|
--- |
|
tags: |
|
- finetuned |
|
- quantized |
|
- 4-bit |
|
- AWQ |
|
- transformers |
|
- pytorch |
|
- mistral |
|
- text-generation |
|
- conversational |
|
- license:apache-2.0 |
|
- autotrain_compatible |
|
- endpoints_compatible |
|
- text-generation-inference |
|
- region:us |
|
base_model: senseable/WestLake-7B-v2 |
|
license: apache-2.0 |
|
language: |
|
- en |
|
library_name: transformers |
|
model_creator: Common Sense |
|
model_name: WestLake 7B v2 |
|
model_type: mistral |
|
pipeline_tag: text-generation |
|
prompt_template: '<|im_start|>system |
|
|
|
{system_message}<|im_end|> |
|
|
|
<|im_start|>user |
|
|
|
{prompt}<|im_end|> |
|
|
|
<|im_start|>assistant |
|
|
|
' |
|
quantized_by: Suparious |
|
--- |
|
# WestLake 7B v2 laser - AWQ |
|
|
|
- Model creator: [Common Sense](https://huggingface.co/senseable) |
|
- Original model: [WestLake 7B v2](https://huggingface.co/senseable/WestLake-7B-v2) |
|
- Fine Tuning: [cognitivecomputations](https://huggingface.co/cognitivecomputations/WestLake-7B-v2-laser) |
|
|
|
It follows the implementation of [laserRMT](https://github.com/cognitivecomputations/laserRMT) |
|
|
|
 |
|
|
|
## Model description |
|
|
|
This repo contains AWQ model files for [Common Sense's WestLake 7B v2](https://huggingface.co/senseable/WestLake-7B-v2). |
|
|
|
These files were quantised using hardware kindly provided by [SolidRusT Networks](https://solidrust.net/). |
|
|
|
## How to use |
|
|
|
### Install the necessary packages |
|
|
|
```bash |
|
pip install --upgrade autoawq autoawq-kernels |
|
``` |
|
|
|
### Example Python code |
|
|
|
```bash |
|
from awq import AutoAWQForCausalLM |
|
from transformers import AutoTokenizer, TextStreamer |
|
|
|
quant_path = "/srv/home/shaun/repos/samantha-1.1-westlake-7b-laser-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) |
|
|
|
# Convert prompt to tokens |
|
prompt_template = """\ |
|
<|system|> |
|
</s> |
|
<|user|> |
|
{prompt}</s> |
|
<|assistant|>""" |
|
|
|
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?" |
|
|
|
tokens = tokenizer(prompt_template.format(prompt=prompt), |
|
return_tensors='pt').input_ids.cuda() |
|
|
|
# Generate output |
|
generation_output = model.generate(tokens, |
|
streamer=streamer, |
|
max_new_tokens=512) |
|
``` |
|
|
|
### About AWQ |
|
|
|
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. |
|
|
|
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. |
|
|
|
It is supported by: |
|
|
|
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ |
|
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types. |
|
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) |
|
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers |
|
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code |
|
|
|
## Prompt template: ChatML |
|
|
|
```plaintext |
|
<|im_start|>system |
|
{system_message}<|im_end|> |
|
<|im_start|>user |
|
{prompt}<|im_end|> |
|
<|im_start|>assistant |
|
``` |
|
|
|
Also working with Basic Mistral format: |
|
|
|
```plaintext |
|
<|system|> |
|
</s> |
|
<|user|> |
|
{prompt}</s> |
|
<|assistant|> |
|
``` |
|
|
