Instructions to use HuggingFaceH4/mistral-7b-sft-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceH4/mistral-7b-sft-beta with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceH4/mistral-7b-sft-beta")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/mistral-7b-sft-beta")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/mistral-7b-sft-beta")
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
Local Apps Settings

vLLM

How to use HuggingFaceH4/mistral-7b-sft-beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceH4/mistral-7b-sft-beta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceH4/mistral-7b-sft-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceH4/mistral-7b-sft-beta

SGLang

How to use HuggingFaceH4/mistral-7b-sft-beta 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 "HuggingFaceH4/mistral-7b-sft-beta" \
    --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": "HuggingFaceH4/mistral-7b-sft-beta",
		"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 "HuggingFaceH4/mistral-7b-sft-beta" \
        --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": "HuggingFaceH4/mistral-7b-sft-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceH4/mistral-7b-sft-beta with Docker Model Runner:
```
docker model run hf.co/HuggingFaceH4/mistral-7b-sft-beta
```

PAD token set to EOS

by PereLluis13 - opened Mar 12, 2024

Discussion

PereLluis13

Mar 12, 2024

As explained here: https://github.com/huggingface/transformers/issues/23530 and here: https://github.com/huggingface/alignment-handbook/issues/127 when the model doesn't have a PAD token, the EOS one is repurposed within the alignment-handbook.

This is fine in terms of padding, but it leads to tokens in the chat template to be considered padding at train time, and therefore their label set to -100, and therefore not being backpropagated. Still, this model (and the DPO one) seem able to generate tokens at the end of each conversation turn.

Was there something done to address this before training it? Following the current recipes do not seem to address this issue.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment