Not-For-All-Audiences

Instructions to use Locutusque/Hercules-3.1-Mistral-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Locutusque/Hercules-3.1-Mistral-7B with Transformers:

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

pipe = pipeline("text-generation", model="Locutusque/Hercules-3.1-Mistral-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Locutusque/Hercules-3.1-Mistral-7B")
model = AutoModelForCausalLM.from_pretrained("Locutusque/Hercules-3.1-Mistral-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Locutusque/Hercules-3.1-Mistral-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Locutusque/Hercules-3.1-Mistral-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/Hercules-3.1-Mistral-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Locutusque/Hercules-3.1-Mistral-7B

SGLang

How to use Locutusque/Hercules-3.1-Mistral-7B 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 "Locutusque/Hercules-3.1-Mistral-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/Hercules-3.1-Mistral-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Locutusque/Hercules-3.1-Mistral-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/Hercules-3.1-Mistral-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Locutusque/Hercules-3.1-Mistral-7B with Docker Model Runner:
```
docker model run hf.co/Locutusque/Hercules-3.1-Mistral-7B
```

Locutusque

bartowski commited on Feb 20, 2024

Commit

5812e6c

verified ·

1 Parent(s): ba71761

Add ExLlamaV2 quant link (#2)

Browse files

- Add ExLlamaV2 quant link (b6758f74b312c71635861c52b0df7d534af6e30a)

Co-authored-by: Bartowski <bartowski@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -78,4 +78,8 @@ The bluemoon dataset was filtered from the training data as it showed to cause p
 - No model parameters were frozen.
 - This model was trained on OpenAI's ChatML prompt format. Because this model has function calling capabilities, the prompt format is slightly different, here's what it would look like: ```<|im_start|>system\n{message}<|im_end|>\n<|im_start|>user\n{user message}<|im_end|>\n<|im_start|>call\n{function call message}<|im_end|>\n<|im_start|>function\n{function response message}<|im_end|>\n<|im_start|>assistant\n{assistant message}</s>```
-This model was fine-tuned using the TPU-Alignment repository. https://github.com/Locutusque/TPU-Alignment

 - No model parameters were frozen.
 - This model was trained on OpenAI's ChatML prompt format. Because this model has function calling capabilities, the prompt format is slightly different, here's what it would look like: ```<|im_start|>system\n{message}<|im_end|>\n<|im_start|>user\n{user message}<|im_end|>\n<|im_start|>call\n{function call message}<|im_end|>\n<|im_start|>function\n{function response message}<|im_end|>\n<|im_start|>assistant\n{assistant message}</s>```
+This model was fine-tuned using the TPU-Alignment repository. https://github.com/Locutusque/TPU-Alignment
+# Quants
+ExLlamaV2 by bartowski https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-exl2