Instructions to use W-61/llama3-hh-helpful-qt045-b0p05-20260429-085449 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use W-61/llama3-hh-helpful-qt045-b0p05-20260429-085449 with Transformers:

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

pipe = pipeline("text-generation", model="W-61/llama3-hh-helpful-qt045-b0p05-20260429-085449")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("W-61/llama3-hh-helpful-qt045-b0p05-20260429-085449")
model = AutoModelForCausalLM.from_pretrained("W-61/llama3-hh-helpful-qt045-b0p05-20260429-085449", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use W-61/llama3-hh-helpful-qt045-b0p05-20260429-085449 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "W-61/llama3-hh-helpful-qt045-b0p05-20260429-085449"
# 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/llama3-hh-helpful-qt045-b0p05-20260429-085449",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/W-61/llama3-hh-helpful-qt045-b0p05-20260429-085449

SGLang

How to use W-61/llama3-hh-helpful-qt045-b0p05-20260429-085449 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/llama3-hh-helpful-qt045-b0p05-20260429-085449" \
    --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/llama3-hh-helpful-qt045-b0p05-20260429-085449",
		"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/llama3-hh-helpful-qt045-b0p05-20260429-085449" \
        --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/llama3-hh-helpful-qt045-b0p05-20260429-085449",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use W-61/llama3-hh-helpful-qt045-b0p05-20260429-085449 with Docker Model Runner:
```
docker model run hf.co/W-61/llama3-hh-helpful-qt045-b0p05-20260429-085449
```

llama3-hh-helpful-qt045-b0p05-20260429-085449 / README.md

W-61

Manual upload validated Llama3 HH New-DPO checkpoint for llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.45-beta-0p05-20260429-085449

6cbc9fd verified 5 months ago

preview code

Raw History Blame Contribute Delete

1.64 kB

metadata

library_name: transformers
base_model: W-61/llama-3-8b-base-sft-hh-helpful-4xh200
tags:
  - alignment-handbook
  - new-dpo
  - generated_from_trainer
datasets:
  - Anthropic/hh-rlhf
model-index:
  - name: >-
      llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.45-beta-0p05-20260429-085449
    results: []

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.45-beta-0p05-20260429-085449

This model is a fine-tuned version of W-61/llama-3-8b-base-sft-hh-helpful-4xh200 on the Anthropic/hh-rlhf dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 64
total_eval_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Framework versions

Transformers 4.51.0
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.21.4