|--|--|--|
|0.5398860398860399|0.71|0.436|0.476|
## Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.0.0
- Tokenizers 0.15.0 |
c1park/kosolra-kullm-LDCC-merge | c1park | "2024-03-05T05:19:30Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"ko",
"en",
"dataset:nlpai-lab/kullm-v2",
"base_model:LDCC/LDCC-SOLAR-10.7B",
"base_model:realPCH/kosolra-kullm",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-21T23:30:22Z" | ---
license: mit
datasets:
- nlpai-lab/kullm-v2
base_model:
- LDCC/LDCC-SOLAR-10.7B
- realPCH/kosolra-kullm
language:
- ko
- en
tags:
- merge
- mergekit
---
### Model Strategy
We merged following two model with SLERP method using [mergekit](https://github.com/arcee-ai/mergekit) library.
- [realPCH/kosolra-kullm](https://huggingface.co/realPCH/kosolra-kullm)
- [LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B)
which are both based on [yanolja/KoSOLAR-10.7B-v0.1](https://huggingface.co/yanolja/KoSOLAR-10.7B-v0.1-deprecated).
### Run the model
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "c1park/kosolra-kullm-LDCC-merge"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
text = "[INST] Put instruction here. [/INST]"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
``` |
ENERGY-DRINK-LOVE/leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_DPOv3 | ENERGY-DRINK-LOVE | "2024-03-16T08:19:00Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"dpo",
"generated_from_trainer",
"conversational",
"base_model:ENERGY-DRINK-LOVE/leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-07T09:49:29Z" | ---
license: cc-by-nc-4.0
base_model: ENERGY-DRINK-LOVE/leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: nhn_dpo_v3_leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT_DPO
results: []
---
|
hwkwon/S-SOLAR-10.7B-v1.3 | hwkwon | "2024-03-08T12:10:26Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"ko",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-08T11:54:14Z" | ---
license: cc-by-nc-4.0
language:
- ko
---
# S-SOLAR-10.7B
<!-- Provide a quick summary of what the model is/does. -->
<!--This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).-->
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model is a fine-tuned version of [yanolja/EEVE-Korean-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0).
### Trained Data
TBA
### Prompt Template
```
### User: User query input
### Assistant:
```
### License
This model is licensed under the cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.
|
jylee420/gemma-2b-data-std-v0 | jylee420 | "2024-03-13T01:45:03Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"arxiv:1910.09700",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-13T01:40:51Z" | ---
library_name: transformers
tags: []
license: "other"
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
freewheelin/free-solar-slerp-v0.3 | freewheelin | "2024-03-14T14:18:25Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"base_model:davidkim205/komt-solar-10.7b-sft-v5",
"base_model:colable/LDCC-CCK-slerp",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-13T01:47:30Z" | ---
base_model:
- davidkim205/komt-solar-10.7b-sft-v5
- colable/LDCC-CCK-slerp
library_name: transformers
tags:
- mergekit
- merge
license: mit
---
# free-solar-0.3
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [davidkim205/komt-solar-10.7b-sft-v5](https://huggingface.co/davidkim205/komt-solar-10.7b-sft-v5)
* [colable/LDCC-CCK-slerp](https://huggingface.co/davidkim205/colable/LDCC-CCK-slerp)
|
freewheelin/free-solar-instrunction-v0.3 | freewheelin | "2024-03-15T02:32:32Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ko",
"en",
"arxiv:2312.15166",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-03-15T02:03:42Z" | ---
language:
- ko
- en
license: mit
---
# Model Card for free-solar-instruction-v0.3
## Developed by : [Freewheelin](https://freewheelin-recruit.oopy.io/) AI Technical Team
## Hardware and Software
* **Training Factors**: We fine-tuned this model using the [HuggingFace TRL Trainer](https://huggingface.co/docs/trl/trainer)
## Method
- This model was trained using the learning method introduced in the [SOLAR paper](https://arxiv.org/pdf/2312.15166.pdf).
