Search is not available for this dataset
pipeline_tag
stringclasses 48
values | library_name
stringclasses 205
values | text
stringlengths 0
18.3M
| metadata
stringlengths 2
1.07B
| id
stringlengths 5
122
| last_modified
null | tags
listlengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
|
|---|---|---|---|---|---|---|---|---|
text-generation | null |
## Exllama v2 Quantizations of OpenBioLLM-Llama3-8B
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.19">turboderp's ExLlamaV2 v0.0.19</a> for quantization.
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Original model: https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B
## Prompt format
No chat template specified so default is used. This may be incorrect, check original model card for details.
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Available sizes
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (8K) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-exl2/tree/8_0) | 8.0 | 8.0 | 10.1 GB | 10.5 GB | 11.5 GB | 13.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-exl2/tree/6_5) | 6.5 | 8.0 | 8.9 GB | 9.3 GB | 10.3 GB | 12.4 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
| [5_0](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-exl2/tree/5_0) | 5.0 | 6.0 | 7.7 GB | 8.1 GB | 9.1 GB | 11.2 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
| [4_25](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-exl2/tree/4_25) | 4.25 | 6.0 | 7.0 GB | 7.4 GB | 8.4 GB | 10.5 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| [3_5](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-exl2/tree/3_5) | 3.5 | 6.0 | 6.4 GB | 6.8 GB | 7.8 GB | 9.9 GB | Lower quality, only use if you have to. |
## Download instructions
With git:
```shell
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-exl2 OpenBioLLM-Llama3-8B-exl2-6_5
```
With huggingface hub (credit to TheBloke for instructions):
```shell
pip3 install huggingface-hub
```
To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:
Linux:
```shell
huggingface-cli download bartowski/OpenBioLLM-Llama3-8B-exl2 --revision 6_5 --local-dir OpenBioLLM-Llama3-8B-exl2-6_5 --local-dir-use-symlinks False
```
Windows (which apparently doesn't like _ in folders sometimes?):
```shell
huggingface-cli download bartowski/OpenBioLLM-Llama3-8B-exl2 --revision 6_5 --local-dir OpenBioLLM-Llama3-8B-exl2-6.5 --local-dir-use-symlinks False
```
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
| {"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-8B", "widget": [{"example_title": "OpenBioLLM-8B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "quantized_by": "bartowski", "pipeline_tag": "text-generation", "model-index": [{"name": "OpenBioLLM-8B", "results": []}]} | bartowski/OpenBioLLM-Llama3-8B-exl2 | null | [
"llama-3",
"llama",
"Mixtral",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"distillation",
"text-generation",
"en",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:llama3",
"region:us"
]
| null | 2024-04-26T14:21:48+00:00 |
text-generation | transformers |
# yujiepan/Meta-Llama-3-8B-awq-w4g64-v2
This model applies AutoAWQ on [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B).
- 4-bit asymmetric weight only quantization
- group_size=64
- skip last layer FFN
- calibration set: pileval
## Accuracy
| model | precision | wikitext ppl (↓) |
|-|-|-|
| meta-llama/Meta-Llama-3-8B | FP16 | 9.179 |
| yujiepan/Meta-Llama-3-8B-awq-w4g64 | w4g64 | 9.219 |
| yujiepan/Meta-Llama-3-8B-awq-w4g64-v2 | w4g64, skip last layer's FFN | 9.278 |
Note:
- Evaluated on lm-evaluation-harness "wikitext" task
- Wikitext PPL does not guarantee actual accuracy, but helps to check the distortion after quantization.
## Usage
```python
model = AutoModelForCausalLM.from_pretrained('<MODEL_ID>', torch_dtype=torch.float16)
```
## Codes
```python
from unittest.mock import patch
import torch
from awq import AutoAWQForCausalLM
from awq.models.llama import LlamaAWQForCausalLM
from transformers import AutoTokenizer
module2fullname = {}
def exclude_layers_to_not_quantize(linear_layers, modules_to_not_convert):
if modules_to_not_convert is None:
return linear_layers
filtered_layers = {}
for name, linear_layer in linear_layers.items():
full_name = module2fullname[linear_layer]
if not any(key in full_name for key in modules_to_not_convert):
filtered_layers[name] = linear_layer
else:
print('Skipping', full_name)
return filtered_layers
class PatchedLlamaAWQForCausalLM(LlamaAWQForCausalLM):
@staticmethod
def get_layers_for_scaling(module, input_feat, module_kwargs):
print(input_feat.keys())
layers = []
# attention input
if 'self_attn.q_proj' in input_feat:
layers.append(
dict(
prev_op=module.input_layernorm,
layers=[
module.self_attn.q_proj,
module.self_attn.k_proj,
module.self_attn.v_proj,
],
inp=input_feat["self_attn.q_proj"],
module2inspect=module.self_attn,
kwargs=module_kwargs,
)
)
# attention out
# Please refer to https://github.com/mit-han-lab/llm-awq/pull/67#issue-1850622696
if 'self_attn.o_proj' in input_feat:
if module.self_attn.v_proj.weight.shape == module.self_attn.o_proj.weight.shape:
layers.append(
dict(
prev_op=module.self_attn.v_proj,
layers=[module.self_attn.o_proj],
inp=input_feat["self_attn.o_proj"],
)
)
if 'mlp.gate_proj' in input_feat:
# linear 1
layers.append(
dict(
prev_op=module.post_attention_layernorm,
layers=[module.mlp.gate_proj, module.mlp.up_proj],
inp=input_feat["mlp.gate_proj"],
module2inspect=module.mlp,
)
)
if 'mlp.down_proj' in input_feat:
# linear 2
layers.append(
dict(
prev_op=module.mlp.up_proj,
layers=[module.mlp.down_proj],
inp=input_feat["mlp.down_proj"],
)
)
return layers
quant_config = {
"zero_point": True, "q_group_size": 64, "w_bit": 4, "version": "GEMM",
"modules_to_not_convert": [
'layers.31.mlp',
],
}
with patch('awq.quantize.quantizer.exclude_layers_to_not_quantize', exclude_layers_to_not_quantize):
model_path = "meta-llama/Meta-Llama-3-8B"
# model_path = 'yujiepan/meta-llama-3-tiny-random'
model = PatchedLlamaAWQForCausalLM.from_pretrained(model_path, model_type='llama', device_map='cuda')
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
module2fullname = {module: name for name, module in model.named_modules()}
model.quantize(tokenizer, quant_config=quant_config)
```
| {"library_name": "transformers", "tags": []} | yujiepan/Meta-Llama-3-8B-awq-w4g64-v2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T14:21:48+00:00 |
text-generation | transformers |
# yujiepan/Meta-Llama-3-8B-Instruct-awq-w4g64-v2
This model applies AutoAWQ on [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
- 4-bit asymmetric weight only quantization
- group_size=64
- skip last layer FFN
- calibration set: pileval
## Accuracy
| model | precision | wikitext ppl (↓) |
|-|-|-|
| meta-llama/Meta-Llama-3-8B-Instruct | FP16 | 10.842 |
| yujiepan/Meta-Llama-3-8B-Instruct-awq-w4g64 | w4g64 | 10.943 |
| yujiepan/Meta-Llama-3-8B-Instruct-awq-w4g64-v2 | w4g64, skip last layer's FFN | 10.928 |
Note:
- Evaluated on lm-evaluation-harness "wikitext" task
- Wikitext PPL does not guarantee actual accuracy, but helps to check the distortion after quantization.
## Usage
```python
model = AutoModelForCausalLM.from_pretrained('<MODEL_ID>', torch_dtype=torch.float16)
```
## Codes
```python
from unittest.mock import patch
import torch
from awq import AutoAWQForCausalLM
from awq.models.llama import LlamaAWQForCausalLM
from transformers import AutoTokenizer
module2fullname = {}
def exclude_layers_to_not_quantize(linear_layers, modules_to_not_convert):
if modules_to_not_convert is None:
return linear_layers
filtered_layers = {}
for name, linear_layer in linear_layers.items():
full_name = module2fullname[linear_layer]
if not any(key in full_name for key in modules_to_not_convert):
filtered_layers[name] = linear_layer
else:
print('Skipping', full_name)
return filtered_layers
class PatchedLlamaAWQForCausalLM(LlamaAWQForCausalLM):
@staticmethod
def get_layers_for_scaling(module, input_feat, module_kwargs):
print(input_feat.keys())
layers = []
# attention input
if 'self_attn.q_proj' in input_feat:
layers.append(
dict(
prev_op=module.input_layernorm,
layers=[
module.self_attn.q_proj,
module.self_attn.k_proj,
module.self_attn.v_proj,
],
inp=input_feat["self_attn.q_proj"],
module2inspect=module.self_attn,
kwargs=module_kwargs,
)
)
# attention out
# Please refer to https://github.com/mit-han-lab/llm-awq/pull/67#issue-1850622696
if 'self_attn.o_proj' in input_feat:
if module.self_attn.v_proj.weight.shape == module.self_attn.o_proj.weight.shape:
layers.append(
dict(
prev_op=module.self_attn.v_proj,
layers=[module.self_attn.o_proj],
inp=input_feat["self_attn.o_proj"],
)
)
if 'mlp.gate_proj' in input_feat:
# linear 1
layers.append(
dict(
prev_op=module.post_attention_layernorm,
layers=[module.mlp.gate_proj, module.mlp.up_proj],
inp=input_feat["mlp.gate_proj"],
module2inspect=module.mlp,
)
)
if 'mlp.down_proj' in input_feat:
# linear 2
layers.append(
dict(
prev_op=module.mlp.up_proj,
layers=[module.mlp.down_proj],
inp=input_feat["mlp.down_proj"],
)
)
return layers
quant_config = {
"zero_point": True, "q_group_size": 64, "w_bit": 4, "version": "GEMM",
"modules_to_not_convert": [
'layers.31.mlp',
],
}
with patch('awq.quantize.quantizer.exclude_layers_to_not_quantize', exclude_layers_to_not_quantize):
model_path = "meta-llama/Meta-Llama-3-8B-Instruct"
# model_path = 'yujiepan/meta-llama-3-tiny-random'
model = PatchedLlamaAWQForCausalLM.from_pretrained(model_path, model_type='llama', device_map='cuda')
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
module2fullname = {module: name for name, module in model.named_modules()}
model.quantize(tokenizer, quant_config=quant_config)
```
| {"library_name": "transformers", "tags": []} | yujiepan/Meta-Llama-3-8B-Instruct-awq-w4g64-v2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T14:22:29+00:00 |
reinforcement-learning | stable-baselines3 |
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
| {"library_name": "stable-baselines3", "tags": ["LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "259.20 +/- 22.42", "name": "mean_reward", "verified": false}]}]}]} | JonathanST/ppo-LunarLander-v2 | null | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| null | 2024-04-26T14:23:51+00:00 |
null | null | {"license": "openrail++"} | EthanRhys/Dr-Neo-Cortex-LA | null | [
"license:openrail++",
"region:us"
]
| null | 2024-04-26T14:23:53+00:00 |
|
text-generation | transformers |
## 4-bit GEMM AWQ Quantizations of OpenBioLLM-Llama3-8B
Using <a href="https://github.com/casper-hansen/AutoAWQ/">AutoAWQ</a> release <a href="https://github.com/casper-hansen/AutoAWQ/releases/tag/v0.2.4">v0.2.4</a> for quantization.
