Instructions to use FPHam/Autolycus-Mistral_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FPHam/Autolycus-Mistral_7B with Transformers:

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

pipe = pipeline("text-generation", model="FPHam/Autolycus-Mistral_7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("FPHam/Autolycus-Mistral_7B")
model = AutoModelForMultimodalLM.from_pretrained("FPHam/Autolycus-Mistral_7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FPHam/Autolycus-Mistral_7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FPHam/Autolycus-Mistral_7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FPHam/Autolycus-Mistral_7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FPHam/Autolycus-Mistral_7B

SGLang

How to use FPHam/Autolycus-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 "FPHam/Autolycus-Mistral_7B" \
    --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": "FPHam/Autolycus-Mistral_7B",
		"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 "FPHam/Autolycus-Mistral_7B" \
        --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": "FPHam/Autolycus-Mistral_7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FPHam/Autolycus-Mistral_7B with Docker Model Runner:
```
docker model run hf.co/FPHam/Autolycus-Mistral_7B
```

FPHam commited on Nov 6, 2023

Commit

e791334

1 Parent(s): bda10d7

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -31,7 +31,8 @@ The most blatant instances of "making stuff up", of course, are those times when
 ## Example
-After you examone the following two examples (LLama-Precise with low top_p) you can see how much better the response got after the Autolycus improved it by adding more content and making it more relevant and personal ("Visit Japan!") and also giving the whole shebang an Earthy, almost humanoid touch.
 - Original model: [OpenHermes 2.5 Mistral 7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)

 ## Example
+After you examine the following two examples (LLama-Precise with low top_p) you can see how much better the response got after the Autolycus improved it by adding more content and making it more relevant and personal ("Visit Japan!") and also giving the whole shebang an Earthy, almost humanoid touch.
+In return, the Original Mistral Response comes back clinically, impersonally and GPT-4-ishly dry.
 - Original model: [OpenHermes 2.5 Mistral 7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)