## Base Model
- [davidkim205/komt-solar-10.7b-sft-v5](https://huggingface.co/davidkim205/komt-solar-10.7b-sft-v5) |
Heoni/Aguie-chat-proto | Heoni | "2024-04-04T12:13:55Z" | 1,105 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"ko",
"en",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-04T10:01:50Z" | ---
license: cc-by-nc-nd-4.0
language:
- ko
- en
---
์์๋ผ๋ฐ๋ฐํ ์์๋ผ๋ฐ๋ฐํ
์์ ๋๋ณด๋ค ๋น ๋ฅด๋ค! ๋ฌด์จ ํจ๋ฅผ ์ก๊ณ ์ถ๋?
์์๋ผ๋ฐ๋ฐํ ์์๋ผ๋ฐ๋ฐํ
๋์ ๋ฒ๊ณ ์ถ๋?
์์๋ผ๋ฐ๋ฐํ ์์๋ผ๋ฐ๋ฐํ
๋ถ์๊ฐ๋๊ณ ์ถ๋?
๋ถ์๊ฐ๋๊ณ ์ถ์ด?
ํํฌํ๋ฉด ๋ํ๋ฏผ๊ตญ์ ๋ฑ ์ธ ๋ช
์ด์ผ. ๊ฒฝ์๋์ ์ง๊ท, ์ ๋ผ๋์ ์๊ท, ๊ธฐ์นด๊ณ ์ ๊ตญ์ ์ผ๋ก ๋! ์์ ์ ์ง๊ท๋ ์๊ท๊ฐ ํํ ๋ถ์๋๋ฐ, ์๊ท๊ฐ ์ง๊ท์ ๊ท๋ฅผ ์งค๋ผ ๋ฒ๋ ธ์ด. ๊ธฐ๋์ ์ง๊ท์ผ
# Aguie-chat-proto
<!-- Provide a quick summary of what the model is/does. -->
<!--This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).-->
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model is a fine-tuned version of LLama2-koen-13b
### Trained Data
- 3,000,000 korean instruction following set
### Prompt Template
```
### Instruction:
### Output:
```
### License
This model is licensed under the cc-by-nc-nd-4.0. |
QuantumIntelligence/QI-neural-chat-7B-ko-DPO | QuantumIntelligence | "2024-04-11T23:36:21Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"Korean",
"LLM",
"Chatbot",
"DPO",
"Intel/neural-chat-7b-v3-3",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-11T13:21:56Z" | ---
license: apache-2.0
library_name: transformers
tags:
- Korean
- LLM
- Chatbot
- DPO
- Intel/neural-chat-7b-v3-3
---
# QI-neural-chat-7B-ko-DPO
This is a fine tuned model based on the [neural-chat-7b-v3-3](https://huggingface.co/Intel/neural-chat-7b-v3-3) with Korean DPO dataset([Oraca-DPO-Pairs-KO](https://huggingface.co/datasets/Ja-ck/Orca-DPO-Pairs-KO)).
It processes Korean language relatively well, so it is useful when creating various applications.
### Basic Usage
```
from transformers import AutoModelForCausalLM, AutoTokenizer, GPTQConfig
import transformers
import torch
model_id = "QuantumIntelligence/QI-neural-chat-7B-ko-DPO"
tokenizer = AutoTokenizer.from_pretrained(model_id)
# model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_8bit=True) # quantization
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
tokenizer=tokenizer,
)
prompt = """Classify the text into neutral, negative or positive.
Text: This movie is definitely one of my favorite movies of its kind. The interaction between respectable and morally strong characters is an ode to chivalry and the honor code amongst thieves and policemen.
Sentiment:
"""
outputs = pipeline(prompt, max_new_tokens=6)
print(outputs[0]["generated_text"])
```
### Using Korean
- Sentiment
```
prompt = """
๋ค์ ํ
์คํธ๋ฅผ ์ค๋ฆฝ, ๋ถ์ , ๊ธ์ ์ผ๋ก ๋ถ๋ฅํด์ค.
ํ
์คํธ: ํ๋์ ๋ณด๋ ๋น๊ฐ ์ฌ๋ฏ ํ๋ค. ์ฐ์ธํ ๊ธฐ๋ถ์ด ๋ค์ด์ ์ ์ ํ์ ํ ๊น ๊ณ ๋ฏผ์ค์ธ๋ฐ ๊ฐ์ด ๋ง์ค ์ฌ๋์ด ์๋ค.