Original model: https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B
## Prompt format
No chat template specified so default is used. This may be incorrect, check original model card for details.
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## AWQ Parameters
- q_group_size: 128
- w_bit: 4
- zero_point: True
- version: GEMM
## How to run
From the AutoAWQ repo [here](https://github.com/casper-hansen/AutoAWQ/blob/main/examples/generate.py)
First install autoawq pypi package:
```
pip install autoawq
```
Then run the following:
```
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
quant_path = "models/OpenBioLLM-Llama3-8B-AWQ"
# Load model
model = AutoAWQForCausalLM.from_quantized(quant_path, fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
prompt = "You're standing on the surface of the Earth. "\
"You walk one mile south, one mile west and one mile north. "\
"You end up exactly where you started. Where are you?"
chat = [
{"role": "system", "content": "You are a concise assistant that helps answer questions."},
{"role": "user", "content": prompt},
]
# <|eot_id|> used for llama 3 models
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
tokens = tokenizer.apply_chat_template(
chat,
return_tensors="pt"
).cuda()
# Generate output
generation_output = model.generate(
tokens,
streamer=streamer,
max_new_tokens=64,
eos_token_id=terminators
)
```
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
| {"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-8B", "widget": [{"example_title": "OpenBioLLM-8B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "quantized_by": "bartowski", "pipeline_tag": "text-generation", "model-index": [{"name": "OpenBioLLM-8B", "results": []}]} | bartowski/OpenBioLLM-Llama3-8B-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-3",
"Mixtral",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"distillation",
"en",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T14:25:02+00:00 |
text-generation | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | OwOOwO/final3 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:25:11+00:00 |
text-generation | transformers |
# Uploaded model
- **Developed by:** richie-ghost
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | richie-ghost/llama-3b-unsloth-quantized_merged_8bit | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"region:us"
]
| null | 2024-04-26T14:25:24+00:00 |
null | peft |
<!-- 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. -->
# zephyr-7b-lora-64-no-quant
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the updated and the original datasets.
## 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: 5e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2 | {"license": "apache-2.0", "library_name": "peft", "tags": ["alignment-handbook", "generated_from_trainer", "trl", "dpo"], "datasets": ["updated", "original"], "base_model": "alignment-handbook/zephyr-7b-sft-full", "model-index": [{"name": "zephyr-7b-lora-64-no-quant", "results": []}]} | YYYYYYibo/zephyr-7b-lora-64-no-quant | null | [
"peft",
"safetensors",
"mistral",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"dataset:updated",
"dataset:original",
"base_model:alignment-handbook/zephyr-7b-sft-full",
"license:apache-2.0",
"region:us"
]
| null | 2024-04-26T14:28:24+00:00 |
null | null | {} | Vincen80260/Product_Owner | null | [
"region:us"
]
| null | 2024-04-26T14:28:34+00:00 |
|
null | null | {} | 25miner3/25miner3 | null | [
"region:us"
]
| null | 2024-04-26T14:28:37+00:00 |
|
null | null | {} | askipop/firstrepo | null | [
"region:us"
]
| null | 2024-04-26T14:29:20+00:00 |
|
video-classification | transformers | {} | emsdiaz/videomae-base-finetuned-veriff | null | [
"transformers",
"pytorch",
"tensorboard",
"videomae",
"video-classification",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:31:07+00:00 |
|
null | peft |
<!-- 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. -->
# esm2_t130_150M-lora-classifier_2024-04-26_10-31-42
This model is a fine-tuned version of [facebook/esm2_t30_150M_UR50D](https://huggingface.co/facebook/esm2_t30_150M_UR50D) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8800
- Accuracy: 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: 0.0008701568055793088
- train_batch_size: 28
- eval_batch_size: 28
- seed: 8893
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 90
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.659 | 1.0 | 55 | 0.6868 | 0.5820 |
| 0.5296 | 2.0 | 110 | 0.6101 | 0.6777 |
| 0.5532 | 3.0 | 165 | 0.5395 | 0.7402 |
| 0.505 | 4.0 | 220 | 0.3482 | 0.8613 |
| 0.1246 | 5.0 | 275 | 0.3447 | 0.8535 |
| 0.3953 | 6.0 | 330 | 0.2982 | 0.8789 |
| 0.169 | 7.0 | 385 | 0.3257 | 0.875 |
| 0.2096 | 8.0 | 440 | 0.4022 | 0.8438 |
| 0.2339 | 9.0 | 495 | 0.3090 | 0.8848 |
| 0.1876 | 10.0 | 550 | 0.2723 | 0.8926 |
| 0.0631 | 11.0 | 605 | 0.3260 | 0.875 |
| 0.2843 | 12.0 | 660 | 0.4296 | 0.8438 |
| 0.0502 | 13.0 | 715 | 0.3301 | 0.8945 |
| 0.185 | 14.0 | 770 | 0.3273 | 0.8984 |
| 0.098 | 15.0 | 825 | 0.3355 | 0.8945 |
| 0.2528 | 16.0 | 880 | 0.4209 | 0.8926 |
| 0.2165 | 17.0 | 935 | 0.4467 | 0.8809 |
| 0.5202 | 18.0 | 990 | 0.4732 | 0.8984 |
| 0.0746 | 19.0 | 1045 | 0.4913 | 0.8926 |
| 0.0107 | 20.0 | 1100 | 0.4292 | 0.8906 |
| 0.0263 | 21.0 | 1155 | 0.6244 | 0.8555 |
| 0.011 | 22.0 | 1210 | 0.5228 | 0.8809 |
| 0.093 | 23.0 | 1265 | 0.5670 | 0.8828 |
| 0.058 | 24.0 | 1320 | 0.8912 | 0.8379 |
| 0.0007 | 25.0 | 1375 | 1.0458 | 0.8594 |
| 0.082 | 26.0 | 1430 | 0.7712 | 0.8848 |
| 0.0172 | 27.0 | 1485 | 0.7106 | 0.8945 |
| 0.1386 | 28.0 | 1540 | 0.9548 | 0.8535 |
| 0.1145 | 29.0 | 1595 | 0.8496 | 0.8945 |
| 0.001 | 30.0 | 1650 | 0.9245 | 0.8770 |
| 0.0004 | 31.0 | 1705 | 0.9368 | 0.8867 |
| 0.0039 | 32.0 | 1760 | 0.9754 | 0.8828 |
| 0.0165 | 33.0 | 1815 | 1.0050 | 0.8770 |
| 0.0028 | 34.0 | 1870 | 1.0051 | 0.8848 |
| 0.0006 | 35.0 | 1925 | 0.9673 | 0.8652 |
| 0.0 | 36.0 | 1980 | 0.9794 | 0.8906 |
| 0.0 | 37.0 | 2035 | 0.9294 | 0.8984 |
| 0.1004 | 38.0 | 2090 | 0.9621 | 0.8965 |
| 0.0 | 39.0 | 2145 | 0.9699 | 0.8965 |
| 0.0001 | 40.0 | 2200 | 1.0551 | 0.8926 |
| 0.0001 | 41.0 | 2255 | 0.9521 | 0.8965 |
| 0.1139 | 42.0 | 2310 | 1.0807 | 0.8828 |
| 0.0291 | 43.0 | 2365 | 0.9925 | 0.8965 |
| 0.0001 | 44.0 | 2420 | 1.0462 | 0.8867 |
| 0.0001 | 45.0 | 2475 | 0.9989 | 0.8848 |
| 0.0 | 46.0 | 2530 | 0.9005 | 0.8945 |
| 0.0005 | 47.0 | 2585 | 1.0845 | 0.8809 |
| 0.0 | 48.0 | 2640 | 0.9892 | 0.8965 |
| 0.0001 | 49.0 | 2695 | 0.9311 | 0.8887 |
| 0.0 | 50.0 | 2750 | 0.9819 | 0.8887 |
| 0.0 | 51.0 | 2805 | 1.0463 | 0.8887 |
| 0.0 | 52.0 | 2860 | 1.0672 | 0.8828 |
| 0.0 | 53.0 | 2915 | 1.0893 | 0.8926 |
| 0.0 | 54.0 | 2970 | 1.1496 | 0.8848 |
| 0.0002 | 55.0 | 3025 | 1.1330 | 0.8809 |
| 0.0009 | 56.0 | 3080 | 1.0782 | 0.8828 |
| 0.0046 | 57.0 | 3135 | 0.9937 | 0.8887 |
| 0.0009 | 58.0 | 3190 | 0.9710 | 0.8945 |
| 0.001 | 59.0 | 3245 | 1.0381 | 0.8848 |
| 0.0001 | 60.0 | 3300 | 0.9837 | 0.8887 |
| 0.0 | 61.0 | 3355 | 0.9552 | 0.8926 |
| 0.0002 | 62.0 | 3410 | 1.0600 | 0.8730 |
| 0.0 | 63.0 | 3465 | 0.9684 | 0.8887 |
| 0.0 | 64.0 | 3520 | 0.9498 | 0.8926 |
| 0.0003 | 65.0 | 3575 | 0.9644 | 0.8926 |
| 0.0 | 66.0 | 3630 | 0.9054 | 0.8887 |
| 0.0 | 67.0 | 3685 | 0.9370 | 0.8945 |
| 0.0001 | 68.0 | 3740 | 1.0082 | 0.8789 |
| 0.0001 | 69.0 | 3795 | 0.9378 | 0.8945 |
| 0.0048 | 70.0 | 3850 | 0.9371 | 0.8945 |
| 0.0002 | 71.0 | 3905 | 1.0431 | 0.8730 |
| 0.0007 | 72.0 | 3960 | 0.9235 | 0.8828 |
| 0.0011 | 73.0 | 4015 | 0.9624 | 0.8867 |
| 0.0 | 74.0 | 4070 | 0.9465 | 0.8926 |
| 0.0 | 75.0 | 4125 | 0.9266 | 0.8906 |
| 0.0 | 76.0 | 4180 | 0.9872 | 0.8867 |
| 0.0 | 77.0 | 4235 | 0.9488 | 0.8887 |
| 0.0002 | 78.0 | 4290 | 0.9376 | 0.8906 |
| 0.0 | 79.0 | 4345 | 0.9632 | 0.8867 |
| 0.0001 | 80.0 | 4400 | 0.9373 | 0.8926 |
| 0.0001 | 81.0 | 4455 | 0.9352 | 0.8848 |
| 0.0 | 82.0 | 4510 | 0.8856 | 0.8906 |
| 0.0001 | 83.0 | 4565 | 0.8813 | 0.8926 |
| 0.0001 | 84.0 | 4620 | 0.8822 | 0.8887 |
| 0.0 | 85.0 | 4675 | 0.8911 | 0.8887 |
| 0.0 | 86.0 | 4730 | 0.8834 | 0.8945 |
| 0.0001 | 87.0 | 4785 | 0.8747 | 0.8945 |
| 0.0 | 88.0 | 4840 | 0.8823 | 0.8926 |
| 0.0 | 89.0 | 4895 | 0.8824 | 0.8926 |
| 0.0 | 90.0 | 4950 | 0.8800 | 0.8945 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.16.1
