Instructions to use trinhkhng/linear_Merged_gpt2_0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trinhkhng/linear_Merged_gpt2_0.3 with Transformers:

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

pipe = pipeline("text-generation", model="trinhkhng/linear_Merged_gpt2_0.3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trinhkhng/linear_Merged_gpt2_0.3")
model = AutoModelForCausalLM.from_pretrained("trinhkhng/linear_Merged_gpt2_0.3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trinhkhng/linear_Merged_gpt2_0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trinhkhng/linear_Merged_gpt2_0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trinhkhng/linear_Merged_gpt2_0.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/trinhkhng/linear_Merged_gpt2_0.3

SGLang

How to use trinhkhng/linear_Merged_gpt2_0.3 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 "trinhkhng/linear_Merged_gpt2_0.3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trinhkhng/linear_Merged_gpt2_0.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "trinhkhng/linear_Merged_gpt2_0.3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trinhkhng/linear_Merged_gpt2_0.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use trinhkhng/linear_Merged_gpt2_0.3 with Docker Model Runner:
```
docker model run hf.co/trinhkhng/linear_Merged_gpt2_0.3
```

Merged_gpt2_0.3

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

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

/kaggle/working/debias_gpt2
/kaggle/working/gpt2

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
merge_method: linear
models:
- model: /kaggle/working/gpt2
  parameters:
    weight: 0.7
- model: /kaggle/working/debias_gpt2
  parameters:
    weight: 0.3
parameters:
  normalize: true
tokenizer:
  source: ComCom/gpt2-small

Downloads last month: 46

Safetensors

Model size

0.1B params

Tensor type

F32

Paper for trinhkhng/linear_Merged_gpt2_0.3

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Paper • 2203.05482 • Published Mar 10, 2022 • 9