๋ถ๋ฅ:
"""
outputs = pipeline(prompt, max_new_tokens=6)
print(outputs[0]["generated_text"])
```
- Summarization
```
prompt = """
๊ตญ๋ด ์ฐ๊ตฌ์ง์ด ๋ฏธ๊ตญ, ์๊ตญ ๊ณต๋ ์ฐ๊ตฌํ๊ณผ ์ฒญ๊ฐ ๊ธฐ๋ฅ์ ๊ด์ฌํ๋ ๋จ๋ฐฑ์ง ๊ตฌ์กฐ๋ฅผ ๊ท๋ช
ํ๋ค. ๋์ฒญ ์น๋ฃ๋ฒ์ ๊ฐ๋ฐํ๋ ๋ฐ ๋์์ด ๋ ๊ฒ์ผ๋ก ๋ณด์ธ๋ค.
ํฌ์คํ
์ ์กฐ์ค์ ์๋ช
๊ณผํ๊ณผ ๊ต์ ์ฐ๊ตฌํ์ด ๊น๊ดํ ๊ฒฝํฌ๋ ์์ฉํํ๊ณผ ๊ต์ ์ฐ๊ตฌํ, ๋ธ์
ฐ๋ณผ๋ก๋ ์นดํธ๋ฆฌ์น ๋ฏธ๊ตญ ์๋ ์บ๋ฆฌํฌ๋์๋ ๊ต์ ์ฐ๊ตฌํ, ์บ๋กค ๋ก๋น์จ ์๊ตญ ์ฅ์คํผ๋๋ ๊ต์์ ํจ๊ป ์ฒญ๊ฐ ๊ด๋ จ ํน์ ์์ฉ์ฒด ๋จ๋ฐฑ์ง ๊ตฌ์กฐ์ ๋ฉ์ปค๋์ฆ์ ๋ฐํ๋ ๋ฐ ์ฑ๊ณตํ๋ค๊ณ 11์ผ ๋ฐํ๋ค.
๊ท ์์ชฝ์๋ ์๋ฆฌ๋ฅผ ๊ฐ์งํ๋ ๋ฌํฝ์ด๊ด๊ณผ ํํ๊ฐ๊ฐ์ ๋ด๋นํ๋ ์ ์ ๊ธฐ๊ด์ด ์๋ค. ์ด ๊ธฐ๊ด๋ค์ ์ธํฌ๋ค์ ์์ฉ์ฒด ๋จ๋ฐฑ์ง์ธ โGPR156โ์ ๊ฐ๊ณ ์๋ค. GPR156์ด ํ์ฑํ๋๋ฉด ์ธํฌ ๋ด G๋จ๋ฐฑ์ง๊ณผ ๊ฒฐํฉํด ์ ํธ๋ฅผ ์ ๋ฌํ๋ค. G๋จ๋ฐฑ์ง์ โ๊ตฌ์๋ ๋ดํด๋ ์คํ์ด๋-๊ฒฐํฉ ๋จ๋ฐฑ์งโ๋ก ์ ํธ๋ฅผ ์ ๋ฌํ๋ ์ค๊ฐ์๋ค.
GPR156์ ๋ค๋ฅธ ์์ฉ์ฒด์ ๋ฌ๋ฆฌ ํน๋ณํ ์๊ทน์ด ์์ด๋ ํญ์ ๋์ ํ์ฑ์ ์ ์งํ๋ฉฐ ์ฒญ๊ฐ๊ณผ ํํ ๊ธฐ๋ฅ ์ ์ง์ ํฐ ์ญํ ์ ํ๋ค. ์ ์ฒ์ ์ผ๋ก ์ฒญ๊ฐ ์ฅ์ ๊ฐ ์๋ ํ์๋ค์ ์น๋ฃํ๊ธฐ ์ํด์๋ ์ด ๋จ๋ฐฑ์ง์ ๊ตฌ์กฐ์ ์์ฉ ๋ฉ์ปค๋์ฆ์ ์์์ผ ํ๋ค.