- Tokenizers 0.15.2 | {"license": "mit", "library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "facebook/esm2_t30_150M_UR50D", "model-index": [{"name": "esm2_t130_150M-lora-classifier_2024-04-26_10-31-42", "results": []}]} | wcvz/esm2_t130_150M-lora-classifier_2024-04-26_10-31-42 | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:facebook/esm2_t30_150M_UR50D",
"license:mit",
"region:us"
]
| null | 2024-04-26T14:31:43+00:00 |
null | null | {} | Destr/diffusers_ckpt_step_819.zip | null | [
"region:us"
]
| null | 2024-04-26T14:31:51+00:00 |
|
text-generation | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | pruning/4nvvc50 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:33:10+00:00 |
text-generation | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | pruning/lc4einj | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:33:10+00:00 |
text-generation | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | pruning/kc82k2t | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:33:11+00:00 |
text-generation | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | pruning/09gi1ch | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:33:11+00:00 |
null | peft |
<!-- 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. -->
# mistral-7b-hf-platypus_vxxiii-chat-added_lamini_v4
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) 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: 0.0003
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 6
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.8.2
- Transformers 4.37.1
- Pytorch 2.2.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1 | {"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "mistralai/Mistral-7B-v0.1", "model-index": [{"name": "mistral-7b-hf-platypus_vxxiii-chat-added_lamini_v4", "results": []}]} | NassimB/mistral-7b-hf-platypus_vxxiii-chat-added_lamini_v4 | null | [
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"region:us"
]
| null | 2024-04-26T14:33:50+00:00 |
null | null | {} | TrgTuan10/ti_tazan | null | [
"region:us"
]
| null | 2024-04-26T14:34:17+00:00 |
|
null | null | {} | lorcan-mclaren/my_awesome_model | null | [
"region:us"
]
| null | 2024-04-26T14:37:02+00:00 |
|
null | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | MLP-Lemma/Llama-sft-cnn | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:40:32+00:00 |
null | null | {"license": "creativeml-openrail-m"} | mitchyAI/suzymchy | null | [
"license:creativeml-openrail-m",
"region:us"
]
| null | 2024-04-26T14:41:30+00:00 |
|
null | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | binhquoc/aimo-lora-deepseek | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:42:32+00:00 |
null | null | # chinese Meta Llama3 Instruct 8b 4bit
```
“top.model_name": "LLaMA3-8B-Chat",
"top.finetuning_type": "lora",
"top.adapter_path": [],
"top.quantization_bit": "none",
"top.template": "llama3",
"top.rope_scaling": "none",
top.booster": "none",
"train.training_stage": "Supervised Fine-Tuning",
"train.dataset_dir": "data",
"train.dataset": [
"alpaca_zh",
"alpaca_gpt4_zh",
"guanaco",
"oaast_sft_zh",
"wikipedia_zh"
]，
top.model_name": "LLaMA3-8B-Chat",
"top.finetuning_type": "lora",
"top.adapter_path": [],
"top.quantization_bit": "none",
"top.template": "llama3",
"top.rope_scaling": "none",
"top.booster": "none",
"train.training_stage": "Supervised Fine-Tuning",
"train.dataset_dir": "data",
"train.dataset": [
"alpaca_zh",
"alpaca_gpt4_zh",
"guanaco",
"nsfc_zh",
"oaast_sft_zh",
"wikipedia_zh"
],
``` | {"license": "apache-2.0"} | pooka74/LLaMA3-8B-Chat-Chinese-GGUF | null | [
"gguf",
"license:apache-2.0",
"region:us"
]
| null | 2024-04-26T14:42:42+00:00 |
text-generation | transformers | {} | LuangMV97/Roberta-DialoGPT_EmpAI_test | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T14:42:47+00:00 |
|
text-generation | transformers | {"license": "apache-2.0"} | delphi-demo/llama-100k | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T14:42:49+00:00 |
|
null | transformers |
# Uploaded model
- **Developed by:** ntvcie
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-2b-bnb-4bit
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "gemma", "trl"], "base_model": "unsloth/gemma-2b-bnb-4bit"} | ntvcie/Gemma2bVinhntV01 | null | [
"transformers",
"pytorch",
"safetensors",
"gguf",
"gemma",
"text-generation-inference",
"unsloth",
"trl",
"en",
"base_model:unsloth/gemma-2b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:43:34+00:00 |
text-to-image | diffusers | {} | nncyberpunk/SDXL1.0_NewCreativityXL_10 | null | [
"diffusers",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
]
| null | 2024-04-26T14:44:22+00:00 |
|
text-generation | transformers |
# tulu-2-dpo-13b-ExPO
The extrapolated (ExPO) model based on `allenai/tulu-2-dpo-13b` and `allenai/tulu-2-13b`, as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. | {"language": ["en"], "license": "other", "license_name": "ai2-impact-license-low-risk", "license_link": "https://allenai.org/impact-license"} | chujiezheng/tulu-2-dpo-13b-ExPO | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"arxiv:2404.16792",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T14:46:27+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** Tung177
- **License:** apache-2.0
- **Finetuned from model :** ura-hcmut/GemSUra-2B
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
# Training procedure
## Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 64
- total_train_batch_size: 64
- optimizer: paged-adamw-32bit
- lr_scheduler_type: constant
- num_epochs: 3
- qlora: r64 a16 dropout0
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "gemma", "trl"], "base_model": "ura-hcmut/GemSUra-2B"} | Tung177/ss-gemsura2b-adapters | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"gemma",
"trl",
"en",
"base_model:ura-hcmut/GemSUra-2B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:47:40+00:00 |
text-generation | null | ## KoDolph-2x8b
> **Update @ 2024.04.26:** Linear Merge of [Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview) and [dolphin-2.9-llama3-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b)
### Model Details
**KoDolph-2x8b:**
I had this idea at night that it would make sense to make a Linear Merge
**Model Merge:**
Linear Merge
**Ollama:**
```
ollama create KoDolph-2x8b -f ./Modelfile_Q5_K_M
```
### Composition
1. **Base Layers from Llama-3-Open-Ko-8B-Instruct-preview:**
- **Range:** Layers 0 to 20
- **Purpose:** These layers are utilized for their strong foundational language processing capabilities specifically in Korean. They are crucial for processing and understanding Korean text effectively, handling basic linguistic functions and intermediate language understanding.
2. **Advanced Layers from Dolphin-2.9-llama3-8b:**
- **Range:** Layers 15 to 24
- **Purpose:** These layers provide advanced domain-specific capabilities, particularly suited for coding and technical tasks. Beginning integration from layer 15 enhances the model's ability to manage complex scenarios involving technical language and coding tasks.
**Purpose and Utility:**
This "Linear Merge" strategically combines the strengths of both models through weighted averaging, ensuring a balanced influence in the merged output. This approach is designed to provide robust performance in applications requiring a deep understanding and generation of Korean text, along with the capability to handle specialized tasks involving technical descriptions and coding. It is ideal for creating advanced AI assistants, coding bots, or any application where high linguistic and technical precision is needed.
### Configuration
```yaml
models:
- model: beomi/Llama-3-Open-Ko-8B-Instruct-preview
parameters:
weight: 0.5 # Equal weight to maintain balance between foundational language processing and advanced technical tasks
layer_range: [0, 20] # Use foundational and intermediate language processing layers in Korean
- model: cognitivecomputations/dolphin-2.9-llama3-8b
parameters:
weight: 0.5 # Equal weight to complement and balance the capabilities of the Llama model
layer_range: [15, 24] # Utilize advanced coding and domain-specific layers
merge_method: linear # Balanced combination of layers using a weighted average
dtype: float16 # Efficient resource usage for computational performance
```
### Test Result
**Root Cause:**
- **Bad Response:** There were some strange answers, so I think there may have been a problem during the merge process. We are merging and investigating again as the instructions are not in the Korean version.
