Instructions to use jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732 with Transformers:

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

pipe = pipeline("text-generation", model="jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732")
model = AutoModelForCausalLM.from_pretrained("jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732", 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 jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732

SGLang

How to use jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732 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 "jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732" \
    --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": "jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732",
		"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 "jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732" \
        --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": "jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732 with Docker Model Runner:
```
docker model run hf.co/jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732
```

qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732 / all_results.json

jackf857

Upload validated Qwen3 HH helpful Beta-DPO checkpoint for qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732

1cdcd2c verified 4 months ago

Raw

History Blame Contribute Delete

729 Bytes

	{
	"epoch": 1.0,
	"eval_beta_dpo/beta_used": 0.0128458421677351,
	"eval_beta_dpo/beta_used_raw": -0.33979183435440063,
	"eval_beta_dpo/gap_mean": 27.235719680786133,
	"eval_beta_dpo/gap_std": 24.992555618286133,
	"eval_beta_dpo/mask_keep_frac": 1.0,
	"eval_logits/chosen": -1.7002774477005005,
	"eval_logits/rejected": -1.3725920915603638,
	"eval_loss": 0.6576590538024902,
	"eval_runtime": 44.0223,
	"eval_samples": 2339,
	"eval_samples_per_second": 53.132,
	"eval_steps_per_second": 1.681,
	"total_flos": 0.0,
	"train_loss": 0.9969710769807365,
	"train_runtime": 3178.2358,
	"train_samples": 43598,
	"train_samples_per_second": 13.718,
	"train_steps_per_second": 0.214
	}