์ฐ๊ตฌํ์ ์ด์ ์จ์ ์ํ๋ฏธ๊ฒฝ(Cryo-EM) ๋ถ์๋ฒ์ ์ฌ์ฉํด GPR156๊ณผ GPR156-G๋จ๋ฐฑ์ง ๊ฒฐํฉ ๋ณตํฉ์ฒด๋ฅผ ๊ณ ํด์๋๋ก ๊ด์ฐฐํ๋ค. ์ด๋ฅผ ํตํด ์์ฉ์ฒด๋ฅผ ํ์ฑํํ๋ ์์ฉ์ ์์ด๋ GPR156์ด ๋์ ํ์ฑ์ ์ ์งํ ์ ์๋ ์์ธ์ ์ฐพ์๋ค.
GPR156์ ์ธํฌ๋ง์ ํ๋ถํ ์ธ์ง์ง๊ณผ ๊ฒฐํฉํด ํ์ฑํ๋๋ค. ์ธํฌ์ง์ ์๋ G๋จ๋ฐฑ์ง๊ณผ์ ์ํธ์์ฉ์ ํตํด ์์ฒด์ ์ผ๋ก ๊ตฌ์กฐ๋ฅผ ๋ณํ, ๋์ ํ์ฑ์ ์ ์งํ๋ค๋ ์ฌ์ค๋ ํ์ธ๋๋ค.
๊ธฐ์กด์ ์๋ ค์ง ์์ฉ์ฒด ๋จ๋ฐฑ์ง๋ค๊ณผ ๋ฌ๋ฆฌ GPR156์ ์ธํฌ๋ง์ ํต๊ณผํ๋ 7๋ฒ์งธ ํ๋ฆญ์ค ๋ง๋จ ๋ถ๋ถ์ ๊ตฌ์กฐ๋ฅผ ์ ์ฐํ๊ฒ ๋ฐ๊พธ๋ฉฐ G๋จ๋ฐฑ์ง๊ณผ์ ๊ฒฐํฉ์ ์ ๋ํ๋ค. ์ด๋ฅผ ํตํด ์ ํธ๋ฅผ ํ์ฑํํจ์ผ๋ก์จ ์๋ฆฌ๋ฅผ ๊ฐ์งํ๋ ๋ฐ ๋์์ ์ฃผ์๋ค.
์กฐ ๊ต์๋ โ์ ์ฒ์ ์ผ๋ก ๋์ฒญ๊ณผ ๊ท ํ ๊ฐ๊ฐ ๊ธฐ๋ฅ์ ์ฅ์ ๊ฐ ์๋ ํ์๋ค์ด ๋ง๋คโ๋ฉฐ โ์ด๋ค์ ์ํ ํ๊ธฐ์ ์ธ ์น๋ฃ๋ฒ๊ณผ ์ฝ๋ฌผ ๊ฐ๋ฐ์ ์ด๋ฒ ์ฐ๊ตฌ๊ฐ ํฐ ๋์์ด ๋๊ธธ ๋ฐ๋๋คโ๊ณ ๋งํ๋ค. ์ฐ๊ตฌ ๋
ผ๋ฌธ์ ๊ตญ์ ํ์ ์ง โ๋ค์ด์ฒ ๊ตฌ์กฐ&๋ถ์ ์๋ฌผํโ ์จ๋ผ์ธํ์ ์ต๊ทผ ๊ฒ์ฌ๋๋ค.
์ ๋ฌธ์ฅ์ ํ๊ธ๋ก 100์๋ด๋ก ์์ฝํด์ค.
์์ฝ:
"""
outputs = pipeline(prompt, max_new_tokens=256, return_full_text = False, pad_token_id=tokenizer.eos_token_id)&&
print(outputs[0]["generated_text"])
```
- Question answering
```
prompt = """
์ฐธ๊ฐ์๋ค์ ๋จผ์ fMRI ๊ธฐ๊ธฐ ์์์ ์์ ์ ์ด์ผ๊ธฐ๋ฅผ ์ฝ๋ ๋์ ๋์ ํ๋ ํจํด์ ๊ธฐ๋กํ๋ค. ์ด์ผ๊ธฐ๋ฅผ ๋ค์ ์ฝ์ผ๋ฉด์๋ ์ด์ผ๊ธฐ ์ ๋จ์ด์ ๋ํด ์๊ฐ์๊ฐ ์์ ์ด ๋๋ผ๋ ์๊ธฐ ๊ด๋ จ๋, ๊ธยท๋ถ์ ์ ์๋ฅผ ๋ณด๊ณ ํ๋ค. ์์ง๋ 49๋ช
์ ๋ฐ์ดํฐ๋ ์๊ธฐ ๊ด๋ จ๋์ ๊ธยท๋ถ์ ์ ์ ์ ์์ ๋ฐ๋ผ ๋ค์ฏ ๊ฐ ์์ค์ผ๋ก ๋ถ๋ฅ๋๋ค.