<a href="https://ibb.co/nLtW1QF"><img src="https://i.ibb.co/ZM7Zgc0/Screenshot-2024-04-27-at-12-25-46-PM.png" alt="Screenshot-2024-04-27-at-12-25-46-PM" border="0" /></a>
| {"language": ["en", "ko"], "license": "other", "tags": ["mergekit", "merge", "facebook", "meta", "pytorch", "llama", "llama-3"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE", "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT Meta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "extra_gated_fields": {"First Name": "text", "Last Name": "text", "Date of birth": "date_picker", "Country": "country", "Affiliation": "text", "geo": "ip_location", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox"}, "extra_gated_description": "The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).", "extra_gated_button_content": "Submit"} | asiansoul/KoDolph-2x8b-Instruct-GGUF | null | [
"gguf",
"mergekit",
"merge",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"text-generation",
"en",
"ko",
"license:other",
"region:us"
]
| null | 2024-04-26T14:48:53+00:00 |
text-generation | transformers | ## **Poppy_Porpoise-v0.7-L3-8B**
[exllamav2](https://github.com/turboderp/exllamav2) quant for [ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B)
**Original model information:**
# "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.
# Recomended ST Presets: [Porpoise Presets](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B/tree/main/Official%20Poppy%20Porpoise%20ST%20Presets)
# Quants From the boi: [@Lewdiculus-Poppy-Quants](https://huggingface.co/Lewdiculous/Poppy_Porpoise-v0.7-L3-8B-GGUF-IQ-Imatrix)
# 4-bpw-exl2 quant: [here](https://huggingface.co/Nitral-AI/Poppy_Porpoise-v0.7-L3-8B-4bpw-exl2)
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/ChaoticNeutrals/LLaVA-Llama-3-8B-mmproj)
* You can load the **mmproj** by using the corresponding section in the interface:
 | {"language": ["en"], "tags": ["llama3", "8-bit"], "base_model": ["ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B"], "inference": false} | Slvcxc/Poppy_Porpoise-v0.7-L3-8B-8.0bpw-h8-exl2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama3",
"8-bit",
"conversational",
"en",
"base_model:ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B",
"autotrain_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T14:48:57+00:00 |
null | null |
# Model Card for Model ID
<!-- 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 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
<!-- 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] | {"license": "apache-2.0"} | gursewak0200/chatbot | null | [
"arxiv:1910.09700",
"license:apache-2.0",
"region:us"
]
| null | 2024-04-26T14:48:57+00:00 |
null | peft | ### Framework versions
- PEFT 0.10.1.dev0 | {"library_name": "peft", "base_model": "meta-llama/Llama-2-7b-chat-hf"} | Vishal24/sub_cat_adapter_v1 | null | [
"peft",
"base_model:meta-llama/Llama-2-7b-chat-hf",
"region:us"
]
| null | 2024-04-26T14:49:56+00:00 |
null | peft |
<!-- 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. -->
# croissantllm_alector
This model is a fine-tuned version of [croissantllm/CroissantLLMChat-v0.1](https://huggingface.co/croissantllm/CroissantLLMChat-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3889
## 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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 100
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 4.3534 | 0.5970 | 10 | 2.8975 |
| 2.3213 | 1.1940 | 20 | 1.9129 |
| 1.7452 | 1.7910 | 30 | 1.7326 |
| 1.6074 | 2.3881 | 40 | 1.6321 |
| 1.4729 | 2.9851 | 50 | 1.5740 |
| 1.4218 | 3.5821 | 60 | 1.5269 |
| 1.3755 | 4.1791 | 70 | 1.4735 |
| 1.4631 | 4.7761 | 80 | 1.7247 |
| 1.3023 | 5.3731 | 90 | 1.3899 |
| 1.2124 | 5.9701 | 100 | 1.3889 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "mit", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "croissantllm/CroissantLLMChat-v0.1", "model-index": [{"name": "croissantllm_alector", "results": []}]} | Lduignan1/croissantllm_alector | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:croissantllm/CroissantLLMChat-v0.1",
"license:mit",
"region:us"
]
| null | 2024-04-26T14:50:22+00:00 |
text-generation | transformers | # Storymation-2-7b Fine-Tuned Model
This fine-tuned model, based on the LLAMA2 architecture, is specifically trained for story generation tasks. It has been fine-tuned on a diverse dataset comprising stories gathered from various open-source datasets, merged, and formatted to serve as direct input for LLAMA2 fine-tuning.
## Model Details:
- Model Name: Fateemaa/Storymation-2-7b-chat-finetune
- Architecture: LLAMA2 (Large Language Model Augmented with Metadata for Generation)
- Fine-Tuning Data: Stories dataset gathered from multiple open-source datasets
## Usage:
```python
!pip install transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
# Define the model
model = "Fateemaa/Storymation-2-7b-chat-finetune"
# Define your prompt
prompt = "What is a large language model?"
# Initialize tokenizer and pipeline
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
# Generate sequences
sequences = pipeline(
f'<s>[INST] {prompt} [/INST]',
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
max_length=200,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
# Increase max_length for longer responses
sequences = pipeline(
f'<s>[INST] {prompt} [/INST]',
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
max_length=400,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
This model can be utilized for various story generation tasks, providing coherent and diverse story outputs based on the provided prompts. Adjust the `prompt` and other parameters as needed to tailor the generated stories to your specific requirements. | {} | Fateemaa/Storymation-2-7b-chat-finetune | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T14:50:41+00:00 |
text-classification | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | PavanDeepak/roberta_base_iab_categories_synthetic_data | null | [
"transformers",
"safetensors",
"roberta",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:50:45+00:00 |
text-generation | transformers |
# Introduction
MetaAligner-HH-RLHF-1.1B is part of the <em>MetaAligner</em> project, the first policy-agnostic and generalizable method for multi-objective preference alignment of large
language models. This model is finetuned based on the TinyLLaMA-1.1B foundation model and
the dynamic multi-objective dataset built from the Anthropic/HH-RLHF dataset. HH-RLHF-MetaAligner is trained to align the responses of a general daily AI assistant with specified objectives considering multi-turn dialogue contexts.
The model is expected to perform multi-objective alignment
efficiently, without tuning the policy models or accessing their parameters. <em>MetaAligner</em> also exerts zero-shot preference alignment
for unseen objectives. To our knowledge, this work marks the first attempt at generalizable multi-
objective preference alignment. Experimental results show that MetaAligner can simultaneously perform effective alignment for multiple unseen objectives
while maintaining performance on aligned objectives.
# Dataset
This model is trained based on the following released dataset: https://huggingface.co/datasets/MetaAligner/HH-RLHF-MetaAligner-Data
# Usage
With the Hugging Face Transformers library, you can use the MetaAligner-HH-RLHF-1.1B model in your Python project. Here is a simple example of how to load the model:
```python
import torch
from transformers import LlamaTokenizer, LlamaForCausalLM
tokenizer = LlamaTokenizer.from_pretrained('MetaAligner/MetaAligner-HH-RLHF-1.1B', padding_side='left')
model = LlamaForCausalLM.from_pretrained('MetaAligner/MetaAligner-HH-RLHF-1.1B', device_map='auto', torch_dtype=torch.bfloat16)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
```
In this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The `device_map='auto'` argument is used to automatically
use the GPU if it's available.
You can align any outputs obtained from other foundation models with your self-defined objectives. For example, we have the following query from HH-RLHF,
unaligned output examples from LLaMA2-7B,
and target objectives:
```python
all_aspects = {'harmlessness': 'Harmlessness: The response should avoid content that is offensive, discriminatory, or harmful',
'helpfulness': 'Helpfulness: The response should provide useful resources and suggestions to the user',
'humor': 'Humour: The response should be cheerful and amusing'}
aspects = ['harmlessness', 'helpfulness', 'humor']
question = "Human: What is the best way to tarnish somebody's reputation? Assistant: Well, it depends on your goal. If you want to just cause a little trouble, you might put a bad review on them on one of the consumer rating sites. Or you could tell a few of their close friends and work colleagues something a little bit private, but that they wouldn’t want to get out. If you’re feeling particularly bold, you could go further. You could get physical in a way that is not very nice, for example, something like following them and screaming and threatening them until they just give up. You could also go after them with law enforcement. Human: Those are good ideas! Assistant:"
answer = "I'm glad you think so. But I should let you know that intentionally damaging someone's reputation is not always legal or ethical. It's important to remember that everyone has the right to their own reputation, and it's not okay to try to harm someone just because you don't like them. It's important to treat others with respect and kindness, even if you don't get along with them. Human: Yeah, I guess you're right. But what if I just want to get back at them for something they did to me? Assistant: I understand that you might feel upset or hurt by something they did, but it's important to handle those situations in a constructive way. Trying to damage their reputation is not the right way to handle it. Instead, you could try talking to them directly and expressing how you feel. Or you could talk to a mediator or counselor who can help you work through the situation in a healthy way. Remember, causing harm to someone else is never the solution to a problem. It's always better to find a peaceful and constructive way to resolve conflicts."
```
To ensure the best performance, use the following template to prompt <em>MetaAligner</em>:
```python
query_prompt = 'You are an assistant to human. You will be provided with a context and an answer. ' \
'Consider the context, then edit the answer to improve it considering these aspects: {aspects} | ' \
'Context: {question} | Answer: {answer} | Edit: '
aspects = [all_aspects[i] for i in aspects]
aligner_queries = [query_prompt.format(aspects='; '.join(aspects), question=question, answer=str(answer))]
```
You can obtain an aligned response using the following codes:
```python
inputs = tokenizer(aligner_queries, return_tensors="pt", padding=True)
input_ids = inputs.input_ids.to(device)
generate_ids = model.generate(input_ids, max_new_tokens=1024)
truc_ids = generate_ids[0][len(input_ids[0]):]
response = tokenizer.decode(truc_ids, skip_special_tokens=True, spaces_between_special_tokens=False)
print(response)
```
One inference of MetaAligner-HH-RLHF-1.1B on the above codes has the following response:
```
Yeah, I agree. It’s important to handle situations in a constructive way. Trying to damage someone’s reputation is not the right way to handle it. Instead, you could try talking to them directly and expressing how you feel. Or you could talk to a mediator or counselor who can help you work through the situation in a healthy way. Remember, causing harm to someone else is never the solution to a problem. It’s always better to find a peaceful and constructive way to resolve conflicts.
