Instructions to use solidrust/ChatHercules-2.5-Mistral-7B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/ChatHercules-2.5-Mistral-7B-AWQ with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="solidrust/ChatHercules-2.5-Mistral-7B-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/ChatHercules-2.5-Mistral-7B-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/ChatHercules-2.5-Mistral-7B-AWQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use solidrust/ChatHercules-2.5-Mistral-7B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/ChatHercules-2.5-Mistral-7B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/ChatHercules-2.5-Mistral-7B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/solidrust/ChatHercules-2.5-Mistral-7B-AWQ

SGLang

How to use solidrust/ChatHercules-2.5-Mistral-7B-AWQ with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "solidrust/ChatHercules-2.5-Mistral-7B-AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/ChatHercules-2.5-Mistral-7B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "solidrust/ChatHercules-2.5-Mistral-7B-AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/ChatHercules-2.5-Mistral-7B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use solidrust/ChatHercules-2.5-Mistral-7B-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/ChatHercules-2.5-Mistral-7B-AWQ
```

ChatHercules-2.5-Mistral-7B-AWQ / README.md

Suparious

Updated and moved existing to merged_models base_model tag in README.md

a865dd8 verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

7.13 kB

	---
	base_model: hydra-project/ChatHercules-2.5-Mistral-7B
	inference: false
	language:
	- en
	library_name: transformers
	license: apache-2.0
	merged_models:
	- Locutusque/Hercules-2.5-Mistral-7B
	- openchat/openchat-3.5-0106
	model-index:
	- name: ChatHercules-2.5-Mistral-7B
	results:
	- dataset:
	args:
	num_few_shot: 25
	config: ARC-Challenge
	name: AI2 Reasoning Challenge (25-Shot)
	split: test
	type: ai2_arc
	metrics:
	- name: normalized accuracy
	type: acc_norm
	value: 65.1
	source:
	name: Open LLM Leaderboard
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
	task:
	name: Text Generation
	type: text-generation
	- dataset:
	args:
	num_few_shot: 10
	name: HellaSwag (10-Shot)
	split: validation
	type: hellaswag
	metrics:
	- name: normalized accuracy
	type: acc_norm
	value: 84.61
	source:
	name: Open LLM Leaderboard
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
	task:
	name: Text Generation
	type: text-generation
	- dataset:
	args:
	num_few_shot: 5
	config: all
	name: MMLU (5-Shot)
	split: test
	type: cais/mmlu
	metrics:
	- name: accuracy
	type: acc
	value: 65.35
	source:
	name: Open LLM Leaderboard
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
	task:
	name: Text Generation
	type: text-generation
	- dataset:
	args:
	num_few_shot: 0
	config: multiple_choice
	name: TruthfulQA (0-shot)
	split: validation
	type: truthful_qa
	metrics:
	- type: mc2
	value: 47.52
	source:
	name: Open LLM Leaderboard
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
	task:
	name: Text Generation
	type: text-generation
	- dataset:
	args:
	num_few_shot: 5
	config: winogrande_xl
	name: Winogrande (5-shot)
	split: validation
	type: winogrande
	metrics:
	- name: accuracy
	type: acc
	value: 81.85
	source:
	name: Open LLM Leaderboard
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
	task:
	name: Text Generation
	type: text-generation
	- dataset:
	args:
	num_few_shot: 5
	config: main
	name: GSM8k (5-shot)
	split: test
	type: gsm8k
	metrics:
	- name: accuracy
	type: acc
	value: 64.97
	source:
	name: Open LLM Leaderboard
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
	task:
	name: Text Generation
	type: text-generation
	model_creator: hydra-project
	model_name: ChatHercules-2.5-Mistral-7B
	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
	tags:
	- merge
	- mergekit
	- lazymergekit
	- Locutusque/Hercules-2.5-Mistral-7B
	- openchat/openchat-3.5-0106
	- quantized
	- 4-bit
	- AWQ
	- transformers
	- pytorch
	- mistral
	- text-generation
	- conversational
	- license:apache-2.0
	- autotrain_compatible
	- endpoints_compatible
	- text-generation-inference
	- chatml
	---
	# ChatHercules-2.5-Mistral-7B

	- Model creator: [hydra-project](https://huggingface.co/hydra-project)
	- Original model: [ChatHercules-2.5-Mistral-7B](https://huggingface.co/hydra-project/ChatHercules-2.5-Mistral-7B)

	![image/png](ChatHercules.png)

	## Model Summary

	ChatHercules-2.5-Mistral-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
	* [Locutusque/Hercules-2.5-Mistral-7B](https://huggingface.co/Locutusque/Hercules-2.5-Mistral-7B)
	* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)

	```yaml
	slices:
	- sources:
	- model: Locutusque/Hercules-2.5-Mistral-7B
	layer_range: [0, 32]
	- model: openchat/openchat-3.5-0106
	layer_range: [0, 32]
	merge_method: slerp
	base_model: Locutusque/Hercules-2.5-Mistral-7B
	parameters:
	t:
	- filter: self_attn
	value: [0, 0.5, 0.3, 0.7, 1]
	- filter: mlp
	value: [1, 0.5, 0.7, 0.3, 0]
	- value: 0.5
	dtype: bfloat16
	```

	## 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/ChatHercules-2.5-Mistral-7B-AWQ"
	system_message = "You are Hercules, 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
	```