์ง๋ฌธ: ์คํ์ ๋์์ด ๋ ์ฌ๋์ ๋ช ๋ช
์ธ๊ฐ? ํ๊ธ๋ก ๋๋ต.
๋๋ต:
"""
outputs = pipeline(prompt, max_new_tokens=30, return_full_text = False)
generated_text = outputs[0]["generated_text"]
print(generated_text)
```
- Reasoning
```
prompt = """
๊ฐ ๋ฐฉ์ ๊ณต์ด 5๊ฐ ์๊ณ , ๋ฐฉ์ ์ด ๊ฐ์๋ 4. ์ด ๊ณต์ ๊ฐฏ์๋ ๋ช๊ฐ ์ธ๊ฐ?
"""
outputs = pipeline(prompt, max_new_tokens=40, return_full_text = False, pad_token_id=tokenizer.eos_token_id)
print(outputs[0]["generated_text"])
```
- Chatbot template
```
messages = [{"role": "user", "content": "์ข์ ์ทจ๋ฏธ๋ฅผ ๊ฐ์ง๋ ค๋ฉด ์ด๋ป๊ฒ ํ๋์?"}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=512, do_sample=True, temperature=0.7, top_k=50, top_p=0.95, return_full_text = False)
generated_text = outputs[0]["generated_text"]
print(generated_text)
```
### Request
The support of GPU computing resource is required for the development and implementation of state-of-the-art models.
I would appreciate if anyone could help.
Email: [email protected] |
nourheshamshaheen/llava_8epochs_2000steps_4clients | nourheshamshaheen | "2024-07-01T16:34:27Z" | 1,105 | 0 | transformers | [
"transformers",
"safetensors",
"llava_llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2024-07-01T15:09:13Z" | Entry not found |
Writer/palmyra-3B | Writer | "2024-02-28T09:41:37Z" | 1,104 | 8 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"text generation",
"causal-lm",
"Writer-data",
"NeMo",
"palmyra",
"en",
"dataset:English",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-03-01T02:22:46Z" | ---
language:
- en
datasets:
- English
tags:
- text generation
- pytorch
- causal-lm
- Writer-data
- NeMo
- palmyra
pipeline_tag: text-generation
library_name: transformers
license: apache-2.0
---
# Palmyra 3B
<style>
img {
display: inline;
}
</style>
|[](#model-architecture)|[](#model-architecture)|[](#datasets)
## Model Description
Palmyra 3B was primarily pre-trained with English text. Note that there is still a trace amount of non-English data present within the training corpus that was accessed through CommonCrawl. A causal language modeling (CLM) objective was utilized during the process of the model's pretraining. Similar to GPT-3, Palmyra 3B is a member of the same family of models that only contain a decoder. As a result, it was pre-trained utilizing the objective of self-supervised causal language modeling. Palmyra 3B uses the prompts and general experimental setup from GPT-3 in order to conduct its evaluation per GPT-3.
## Use case
Palmyra 3B is the fastest of Writerโs LLMs and can perform important tasks such as text parsing, simple classification, address correction, and keyword recognition. Providing more context drives even better performance.
## Training data
Palmyra 3B was trained on Writerโs custom dataset.
## Intended Use and Limitations
Palmyra 3B learns an inner representation of the English language that can be used to extract features useful for downstream tasks. However, the model is best at what it was pre-trained for which is generating text from a prompt.