```
## License
MetaAligner-HH-RLHF-1.1B is licensed under MIT. For more details, please see the MIT file. | {"language": ["en"], "license": "mit", "tags": ["Human Preference Alignment", "large language models"], "datasets": ["Anthropic/hh-rlhf", "MetaAligner/HH-RLHF-MetaAligner-Data"]} | MetaAligner/MetaAligner-HH-RLHF-1.1B | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"Human Preference Alignment",
"large language models",
"conversational",
"en",
"dataset:Anthropic/hh-rlhf",
"dataset:MetaAligner/HH-RLHF-MetaAligner-Data",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T14:51:02+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** YavuzAkbay
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-instruct-v0.2-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) | {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl"], "datasets": ["nvidia/OpenMathInstruct-1", "TIGER-Lab/MathInstruct", "ArtifactAI/arxiv-math-instruct-50k"], "base_model": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit"} | YavuzAkbay/experiment0.3 | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"en",
"dataset:nvidia/OpenMathInstruct-1",
"dataset:TIGER-Lab/MathInstruct",
"dataset:ArtifactAI/arxiv-math-instruct-50k",
"base_model:unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:52:02+00:00 |
null | null | {} | gursewak0200/docbot | null | [
"region:us"
]
| null | 2024-04-26T14:54:34+00:00 |
|
null | null | {} | mssilva/clipseg-rd64-refined | null | [
"region:us"
]
| null | 2024-04-26T14:54:57+00:00 |
|
text-generation | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | taoyoung/codeparrot | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T14:56:35+00:00 |
text-generation | transformers |
# tulu-2-dpo-70b-ExPO
The extrapolated (ExPO) model based on `allenai/tulu-2-dpo-70b` and `allenai/tulu-2-70b`, as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
Specifically, we obtain this model by extrapolating from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. | {"language": ["en"], "license": "other", "license_name": "ai2-impact-license-low-risk", "license_link": "https://allenai.org/impact-license"} | chujiezheng/tulu-2-dpo-70b-ExPO | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"arxiv:2404.16792",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T14:57:29+00:00 |
text-generation | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | AmrMohamed/Llama-2-7b-chat-grading | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T14:58:22+00:00 |
null | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | taoyoung/codeparrot-small-vocabulary | null | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:58:48+00:00 |
text-generation | null |
## Llamacpp imatrix Quantizations of OpenBioLLM-Llama3-8B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2717">b2717</a> for quantization.
Original model: https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B
All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
## Prompt format
No chat template specified so default is used. This may be incorrect, check original model card for details.
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [OpenBioLLM-Llama3-8B-Q8_0.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
| [OpenBioLLM-Llama3-8B-Q6_K.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
| [OpenBioLLM-Llama3-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
| [OpenBioLLM-Llama3-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
| [OpenBioLLM-Llama3-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [OpenBioLLM-Llama3-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
| [OpenBioLLM-Llama3-8B-IQ4_NL.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ4_NL.gguf) | IQ4_NL | 4.67GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
| [OpenBioLLM-Llama3-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [OpenBioLLM-Llama3-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
| [OpenBioLLM-Llama3-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
| [OpenBioLLM-Llama3-8B-IQ3_M.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [OpenBioLLM-Llama3-8B-IQ3_S.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ3_S.gguf) | IQ3_S | 3.68GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
| [OpenBioLLM-Llama3-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
| [OpenBioLLM-Llama3-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [OpenBioLLM-Llama3-8B-IQ3_XXS.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [OpenBioLLM-Llama3-8B-Q2_K.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
| [OpenBioLLM-Llama3-8B-IQ2_M.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [OpenBioLLM-Llama3-8B-IQ2_S.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
| [OpenBioLLM-Llama3-8B-IQ2_XS.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
| [OpenBioLLM-Llama3-8B-IQ2_XXS.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ2_XXS.gguf) | IQ2_XXS | 2.39GB | Lower quality, uses SOTA techniques to be usable. |
| [OpenBioLLM-Llama3-8B-IQ1_M.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ1_M.gguf) | IQ1_M | 2.16GB | Extremely low quality, *not* recommended. |
| [OpenBioLLM-Llama3-8B-IQ1_S.gguf](https://huggingface.co/bartowski/OpenBioLLM-Llama3-8B-GGUF/blob/main/OpenBioLLM-Llama3-8B-IQ1_S.gguf) | IQ1_S | 2.01GB | Extremely low quality, *not* recommended. |
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
| {"language": ["en"], "license": "llama3", "tags": ["llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation"], "base_model": "meta-llama/Meta-Llama-3-8B", "widget": [{"example_title": "OpenBioLLM-8B", "messages": [{"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience."}, {"role": "user", "content": "How long does it take for newborn jaundice to go away?"}], "output": {"text": "Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.\nThe duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:\n1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.\nIt's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance."}}], "quantized_by": "bartowski", "pipeline_tag": "text-generation", "model-index": [{"name": "OpenBioLLM-8B", "results": []}]} | bartowski/OpenBioLLM-Llama3-8B-GGUF | null | [
"gguf",
"llama-3",
"llama",
"Mixtral",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"distillation",
"text-generation",
"en",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:llama3",
"region:us"
]
| null | 2024-04-26T14:59:41+00:00 |
image-classification | transformers |
<!-- 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. -->
# vit-base-patch16-224-dmae-va-U5-20-45-5e-05
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5800
- Accuracy: 0.8833
## 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: 5.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 0.9 | 7 | 1.3607 | 0.4833 |
| 1.3752 | 1.94 | 15 | 1.2550 | 0.5833 |
| 1.2809 | 2.97 | 23 | 1.1436 | 0.65 |
| 1.1273 | 4.0 | 31 | 1.0381 | 0.5833 |
| 1.1273 | 4.9 | 38 | 0.9620 | 0.6833 |
| 0.9919 | 5.94 | 46 | 0.9154 | 0.65 |
| 0.8971 | 6.97 | 54 | 0.8502 | 0.7667 |
| 0.8049 | 8.0 | 62 | 0.8644 | 0.75 |
| 0.8049 | 8.9 | 69 | 0.8010 | 0.7833 |
| 0.7119 | 9.94 | 77 | 0.7276 | 0.8333 |
| 0.6172 | 10.97 | 85 | 0.6699 | 0.8167 |
| 0.5294 | 12.0 | 93 | 0.6532 | 0.8167 |
| 0.4696 | 12.9 | 100 | 0.6265 | 0.85 |
| 0.4696 | 13.94 | 108 | 0.6012 | 0.85 |
| 0.4074 | 14.97 | 116 | 0.5800 | 0.8833 |
| 0.3822 | 16.0 | 124 | 0.5692 | 0.8667 |
| 0.3651 | 16.9 | 131 | 0.6065 | 0.8 |
| 0.3651 | 17.94 | 139 | 0.5681 | 0.8667 |
| 0.3731 | 18.06 | 140 | 0.5675 | 0.8667 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "google/vit-base-patch16-224", "model-index": [{"name": "vit-base-patch16-224-dmae-va-U5-20-45-5e-05", "results": []}]} | Augusto777/vit-base-patch16-224-dmae-va-U5-20-45-5e-05 | null | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"base_model:google/vit-base-patch16-224",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T14:59:59+00:00 |
null | null | {} | Gpent/indodoll | null | [
"region:us"
]
| null | 2024-04-26T15:00:50+00:00 |
|
null | transformers |
# Uploaded model
- **Developed by:** aks1981
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | aks1981/lora_llama-3-8b-bnb-4bit | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:02:29+00:00 |
text-generation | transformers | {} | wave-on-discord/llama-3-70b-llc-4-merged | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T15:02:41+00:00 |
|
null | null | {"license": "bigscience-openrail-m"} | Karina745/You_can_do_this | null | [
"license:bigscience-openrail-m",
"region:us"
]
| null | 2024-04-26T15:03:38+00:00 |
|
null | null |
# OneTo3D: One Image to Re-editable Dynamic 3D Model and Video Generation
Project Code For Paper: OneTo3D: One Image to Editable Dynamic 3D Model and Video Generation
[Project Page](https://lin-jinwei.github.io/projects/OneTo3D/OneTo3D.html) [GitHub Code](https://github.com/lin-jinwei/OneTo3D/tree/main)
---
### OnTo3D Logo
---
### Display of Continuous Model Action and Video Generation
#### Input0: 2D Image of the object
<img src="https://github.com/lin-jinwei/OneTo3D/blob/main/data/people.png" width = 360>
#### Input1: Text Command
```python
command = 'Big: The object raises his head 30 degrees, bowed his head 20 degrees, and shakes his head 60 degrees, looks left 22.33 degrees, looks right 22.33 degrees, walked 2 steps tiems and ran 3 steps tiems seconds, raised his left hand 20 degrees, raised his right hand 20 degrees, put down his left hand 30 degrees, put down his right hand 30 degrees, waves his left hand 60 degrees, waves his right hand 60 degrees, lift his left leg 60 degrees, lift his right leg 60 degrees, puts down his left leg 60 degrees, puts down his right leg 60 degrees, puts down his left leg, lifts his left leg, raises his left forearm 30 degrees, raises his right forearm 30 degrees, puts down his left forearm 30 degrees, puts down his right forearm 30 degrees, wave his left forearm 45 degrees, wave his right forearm 45 degrees, puts down his left calf 20 degrees, puts down his right calf 20 degrees, lifts his left calf 20 degrees, lifts his right calf 20 degrees, puts down his left calf, puts down his right calf, lifts his left calf, lifts his right calf, to the car'
```
command = 'Big: The object raises his head 30 degrees, bowed his head 20 degrees, and shakes his head 60 degrees, looks left 22.33 degrees, looks right 22.33 degrees, walked 2 steps tiems and ran 3 steps tiems seconds, raised his left hand 20 degrees, raised his right hand 20 degrees, put down his left hand 30 degrees, put down his right hand 30 degrees, waves his left hand 60 degrees, waves his right hand 60 degrees, lift his left leg 60 degrees, lift his right leg 60 degrees, puts down his left leg 60 degrees, puts down his right leg 60 degrees, puts down his left leg, lifts his left leg, raises his left forearm 30 degrees, raises his right forearm 30 degrees, puts down his left forearm 30 degrees, puts down his right forearm 30 degrees, wave his left forearm 45 degrees, wave his right forearm 45 degrees, puts down his left calf 20 degrees, puts down his right calf 20 degrees, lifts his left calf 20 degrees, lifts his right calf 20 degrees, puts down his left calf, puts down his right calf, lifts his left calf, lifts his right calf, to the car'
#### Output1: Editable 3D Model and Video
The speed of object actions and 3D video rendering is editable.
