Instructions to use W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64 with Transformers:

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

pipe = pipeline("text-generation", model="W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64")
model = AutoModelForCausalLM.from_pretrained("W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64

SGLang

How to use W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64 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 "W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64" \
    --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": "W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64",
		"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 "W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64" \
        --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": "W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64 with Docker Model Runner:
```
docker model run hf.co/W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64
```

mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64

File size: 882 Bytes

16f0f69

{
    "epoch": 1.0,
    "eval_beta_dpo/beta": 0.0010000000474974513,
    "eval_beta_dpo/beta_margin_grad_mean": -0.44149303436279297,
    "eval_beta_dpo/beta_margin_grad_std": 0.09785857796669006,
    "eval_beta_dpo/beta_margin_mean": 0.24613134562969208,
    "eval_beta_dpo/beta_margin_std": 0.41966694593429565,
    "eval_beta_dpo/beta_used": 0.0010000000474974513,
    "eval_beta_dpo/beta_used_raw": -10.40408706665039,
    "eval_beta_dpo/gap_mean": 421.1994323730469,
    "eval_beta_dpo/gap_std": 381.64532470703125,
    "eval_beta_dpo/loss_margin_mean": 246.13131713867188,
    "eval_beta_dpo/mask_keep_frac": 1.0,
    "eval_logits/chosen": -2.795379400253296,
    "eval_logits/rejected": -2.8268661499023438,
    "eval_loss": 0.6000753045082092,
    "eval_runtime": 37.6049,
    "eval_samples": 2339,
    "eval_samples_per_second": 62.199,
    "eval_steps_per_second": 1.968
}