### How to use
This model can be easily loaded using the `AutoModelForCausalLM` functionality:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("Writer/palmyra-3B")
tokenizer = AutoTokenizer.from_pretrained("Writer/palmyra-3B")
```
### Limitations and Biases
Palmyra 3B core functionality is to take a string of text and predict the next token. While language models are widely used for other tasks, there are many unknowns in this work. When prompting Palmyra, keep in mind that the next statistically likely token is not always the token that produces the most "accurate" text. Never rely on Palmyra 3B to produce factually correct results.
Palmyra 3B was trained on Writerโs custom data. As with all language models, it is difficult to predict how Palmyra 3B will respond to specific prompts, and offensive content may appear unexpectedly. We recommend that the outputs be curated or filtered by humans before they are released, both to censor undesirable content and to improve the quality of the results.
## Citation and Related Information
To cite this model:
```
@misc{Palmyra,
author = {Writer Engineering Team},
title = {{Palmyra 3B Parameter Autoregressive Language Model}},
howpublished = {\url{https://dev.writer.com}},
year = 2023,
month = March
}
``` |
TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ | TheBloke | "2023-10-03T21:14:26Z" | 1,104 | 36 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:2304.07327",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] | text-generation | "2023-04-29T13:51:12Z" | ---
inference: false
license: other
model_type: llama
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# OpenAssistant LLaMA 30B SFT 7 GPTQ
These files are GPTQ model files for [OpenAssistant LLaMA 30B SFT 7](https://huggingface.co/OpenAssistant/oasst-sft-7-llama-30b-xor).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
These models were quantised using hardware kindly provided by [Latitude.sh](https://www.latitude.sh/accelerate).
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenAssistant-SFT-7-Llama-30B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/OpenAssistant-SFT-7-Llama-30B-HF)
## Prompt template: OpenAssistant
```
<|prompter|>{prompt}<|endoftext|><|assistant|>
```
## Provided files
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
| Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
| ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
| main | 4 | None | True | 16.94 GB | True | GPTQ-for-LLaMa | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
| gptq-4bit-32g-actorder_True | 4 | 32 | True | 19.44 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
| gptq-4bit-64g-actorder_True | 4 | 64 | True | 18.18 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 64g uses less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
| gptq-4bit-128g-actorder_True | 4 | 128 | True | 17.55 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
| gptq-8bit--1g-actorder_True | 8 | None | True | 32.99 GB | False | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
| gptq-8bit-128g-actorder_False | 8 | 128 | False | 33.73 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
| gptq-3bit--1g-actorder_True | 3 | None | True | 12.92 GB | False | AutoGPTQ | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
| gptq-3bit-128g-actorder_False | 3 | 128 | False | 13.51 GB | False | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
## How to download from branches
- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ:gptq-4bit-32g-actorder_True`
- With Git, you can clone a branch with:
```
git clone --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ`
```
- In Python Transformers code, the branch is the `revision` parameter; see below.
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done"
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `OpenAssistant-SFT-7-Llama-30B-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to set GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
## How to use this GPTQ model from Python code
First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
`GITHUB_ACTIONS=true pip install auto-gptq`
Then try the following example code:
```python
from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
model_name_or_path = "TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ"
model_basename = "OpenAssistant-SFT-7-Llama-30B-GPTQ-4bit--1g.act.order"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
model_basename=model_basename
use_safetensors=True,
trust_remote_code=False,
device="cuda:0",
use_triton=use_triton,
quantize_config=None)
"""
To download from a specific branch, use the revision parameter, as in this example:
model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
revision="gptq-4bit-32g-actorder_True",
model_basename=model_basename,
use_safetensors=True,
trust_remote_code=False,
device="cuda:0",
quantize_config=None)
"""
prompt = "Tell me about AI"
prompt_template=f'''<|prompter|>{prompt}<|endoftext|><|assistant|>
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Compatibility
The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLaMa (only CUDA has been tested), and Occ4m's GPTQ-for-LLaMa fork.
ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, ้ฟๆ, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieล, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: OpenAssistant LLaMA 30B SFT 7
# OpenAssistant LLaMA 30B SFT 7
Due to the license attached to LLaMA models by Meta AI it is not possible to directly distribute LLaMA-based models. Instead we provide XOR weights for the OA models.