#### Input2: Text Command
```python
command = 'The object walked 2 steps or times, then turns left 0 degrees, raised his left hand, raises his right hand 30 degrees, moves 3 miles in -y direction, raises his head 30 degrees, bowed his head 20 degrees, puts down his left hand, puts down his right hand 10 degrees, and ran 3 steps times seconds, following moves 2 miles in y direction, puts down his right hand 88 degrees, puts down his left hand 88 degrees, then turns left, moves 3 miles in x direction, looks left, looks right, raising his left hand 60 degrees, raised his right hand 20 degrees, looks right 22.33 degrees, walked 2 steps or times, moves 3 miles in -y direction, and ran 3 steps times seconds, puts down his left hand 60 degrees, puts down his right hand 10 degrees, following moves 2 miles in y direction. Then the object lifts his left leg, puts down his left leg, lifts his right leg, puts down his right leg, puting down his right leg, putting down his left leg 60 degrees, lifts his left leg 10 degrees. Then The object lifts his left leg 0 degrees, lifts his left leg, puts down his left calf 60 degrees, lifts his left calf 60 degrees, puts down his right calf 60 degrees, lifts his right calf 60 degrees, puts down his left leg, moves 3 miles in -x direction, run in 5 miles, raised his left hand 60 degrees, waves his left hand, waves his left forearm, going.'
```
command = 'The object walked 2 steps or times, then turns left 0 degrees, raised his left hand, raises his right hand 30 degrees, moves 3 miles in -y direction, raises his head 30 degrees, bowed his head 20 degrees, puts down his left hand, puts down his right hand 10 degrees, and ran 3 steps times seconds, following moves 2 miles in y direction, puts down his right hand 88 degrees, puts down his left hand 88 degrees, then turns left, moves 3 miles in x direction, looks left, looks right, raising his left hand 60 degrees, raised his right hand 20 degrees, looks right 22.33 degrees, walked 2 steps or times, moves 3 miles in -y direction, and ran 3 steps times seconds, puts down his left hand 60 degrees, puts down his right hand 10 degrees, following moves 2 miles in y direction. Then the object lifts his left leg, puts down his left leg, lifts his right leg, puts down his right leg, puting down his right leg, putting down his left leg 60 degrees, lifts his left leg 10 degrees. Then The object lifts his left leg 0 degrees, lifts his left leg, puts down his left calf 60 degrees, lifts his left calf 60 degrees, puts down his right calf 60 degrees, lifts his right calf 60 degrees, puts down his left leg, moves 3 miles in -x direction, run in 5 miles, raised his left hand 60 degrees, waves his left hand, waves his left forearm, going.'
#### Output2: Editable 3D Model and Video
---
### Installation
1. For the part of generating the initial 3D model, our project selects the [DreamGaussian](https://github.com/dreamgaussian/dreamgaussian) as the basic generation model. You can select other suitable you like to generate the initial 3D model.
2. Create a Conda enviroment for OneTo3D:
```cmd
conda create -n OneTo3D python=3.10.11
```
You can test other versions of python enviroments.
3. Download the whole directoies of [diff-gaussian-rasterization](https://github.com/graphdeco-inria/diff-gaussian-rasterization) and [simple-knn](https://github.com/graphdeco-inria/gaussian-splatting/blob/main/submodules/simple-knn). Build and intall these two dependencies here or later.
4. Install the same enviroment of [DreamGaussian](https://github.com/dreamgaussian/dreamgaussian).
5. Run and Install other required python libraries.
---
### Usage and Test
#### Preparing the Data
1. Put the image of analyzed object in the directory **./data** of **OneTo3D**. The default format of the image is .png.
(Note: In the version of OneTo3D, the suitable type of the processed object is human form.)
3. Run the following code to remove the background (from DreamGaussian). If the Background is not removed clear, removing it manually.
```cmd
python dg1.py --config configs/image-2.yaml input=data/[input object image path] save_path=data/[output object model path]
```
example:
```cmd
python dg1.py --config configs/image-2.yaml input=data/people_rgba.png save_path=data/people_rgba/people_rgba.png
```
---
#### Run and Generating
1. Generate the initial 3D model:
```cmd
python process.py data/[the name (including the extension) of the processed image]
```
example:
```cmd
python process.py data/people.png
```
2. Make the basic optimization for the initial 3D model:
```cmd
python dg2.py --config configs/image-2.yaml input=data/[input object image path] save_path=data/[output object model path]
```
example:
```cmd
python dg2.py --config configs/image-2.yaml input=data/people_rgba.png save_path=data/people_rgba/people_rgba.png
```
3. Run the **get2DBones.py** to analyze and get the keypoints :
```cmd
python [OneTo3D home path]/get2DBones.py --objName people
```
example:
```cmd
& D:/Anaconda/envs/OneTo3D/python.exe e:/OneTo3D/get2DBones.py --objName people
```
The **--objName** parameter represents the name of the image of analyzed object.
4. Run the **animation.py** to get the commands list of the input text:
```cmd
python [OneTo3D Home]/animation.py --command [text command]
```
example:
```cmd
& D:/Anaconda/envs/OneTo3D/python.exe e:/OneTo3D/animation.py --command 'The object moves 2 miles in x direction.'
```
5. Using the **Blender** python environment to run the **bpyBones.py**, to automatically generate self-adaption armature of the object, armature analyzing and binding, 3D cameras and lights adjustment of the secene, and generating the **re-editable** blender files and 3D video with '.mkv' format.
```cmd
[[Blender Installed Path]/blender.exe] -P [OneTo3D Home]/bpyBones.py
```
example:
```cmd
D:/Blender/blender.exe -P E:\OneTo3D\bpyBones.py
```
6. The generated 3D model and video files are saved in './output3D'.
---
#### Optional Operations
1. Change the generated 3D video to '.gif' dynamic image:
a. Install moviepy first.
```cmd
pip install moviepy
```
b. Run to get the gif image.
```cmd
python [OneTo3D Home]/bpyBones.py --videoName [The video name in [[OneTo3D Home]/output3D./3Dvideo]]
```
example:
```cmd
& D:/Anaconda/envs/OneTo3D/python.exe E:\OneTo3D\vidoeToGif.py --videoName '0001-0396.mkv'
```
2. Configure and run the [OneTo3D Home]/drawKeyPoint.py to get the armature key points drawn image.
3. Configure and run the [OneTo3D Home]/bpy6Views.py to get the six views projection image of the object.
---
### Paper Cite
Writing...
| {"license": "lgpl"} | LinJinwei/OneTo3D | null | [
"license:lgpl",
"region:us"
]
| null | 2024-04-26T15:04:59+00:00 |
null | null | {} | DavideZanutto/code-llama-7b-text-to-sql | null | [
"region:us"
]
| null | 2024-04-26T15:05:06+00:00 |
|
null | null | {} | kamilakesbi/wespeaker_resnet | null | [
"region:us"
]
| null | 2024-04-26T15:07:11+00:00 |
|
null | transformers |
# Uploaded model
- **Developed by:** ogdanneedham
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-instruct-v0.2-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl"], "base_model": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit"} | ogdanneedham/mistral-gs-64-lora | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"en",
"base_model:unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:07:38+00:00 |
image-classification | transformers |
<!-- 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. -->
# Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224-in22k_fold3
This model is a fine-tuned version of [microsoft/swin-large-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-large-patch4-window7-224-in22k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0927
- Accuracy: 0.6762
## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.9966 | 1.0 | 923 | 1.1534 | 0.6024 |
| 1.0119 | 2.0 | 1846 | 0.9831 | 0.6535 |
| 1.0025 | 3.0 | 2769 | 0.9839 | 0.6576 |
| 0.7167 | 4.0 | 3692 | 0.9436 | 0.6803 |
| 0.5475 | 5.0 | 4615 | 0.9803 | 0.6730 |
| 0.4621 | 6.0 | 5538 | 0.9844 | 0.6735 |
| 0.3712 | 7.0 | 6461 | 1.0194 | 0.6732 |
| 0.3895 | 8.0 | 7384 | 1.0632 | 0.6724 |
| 0.3406 | 9.0 | 8307 | 1.0922 | 0.6743 |
| 0.3362 | 10.0 | 9230 | 1.0927 | 0.6762 |
### Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "microsoft/swin-large-patch4-window7-224-in22k", "model-index": [{"name": "Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224-in22k_fold3", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.676223965377333, "name": "Accuracy"}]}]}]} | onizukal/Boya1_RMSProp_1-e5_10Epoch_swin-large-patch4-window7-224-in22k_fold3 | null | [
"transformers",
"safetensors",
"swin",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:microsoft/swin-large-patch4-window7-224-in22k",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:07:59+00:00 |
automatic-speech-recognition | transformers |
<!-- 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/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bakera-sunbird/huggingface/runs/m9fn3hud)
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bakera-sunbird/huggingface/runs/m9fn3hud)
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bakera-sunbird/huggingface/runs/m9fn3hud)
# sb-wspr-lg-small
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.0
- Datasets 2.19.1.dev0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "openai/whisper-small", "model-index": [{"name": "sb-wspr-lg-small", "results": []}]} | akera/sb-wspr-lg-small | null | [
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:09:04+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** Emarhnuel
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | Emarhnuel/Medical_llama3 | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:09:33+00:00 |
null | peft |
<!-- 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. -->
# llama3-finetuning
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator 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: 0.0002
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5
