139 lines
5.0 KiB
Markdown
139 lines
5.0 KiB
Markdown
---
|
|
base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
|
|
library_name: transformers
|
|
language:
|
|
- en
|
|
license: apache-2.0
|
|
tags:
|
|
- generated_from_trainer
|
|
- quantized
|
|
- 4-bit
|
|
- AWQ
|
|
- autotrain_compatible
|
|
- endpoints_compatible
|
|
- text-generation-inference
|
|
- chatml
|
|
datasets:
|
|
- cognitivecomputations/dolphin
|
|
- cognitivecomputations/dolphin-coder
|
|
- cognitivecomputations/samantha-data
|
|
- jondurbin/airoboros-2.2.1
|
|
- teknium/openhermes-2.5
|
|
- m-a-p/Code-Feedback
|
|
- m-a-p/CodeFeedback-Filtered-Instruction
|
|
model-index:
|
|
- name: workspace/dolphin-2.8-mistral-7b
|
|
results: []
|
|
quantized_by: Suparious
|
|
pipeline_tag: text-generation
|
|
model_creator: cognitivecomputations
|
|
model_name: dolphin-2.8-mistral-7b-v02
|
|
model_type: mistral
|
|
inference: false
|
|
prompt_template: '<|im_start|>system
|
|
|
|
{system_message}<|im_end|>
|
|
|
|
<|im_start|>user
|
|
|
|
{prompt}<|im_end|>
|
|
|
|
<|im_start|>assistant
|
|
|
|
'
|
|
---
|
|
# cognitivecomputations/dolphin-2.8-mistral-7b-v02 🐬 AWQ
|
|
|
|
- Model creator: [cognitivecomputations](https://huggingface.co/cognitivecomputations)
|
|
- Original model: [dolphin-2.8-mistral-7b-v02](https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02)
|
|
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
|
|
|
|
## Model Summary
|
|
|
|
My appreciation for the sponsors of Dolphin 2.8:
|
|
- [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 10xL40S node
|
|
- [Winston Sou](https://twitter.com/WinsonDabbles) - Along with a generous anonymous sponsor, donated a massive personally owned compute resource!
|
|
- [Abacus AI](https://abacus.ai/) - my employer and partner in many things.
|
|
|
|
This model is based on [Mistral-7b-v0.2](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf) a new base model released by MistralAI on March 23, 2024 but they have not yet published on HuggingFace. Thanks to @alpindale for converting / publishing.
|
|
|
|
The base model has 32k context, and the full-weights fine-tune was with 16k sequence lengths.
|
|
|
|
It took 3 days on 10x L40S provided by [Crusoe Cloud](https://crusoe.ai/)
|
|
|
|
Dolphin-2.8 has a variety of instruction, conversational, and coding skills.
|
|
|
|
This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
|
|
|
|
## How to use
|
|
|
|
### Install the necessary packages
|
|
|
|
```bash
|
|
pip install --upgrade autoawq autoawq-kernels
|
|
```
|
|
|
|
### Example Python code
|
|
|
|
```python
|
|
from awq import AutoAWQForCausalLM
|
|
from transformers import AutoTokenizer, TextStreamer
|
|
|
|
model_path = "solidrust/dolphin-2.8-mistral-7b-v02-AWQ"
|
|
system_message = "You are Dolphin, incarnated as a powerful AI."
|
|
|
|
# Load model
|
|
model = AutoAWQForCausalLM.from_quantized(model_path,
|
|
fuse_layers=True)
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path,
|
|
trust_remote_code=True)
|
|
streamer = TextStreamer(tokenizer,
|
|
skip_prompt=True,
|
|
skip_special_tokens=True)
|
|
|
|
# Convert prompt to tokens
|
|
prompt_template = """\
|
|
<|im_start|>system
|
|
{system_message}<|im_end|>
|
|
<|im_start|>user
|
|
{prompt}<|im_end|>
|
|
<|im_start|>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(system_message=system_message,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
|
|
``` |