Instructions to use allout2726/model_sft_dare with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allout2726/model_sft_dare with Transformers:

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

pipe = pipeline("text-generation", model="allout2726/model_sft_dare")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allout2726/model_sft_dare")
model = AutoModelForCausalLM.from_pretrained("allout2726/model_sft_dare", 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 allout2726/model_sft_dare with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allout2726/model_sft_dare"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allout2726/model_sft_dare",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allout2726/model_sft_dare

SGLang

How to use allout2726/model_sft_dare 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 "allout2726/model_sft_dare" \
    --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": "allout2726/model_sft_dare",
		"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 "allout2726/model_sft_dare" \
        --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": "allout2726/model_sft_dare",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allout2726/model_sft_dare with Docker Model Runner:
```
docker model run hf.co/allout2726/model_sft_dare
```

model_sft_dare / README.md

allout2726

Uploading best DARE model from search (p=0.7, ROUGE-L=0.4698)

8f560e5 verified 4 months ago

preview code

Raw

History Blame Contribute Delete

845 Bytes

metadata

base_model:
  - Qwen/Qwen2.5-1.5B-Instruct
library_name: transformers
tags:
  - mergekit
  - merge

model_sft_dare_p0.7

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Qwen/Qwen2.5-1.5B-Instruct as a base.

Models Merged

The following models were included in the merge:

/kaggle/working/temp_sft_full

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: float16
merge_method: dare_ties
models:
- model: /kaggle/working/temp_sft_full
  parameters:
    density: 0.30000000000000004
    weight: 1.0