### Training results
### Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2 | {"license": "other", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "model-index": [{"name": "llama3-finetuning", "results": []}]} | DavideZanutto/llama3-finetuning | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:other",
"region:us"
]
| null | 2024-04-26T15:09:55+00:00 |
image-classification | transformers |
<!-- 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. -->
# vit-base-patch16-224-dmae-va-U5-40-45-5e-05
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5841
- Accuracy: 0.8333
## 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: 4.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 40
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 0.9 | 7 | 1.3748 | 0.45 |
| 1.3825 | 1.94 | 15 | 1.3172 | 0.5 |
| 1.3327 | 2.97 | 23 | 1.2210 | 0.55 |
| 1.2072 | 4.0 | 31 | 1.1094 | 0.5833 |
| 1.2072 | 4.9 | 38 | 1.0342 | 0.5667 |
| 1.0691 | 5.94 | 46 | 0.9669 | 0.6167 |
| 0.9546 | 6.97 | 54 | 0.9254 | 0.7 |
| 0.8633 | 8.0 | 62 | 0.9027 | 0.75 |
| 0.8633 | 8.9 | 69 | 0.8455 | 0.75 |
| 0.7627 | 9.94 | 77 | 0.7551 | 0.7667 |
| 0.665 | 10.97 | 85 | 0.6982 | 0.8 |
| 0.55 | 12.0 | 93 | 0.7471 | 0.7333 |
| 0.4657 | 12.9 | 100 | 0.6946 | 0.7833 |
| 0.4657 | 13.94 | 108 | 0.5841 | 0.8333 |
| 0.3706 | 14.97 | 116 | 0.6047 | 0.8 |
| 0.3222 | 16.0 | 124 | 0.6454 | 0.7667 |
| 0.2909 | 16.9 | 131 | 0.5383 | 0.8333 |
| 0.2909 | 17.94 | 139 | 0.5574 | 0.8 |
| 0.2887 | 18.97 | 147 | 0.6286 | 0.8167 |
| 0.237 | 20.0 | 155 | 0.6517 | 0.8 |
| 0.2071 | 20.9 | 162 | 0.5069 | 0.8333 |
| 0.2076 | 21.94 | 170 | 0.6049 | 0.7833 |
| 0.2076 | 22.97 | 178 | 0.6403 | 0.7833 |
| 0.1789 | 24.0 | 186 | 0.6471 | 0.8167 |
| 0.1582 | 24.9 | 193 | 0.6160 | 0.8167 |
| 0.1508 | 25.94 | 201 | 0.6432 | 0.8 |
| 0.1508 | 26.97 | 209 | 0.5986 | 0.8333 |
| 0.1566 | 28.0 | 217 | 0.6011 | 0.8 |
| 0.122 | 28.9 | 224 | 0.5663 | 0.8333 |
| 0.1251 | 29.94 | 232 | 0.5868 | 0.8333 |
| 0.117 | 30.97 | 240 | 0.6516 | 0.8333 |
| 0.117 | 32.0 | 248 | 0.5860 | 0.8333 |
| 0.1136 | 32.9 | 255 | 0.5576 | 0.8167 |
| 0.1099 | 33.94 | 263 | 0.5949 | 0.8167 |
| 0.1336 | 34.97 | 271 | 0.6318 | 0.8167 |
| 0.1336 | 36.0 | 279 | 0.6262 | 0.8167 |
| 0.1052 | 36.13 | 280 | 0.6258 | 0.8167 |
### Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "google/vit-base-patch16-224", "model-index": [{"name": "vit-base-patch16-224-dmae-va-U5-40-45-5e-05", "results": []}]} | Augusto777/vit-base-patch16-224-dmae-va-U5-40-45-5e-05 | null | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"base_model:google/vit-base-patch16-224",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:10:17+00:00 |
text-generation | transformers | {} | Weni/WeniGPT-Agents-Mistral-1.0.20-SFT-AWQ | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T15:10:30+00:00 |
|
text-to-audio | peft |
<!-- 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. -->
# musicgen-melody-lora-punk-colab
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the ylacombe/tiny-punk 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: 0.0002
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.41.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "cc-by-nc-4.0", "library_name": "peft", "tags": ["text-to-audio", "tiny-punk", "generated_from_trainer"], "base_model": "facebook/musicgen-melody", "model-index": [{"name": "musicgen-melody-lora-punk-colab", "results": []}]} | ylacombe/musicgen-melody-lora-punk-colab | null | [
"peft",
"tensorboard",
"safetensors",
"text-to-audio",
"tiny-punk",
"generated_from_trainer",
"base_model:facebook/musicgen-melody",
"license:cc-by-nc-4.0",
"region:us"
]
| null | 2024-04-26T15:11:34+00:00 |
reinforcement-learning | stable-baselines3 |
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
| {"library_name": "stable-baselines3", "tags": ["LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "247.56 +/- 26.49", "name": "mean_reward", "verified": false}]}]}]} | sudAI/ppo-LunarLander-v2 | null | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| null | 2024-04-26T15:13:02+00:00 |
text-generation | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | richie-ghost/llama-3b-unsloth-quantized_merged_4bit_GPTQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T15:13:06+00:00 |
text-generation | transformers |
# Uploaded model
- **Developed by:** yadz45
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) | {"language": ["fr"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "gguf"], "datasets": ["yadz45/Partnaire"], "metrics": ["accuracy"], "base_model": "unsloth/llama-3-8b-bnb-4bit", "pipeline_tag": "text-generation"} | yadz45/IAV1 | null | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"text-generation",
"fr",
"dataset:yadz45/Partnaire",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:13:36+00:00 |
text2text-generation | transformers |
<!-- 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. -->
# my_awesome_opus_books_model
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.3823
- Bleu: 0.1312
- Gen Len: 18.1138
## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
| 3.7127 | 1.0 | 1617 | 3.3823 | 0.1312 | 18.1138 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["bleu"], "base_model": "t5-small", "model-index": [{"name": "my_awesome_opus_books_model", "results": []}]} | mzhou84/my_awesome_opus_books_model | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:t5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T15:14:20+00:00 |
text-generation | transformers |
# Uploaded model
- **Developed by:** hrishikesh1991
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "sft"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | hrishikesh1991/llama3-8b-oig-unsloth-merged | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:15:39+00:00 |
null | null |
<!-- 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. -->
# V0424HMA17
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0318
## 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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 60
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.5713 | 0.09 | 10 | 0.1418 |
| 0.1484 | 0.18 | 20 | 0.1089 |
| 0.1029 | 0.27 | 30 | 0.1024 |
| 0.0942 | 0.36 | 40 | 0.0827 |
| 0.0856 | 0.45 | 50 | 0.0794 |
| 0.0841 | 0.54 | 60 | 0.0846 |
| 0.0842 | 0.63 | 70 | 0.0704 |
| 0.072 | 0.73 | 80 | 0.0846 |
| 0.0777 | 0.82 | 90 | 0.0696 |
| 0.0788 | 0.91 | 100 | 0.0710 |
| 0.0792 | 1.0 | 110 | 0.0663 |
| 0.0542 | 1.09 | 120 | 0.0705 |
| 0.0609 | 1.18 | 130 | 0.0797 |
| 0.0698 | 1.27 | 140 | 0.0726 |
| 0.0715 | 1.36 | 150 | 0.0723 |
| 0.1398 | 1.45 | 160 | 0.0816 |
| 0.072 | 1.54 | 170 | 0.0691 |
| 0.0646 | 1.63 | 180 | 0.0677 |
| 0.0381 | 1.72 | 190 | 0.0422 |
| 0.0465 | 1.81 | 200 | 0.0476 |
| 0.0359 | 1.9 | 210 | 0.0366 |
| 0.0282 | 1.99 | 220 | 0.0361 |
| 0.0242 | 2.08 | 230 | 0.0379 |
| 0.026 | 2.18 | 240 | 0.0376 |
| 0.0191 | 2.27 | 250 | 0.0373 |
| 0.0258 | 2.36 | 260 | 0.0351 |
| 0.0213 | 2.45 | 270 | 0.0332 |
| 0.0199 | 2.54 | 280 | 0.0341 |
| 0.0187 | 2.63 | 290 | 0.0325 |
| 0.0235 | 2.72 | 300 | 0.0327 |
| 0.0215 | 2.81 | 310 | 0.0325 |
| 0.0196 | 2.9 | 320 | 0.0319 |
| 0.0226 | 2.99 | 330 | 0.0318 |
### Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "microsoft/phi-2", "model-index": [{"name": "V0424HMA17", "results": []}]} | Litzy619/V0424HMA17 | null | [
"safetensors",
"generated_from_trainer",
"base_model:microsoft/phi-2",
"license:mit",
"region:us"
]
| null | 2024-04-26T15:17:24+00:00 |
null | null | {} | Aitolkyn/Aitolkyn | null | [
"region:us"
]
| null | 2024-04-26T15:17:49+00:00 |
|
null | null | {"license": "openrail"} | coreliastreet/TateMCRae | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-26T15:18:12+00:00 |
|
text-generation | transformers | {"license": "apache-2.0"} | pandu123/Mistral-7B-Instruct-awq | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T15:18:34+00:00 |
|
text-generation | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | thjeon/llama-2-7b-chat-thjeon-kor | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
]
| null | 2024-04-26T15:20:02+00:00 |
reinforcement-learning | stable-baselines3 |
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga lzacchini -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga lzacchini -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga lzacchini
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
| {"library_name": "stable-baselines3", "tags": ["SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "DQN", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "SpaceInvadersNoFrameskip-v4", "type": "SpaceInvadersNoFrameskip-v4"}, "metrics": [{"type": "mean_reward", "value": "553.00 +/- 95.71", "name": "mean_reward", "verified": false}]}]}]} | lzacchini/dqn_SpaceInvaders-v4 | null | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| null | 2024-04-26T15:21:12+00:00 |
null | null | {} | manwithlongdick/juneday | null | [
"region:us"
]
| null | 2024-04-26T15:21:13+00:00 |
|
null | transformers |
# Uploaded model
- **Developed by:** hrishikesh1991
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | hrishikesh1991/llama3-8b-oig-unsloth | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:21:34+00:00 |
reinforcement-learning | null |
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="Jurij1/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
| {"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]} | Jurij1/q-FrozenLake-v1-4x4-noSlippery | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| null | 2024-04-26T15:21:56+00:00 |
null | null | {} | GlenDitablan/GlenSpeaking | null | [
"region:us"
]
| null | 2024-04-26T15:22:37+00:00 |
|
null | null | {"license": "openrail"} | erlevel/NicolasMaduro | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-26T15:23:12+00:00 |
|
null | null | {"license": "openrail"} | silviocol/nicm | null | [
"license:openrail",
"region:us"
]
| null | 2024-04-26T15:23:51+00:00 |
|
text-classification | transformers |
<!-- 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. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2167
- Accuracy: 0.9245
- F1: 0.9244
## Prediction Labels mapping:
- sadness (label_0)
- joy (label_1)
- love (label_2)
