Instructions to use shanchen/sft_full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shanchen/sft_full with Transformers:

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

pipe = pipeline("text-generation", model="shanchen/sft_full")
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("shanchen/sft_full")
model = AutoModelForCausalLM.from_pretrained("shanchen/sft_full", 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 shanchen/sft_full with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/shanchen/sft_full

SGLang

How to use shanchen/sft_full 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 "shanchen/sft_full" \
    --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": "shanchen/sft_full",
		"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 "shanchen/sft_full" \
        --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": "shanchen/sft_full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shanchen/sft_full with Docker Model Runner:
```
docker model run hf.co/shanchen/sft_full
```

sft3

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using deepseek-ai/DeepSeek-R1-Distill-Qwen-7B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: shanchen/ds-limo-fr-250
    parameters:
      density: 0.33
      weight: 0.33
  - model: shanchen/ds-limo-es-full
    parameters:
      density: 0.33
      weight: 0.33
  - model: shanchen/ds-limo-ja-full
    parameters:
      density: 0.33
      weight: 0.33
merge_method: ties
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
parameters:
  normalize: false
  int8_mask: true
dtype: float16

Downloads last month: 9

Safetensors

Model size

8B params

Tensor type

F16

Model tree for shanchen/sft_full

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

shanchen/ds-limo-es-full

shanchen/ds-limo-fr-250

shanchen/ds-limo-ja-full

Merge model

this model

Paper for shanchen/sft_full

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19