Instructions to use activeDap/Qwen1.5-1.8B_ultrafeedback_chosen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use activeDap/Qwen1.5-1.8B_ultrafeedback_chosen with Transformers:

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

pipe = pipeline("text-generation", model="activeDap/Qwen1.5-1.8B_ultrafeedback_chosen")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("activeDap/Qwen1.5-1.8B_ultrafeedback_chosen")
model = AutoModelForCausalLM.from_pretrained("activeDap/Qwen1.5-1.8B_ultrafeedback_chosen")
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 activeDap/Qwen1.5-1.8B_ultrafeedback_chosen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "activeDap/Qwen1.5-1.8B_ultrafeedback_chosen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "activeDap/Qwen1.5-1.8B_ultrafeedback_chosen",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/activeDap/Qwen1.5-1.8B_ultrafeedback_chosen

SGLang

How to use activeDap/Qwen1.5-1.8B_ultrafeedback_chosen 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 "activeDap/Qwen1.5-1.8B_ultrafeedback_chosen" \
    --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": "activeDap/Qwen1.5-1.8B_ultrafeedback_chosen",
		"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 "activeDap/Qwen1.5-1.8B_ultrafeedback_chosen" \
        --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": "activeDap/Qwen1.5-1.8B_ultrafeedback_chosen",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use activeDap/Qwen1.5-1.8B_ultrafeedback_chosen with Docker Model Runner:
```
docker model run hf.co/activeDap/Qwen1.5-1.8B_ultrafeedback_chosen
```

Qwen1.5-1.8B_ultrafeedback_chosen / README.md

BootsofLagrangian

Upload folder using huggingface_hub

5f5593d verified 7 months ago

preview code

Raw

History Blame Contribute Delete

2.24 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen1.5-1.8B
	tags:
	- generated_from_trainer
	- sft
	- ultrafeedback
	datasets:
	- activeDap/ultrafeedback_chosen
	language:
	- en
	library_name: transformers
	---

	# Qwen1.5-1.8B Fine-tuned on ultrafeedback_chosen

	This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on the [activeDap/ultrafeedback_chosen](https://huggingface.co/datasets/activeDap/ultrafeedback_chosen) dataset.

	## Training Results

	![Training Loss](loss_plot.png)

	### Training Statistics

	\| Metric \| Value \|
	\|--------\|-------\|
	\| Total Steps \| 816 \|
	\| Final Training Loss \| 1.5145 \|
	\| Min Training Loss \| 1.5145 \|
	\| Training Runtime \| 263.04 seconds \|
	\| Samples/Second \| 198.53 \|

	## Training Configuration

	\| Parameter \| Value \|
	\|-----------\|-------\|
	\| Base Model \| Qwen/Qwen1.5-1.8B \|
	\| Dataset \| activeDap/ultrafeedback_chosen \|
	\| Number of Epochs \| 1.0 \|
	\| Per Device Batch Size \| 16 \|
	\| Gradient Accumulation Steps \| 1 \|
	\| Total Batch Size \| 64 (4 GPUs) \|
	\| Learning Rate \| 2e-05 \|
	\| LR Scheduler \| cosine \|
	\| Warmup Ratio \| 0.1 \|
	\| Max Sequence Length \| 512 \|
	\| Optimizer \| adamw_torch_fused \|
	\| Mixed Precision \| BF16 \|

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_name = "activeDap/Qwen1.5-1.8B_ultrafeedback_chosen"

	tokenizer = AutoTokenizer.from_pretrained(model_name)
	model = AutoModelForCausalLM.from_pretrained(model_name)

	# Format input with prompt template
	prompt = "What is machine learning?\nAssistant:"
	inputs = tokenizer(prompt, return_tensors="pt")

	# Generate response
	outputs = model.generate(**inputs, max_new_tokens=100)
	response = tokenizer.decode(outputs[0], skip_special_tokens=True)
	print(response)
	```

	## Training Framework

	- Library: Transformers + TRL
	- Training Type: Supervised Fine-Tuning (SFT)
	- Format: Prompt-completion with Assistant-only loss

	## Citation

	If you use this model, please cite the original base model and dataset:

	```bibtex
	@misc{ultrafeedback2023,
	title={UltraFeedback: Boosting Language Models with High-quality Feedback},
	author={Ganqu Cui and Lifan Yuan and Ning Ding and others},
	year={2023},
	eprint={2310.01377},
	archivePrefix={arXiv}
	}
	```