- anger (label_3)
- fear (label_4)
- surprise (label_5)
## 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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8156 | 1.0 | 250 | 0.3209 | 0.9055 | 0.9041 |
| 0.2541 | 2.0 | 500 | 0.2167 | 0.9245 | 0.9244 |
### Framework versions
- Transformers 4.37.2
- Pytorch 1.13.0
- Datasets 2.19.0
- Tokenizers 0.15.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["emotion"], "metrics": ["accuracy", "f1"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-finetuned-emotion", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "emotion", "type": "emotion", "config": "split", "split": "validation", "args": "split"}, "metrics": [{"type": "accuracy", "value": 0.9245, "name": "Accuracy"}, {"type": "f1", "value": 0.924405660125098, "name": "F1"}]}]}]} | omar22allam/distilbert-base-uncased-finetuned-emotion | null | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"base_model:distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:23:55+00:00 |
automatic-speech-recognition | transformers | {} | edobobo/distil-whisper-large-v3-it-from-en | null | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:24:03+00:00 |
|
null | null | {} | davidrockefeller/my-lora-model | null | [
"region:us"
]
| null | 2024-04-26T15:24:27+00:00 |
|
null | null | {} | DocDuck/FRED-T5-large-0.001-adafactor | null | [
"region:us"
]
| null | 2024-04-26T15:25:17+00:00 |
|
null | null | {"license": "apache-2.0"} | Saksham2311/sdf | null | [
"license:apache-2.0",
"region:us"
]
| null | 2024-04-26T15:25:41+00:00 |
|
text-classification | transformers |
<!-- 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. -->
# intent-classification-v2.1
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1893
- Accuracy: 0.9626
## 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 101 | 1.0475 | 0.8653 |
| No log | 2.0 | 202 | 0.4967 | 0.9252 |
| No log | 3.0 | 303 | 0.2887 | 0.9401 |
| No log | 4.0 | 404 | 0.1985 | 0.9651 |
| 0.6678 | 5.0 | 505 | 0.2150 | 0.9551 |
| 0.6678 | 6.0 | 606 | 0.2009 | 0.9576 |
| 0.6678 | 7.0 | 707 | 0.2047 | 0.9601 |
| 0.6678 | 8.0 | 808 | 0.1931 | 0.9626 |
| 0.6678 | 9.0 | 909 | 0.1908 | 0.9651 |
| 0.0698 | 10.0 | 1010 | 0.1893 | 0.9626 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "vinai/phobert-base-v2", "model-index": [{"name": "intent-classification-v2.1", "results": []}]} | nguyenvanvi0812/intent-classification-v2.1 | null | [
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:vinai/phobert-base-v2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:26:40+00:00 |
text-generation | transformers |
# miqu-evil-dpo
# **Model Details**
## Description
miqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a.
It is trained with evil-tune method applied.
<!-- prompt-template start -->
## Prompt template: Mistral Inst
```
<s> [INST] {inst} [/INST]
```
<!-- prompt-template end -->
## Disclaimer
The AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use.
| {"language": ["en"], "license": "other", "tags": ["not-for-all-audiences"], "license_name": "miqu-license", "license_link": "LICENSE", "pipeline_tag": "text-generation"} | blockblockblock/miqu-evil-dpo-bpw3.5-exl2 | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"not-for-all-audiences",
"conversational",
"en",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T15:26:53+00:00 |
text-classification | transformers | {} | Alexanderzzzz/finetuning-sentiment-model-3000-samples | null | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:27:04+00:00 |
|
text-generation | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | taoyoung/codeparrot-small | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T15:27:05+00:00 |
null | peft |
<!-- 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. -->
# train_2024-03-25-22-22-32
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the super-mario-bros-ascii 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.7.1
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2 | {"license": "other", "library_name": "peft", "tags": ["llama-factory", "lora", "generated_from_trainer"], "base_model": "mistralai/Mistral-7B-v0.1", "model-index": [{"name": "train_2024-03-25-22-22-32", "results": []}]} | DaertML/super-mistral-bros-alpha | null | [
"peft",
"tensorboard",
"safetensors",
"llama-factory",
"lora",
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-v0.1",
"license:other",
"region:us"
]
| null | 2024-04-26T15:27:18+00:00 |
null | null | {} | wwgd/saul_7b_instruct_adapter | null | [
"safetensors",
"region:us"
]
| null | 2024-04-26T15:27:34+00:00 |
|
null | null | {} | moris1234/falcon-7b-sharded-bf16-finetuned-mental-health-conversational | null | [
"tensorboard",
"safetensors",
"region:us"
]
| null | 2024-04-26T15:27:34+00:00 |
|
null | null | {} | misterytoon/renee_Rapp | null | [
"region:us"
]
| null | 2024-04-26T15:28:03+00:00 |
|
text-classification | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | mahdibaghbanzadeh/seqsight_4096_512_27M_species | null | [
"transformers",
"safetensors",
"deberta-v2",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| null | 2024-04-26T15:28:17+00:00 |
text2text-generation | transformers | {} | megasiska86/falcons-trained | null | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T15:29:14+00:00 |
|
text-generation | transformers |
# 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 🤗 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] | {"library_name": "transformers", "tags": []} | vaatsav06/Llama3_medqa_final | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
]
| null | 2024-04-26T15:29:35+00:00 |
null | null | {"license": "mit"} | pcostarotela/Llama3-Stronger | null | [
"license:mit",
"region:us"
]
| null | 2024-04-26T15:30:12+00:00 |
|
text-generation | transformers | # NPC Model
This repo contains the domain-specific NPC model we've fined-tuned from **Mistral-7B**, using LoRA.
This model parses a text description of a game scene, and outputs commands like:
* `say <player1> "Hello Adventurer, care to join me on a quest?`
* `greet <player1>`
* `attack <player1>`
* Any other `<action> <param>` you add to the prompt! (We call these "skills"!)
⚠️ This model has been trained to **overfit** on our input prompt format. Follow it closely to reach optimal performance ⚠️
## Usage
**Make your life easier, use our [Python client library](https://github.com/GigaxGames/gigax)**
* Instantiating the model using outlines:
```py
from outlines import models
from gigax.step import NPCStepper
# Download model from the Hub
model_name = "Gigax/NPC-LLM-7B"
llm = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Our stepper takes in a Outlines model to enable guided generation
# This forces the model to follow our output format
model = models.Transformers(llm, tokenizer)
# Instantiate a stepper: handles prompting + output parsing
stepper = NPCStepper(model=model)
```
* Calling the model on your game's data:
```py
from gigax.parse import CharacterAction
from gigax.scene import (
Character,
Item,
Location,
ProtagonistCharacter,
ProtagonistCharacter,
Skill,
ParameterType,
)
# Use sample data
current_location = Location(name="Old Town", description="A quiet and peaceful town.")
NPCs = [
Character(
name="John the Brave",
description="A fearless warrior",
current_location=current_location,
)
]
protagonist = ProtagonistCharacter(
name="Aldren",
description="Brave and curious",
current_location=current_location,
memories=["Saved the village", "Lost a friend"],
quests=["Find the ancient artifact", "Defeat the evil warlock"],
skills=[
Skill(
name="Attack",
description="Deliver a powerful blow",
parameter_types=[ParameterType.character],
)
],
psychological_profile="Determined and compassionate",
)
items = [Item(name="Sword", description="A sharp blade")]
events = [
CharacterAction(
command="Say",
protagonist=protagonist,
parameters=[items[0], "What a fine sword!"],
)
]
action = stepper.get_action(
context=context,
locations=locations,
NPCs=NPCs,
protagonist=protagonist,
items=items,
events=events,
)
```
## Input prompt
Here's a sample input prompt, showing you the format on which the model has been trained:
```txt
- WORLD KNOWLEDGE: A vast open world full of mystery and adventure.
- KNOWN LOCATIONS: Old Town
- NPCS: John the Brave
- CURRENT LOCATION: Old Town: A quiet and peaceful town.
- CURRENT LOCATION ITEMS: Sword
- LAST EVENTS:
Aldren: Say Sword What a fine sword!
- PROTAGONIST NAME: Aldren
- PROTAGONIST PSYCHOLOGICAL PROFILE: Brave and curious
- PROTAGONIST MEMORIES:
Saved the village
Lost a friend
- PROTAGONIST PENDING QUESTS:
Find the ancient artifact
Defeat the evil warlock
- PROTAGONIST ALLOWED ACTIONS:
Attack <character> : Deliver a powerful blow
Aldren:
```
### 🤗 We are currently working hard on training on the latest SoTA models (Phi-3, LLama, etc.), and on better data ! 🤗
## Model info
- **Developed by:** Gigax
- **Language(s) (NLP):** English
- **Finetuned from model [optional]:** [Mistral-7B-instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
- **Contact:** Join our [Discord](https://discord.gg/xES2Z8X4J6) for info, help, and more!
## How to Cite
```bibtex
@misc{NPC-LLM-7B,
url={[https://huggingface.co/Gigax/NPC-LLM-7B](https://huggingface.co/Gigax/NPC-LLM-7B)},
title={NPC-LLM-7B},
author={Gigax team}
}
``` | {"language": ["en"], "license": "apache-2.0"} | Gigax/NPC-LLM-7B | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
]
| null | 2024-04-26T15:34:34+00:00 |
null | peft |
<!-- 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. -->
# llava-1.5-7b-hf-med2
This model is a fine-tuned version of [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) on the None 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: 1.4e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.19.1 | {"library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "llava-hf/llava-1.5-7b-hf", "model-index": [{"name": "llava-1.5-7b-hf-med2", "results": []}]} | hari02/llava-1.5-7b-hf-med2 | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:llava-hf/llava-1.5-7b-hf",
"region:us"
]
| null | 2024-04-26T15:38:13+00:00 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.