Thanks to Mick for writing the `xor_codec.py` script which enables this process
## The Process
Note: This process applies to `oasst-sft-7-llama-30b` model. The same process can be applied to other models in future, but the checksums will be different..
**This process is tested only on Linux (specifically Ubuntu). Some users have reported that the process does not work on Windows. We recommend using WSL if you only have a Windows machine.**
To use OpenAssistant LLaMA-Based Models, you should have a copy of the original LLaMA model weights and add them to a `llama` subdirectory here. If you cannot obtain the original LLaMA, see the note in italic below for a possible alternative.
Ensure your LLaMA 30B checkpoint matches the correct md5sums:
```
f856e9d99c30855d6ead4d00cc3a5573 consolidated.00.pth
d9dbfbea61309dc1e087f5081e98331a consolidated.01.pth
2b2bed47912ceb828c0a37aac4b99073 consolidated.02.pth
ea0405cdb5bc638fee12de614f729ebc consolidated.03.pth
4babdbd05b8923226a9e9622492054b6 params.json
```
*If you do not have a copy of the original LLaMA weights and cannot obtain one, you may still be able to complete this process. Some users have reported that [this model](https://huggingface.co/elinas/llama-30b-hf-transformers-4.29) can be used as a base for the XOR conversion. This will also allow you to skip to Step 7. However, we only support conversion starting from LLaMA original checkpoint and cannot provide support if you experience issues with this alternative approach.*
**Important: Follow these exact steps to convert your original LLaMA checkpoint to a HuggingFace Transformers-compatible format. If you use the wrong versions of any dependency, you risk ending up with weights which are not compatible with the XOR files.**
1. Create a clean Python **3.10** virtual environment & activate it:
```
python3.10 -m venv xor_venv
source xor_venv/bin/activate
```
2. Clone transformers repo and switch to tested version:
```
git clone https://github.com/huggingface/transformers.git
cd transformers
git checkout d04ec99bec8a0b432fc03ed60cea9a1a20ebaf3c
pip install .
```
3. Install **exactly** these dependency versions:
```
pip install torch==1.13.1 accelerate==0.18.0 sentencepiece==0.1.98 protobuf==3.20.1
```
4. Check `pip freeze` output:
```
accelerate==0.18.0
certifi==2022.12.7
charset-normalizer==3.1.0
filelock==3.12.0
huggingface-hub==0.13.4
idna==3.4
numpy==1.24.2
nvidia-cublas-cu11==11.10.3.66
nvidia-cuda-nvrtc-cu11==11.7.99
nvidia-cuda-runtime-cu11==11.7.99
nvidia-cudnn-cu11==8.5.0.96
packaging==23.1
protobuf==3.20.1
psutil==5.9.5
PyYAML==6.0
regex==2023.3.23
requests==2.28.2
sentencepiece==0.1.98
tokenizers==0.13.3
torch==1.13.1
tqdm==4.65.0
transformers @ file:///mnt/data/koepf/transformers
typing_extensions==4.5.0
urllib3==1.26.15
```
5. While in `transformers` repo root, run HF LLaMA conversion script:
```
python src/transformers/models/llama/convert_llama_weights_to_hf.py --input_dir <input_path_llama_base> --output_dir <output_path_llama30b_hf> --model_size 30B
```
6. Run `find . -type f -exec md5sum "{}" +` in the conversion target directory (`output_dir`). This should produce exactly the following checksums if your files are correct:
```
462a2d07f65776f27c0facfa2affb9f9 ./pytorch_model-00007-of-00007.bin
e1dc8c48a65279fb1fbccff14562e6a3 ./pytorch_model-00003-of-00007.bin
9cffb1aeba11b16da84b56abb773d099 ./pytorch_model-00001-of-00007.bin
aee09e21813368c49baaece120125ae3 ./generation_config.json
92754d6c6f291819ffc3dfcaf470f541 ./pytorch_model-00005-of-00007.bin
3eddc6fc02c0172d38727e5826181adb ./pytorch_model-00004-of-00007.bin
eeec4125e9c7560836b4873b6f8e3025 ./tokenizer.model
99762d59efa6b96599e863893cf2da02 ./pytorch_model-00006-of-00007.bin
598538f18fed1877b41f77de034c0c8a ./config.json
fdb311c39b8659a5d5c1991339bafc09 ./tokenizer.json
fecfda4fba7bfd911e187a85db5fa2ef ./pytorch_model.bin.index.json
edd1a5897748864768b1fab645b31491 ./tokenizer_config.json
6b2e0a735969660e720c27061ef3f3d3 ./special_tokens_map.json
5cfcb78b908ffa02e681cce69dbe4303 ./pytorch_model-00002-of-00007.bin
```
**Important: You should now have the correct LLaMA weights and be ready to apply the XORs. If the checksums above do not match yours, there is a problem.**
7. Once you have LLaMA weights in the correct format, you can apply the XOR decoding:
```
python xor_codec.py oasst-sft-7-llama-30b/ oasst-sft-7-llama-30b-xor/ llama30b_hf/
```
You should **expect to see one warning message** during execution:
`Exception when processing 'added_tokens.json'`
This is normal. **If similar messages appear for other files, something has gone wrong**.
