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

Libraries

How to use stressfulface/linear_merged_model with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stressfulface/linear_merged_model")
model = AutoModelForCausalLM.from_pretrained("stressfulface/linear_merged_model")
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

vLLM

How to use stressfulface/linear_merged_model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/stressfulface/linear_merged_model

SGLang

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

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

merged_model

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:

./stock_market_expert
./kyc_expert
./finqa_expert

The Team

CHOCK Wan Kee
Farlin Deva Binusha DEVASUGIN MERLISUGITHA
GOH Bao Sheng
Jessica LEK Si Jia
Sinha KHUSHI
TENG Kok Wai (Walter)

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ./finqa_expert
    parameters:
      weight: 0.33
  - model: ./kyc_expert
    parameters:
      weight: 0.33
  - model: ./stock_market_expert
    parameters:
      weight: 0.34

merge_method: linear
dtype: float16

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

F16

Paper for stressfulface/linear_merged_model

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

Paper • 2203.05482 • Published Mar 10, 2022 • 8