8. Now run `find . -type f -exec md5sum "{}" +` in the output directory (here `oasst-sft-6-llama-30b`). You should get a file with exactly these checksums:
```
8ae4537c64a1ef202d1d82eb0d356703 ./pytorch_model-00007-of-00007.bin
d84f99d23369e159e50cb0597b6c9673 ./pytorch_model-00003-of-00007.bin
f7de50a725d678eb65cc3dced727842f ./pytorch_model-00001-of-00007.bin
27b0dc092f99aa2efaf467b2d8026c3f ./added_tokens.json
aee09e21813368c49baaece120125ae3 ./generation_config.json
31a2b04b139f4af043ad04478f1497f5 ./pytorch_model-00005-of-00007.bin
a16a2dfacbde77a1659a7c9df7966d0a ./pytorch_model-00004-of-00007.bin
eeec4125e9c7560836b4873b6f8e3025 ./tokenizer.model
baa778a8679d47b085446faf97b72758 ./pytorch_model-00006-of-00007.bin
b2d64f2198ab7b53e3b8d12fbcadeb3c ./config.json
deb33dd4ffc3d2baddcce275a00b7c1b ./tokenizer.json
76d47e4f51a8df1d703c6f594981fcab ./pytorch_model.bin.index.json
ed59bfee4e87b9193fea5897d610ab24 ./tokenizer_config.json
704373f0c0d62be75e5f7d41d39a7e57 ./special_tokens_map.json
e836168cdbbb74db51d04f25ed6408ce ./pytorch_model-00002-of-00007.bin
```
If so you have successfully decoded the weights and should be able to use the model with HuggingFace Transformers. **If your checksums do not match those above, there is a problem.**
### Configuration
```
llama-30b-sft-7:
dtype: fp16
log_dir: "llama_log_30b"
learning_rate: 1e-5
model_name: /home/ubuntu/Open-Assistant/model/model_training/.saved/llama-30b-super-pretrain/checkpoint-3500
#model_name: OpenAssistant/llama-30b-super-pretrain
output_dir: llama_model_30b
deepspeed_config: configs/zero3_config_sft.json
weight_decay: 0.0
residual_dropout: 0.0
max_length: 2048
use_flash_attention: true
warmup_steps: 20
gradient_checkpointing: true
gradient_accumulation_steps: 12
per_device_train_batch_size: 2
per_device_eval_batch_size: 3
eval_steps: 101
save_steps: 485
num_train_epochs: 4
save_total_limit: 3
use_custom_sampler: true
sort_by_length: false
#save_strategy: steps
save_strategy: epoch
datasets:
- oasst_export:
lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk"
input_file_path: 2023-04-12_oasst_release_ready_synth.jsonl.gz
val_split: 0.05
- vicuna:
val_split: 0.05
max_val_set: 800
fraction: 1.0
- dolly15k:
val_split: 0.05
max_val_set: 300
- grade_school_math_instructions:
val_split: 0.05
- code_alpaca:
val_split: 0.05
max_val_set: 250
```
- **OASST dataset paper:** https://arxiv.org/abs/2304.07327
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.