Instructions to use Alelcv27/llama3-1b-linear-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Alelcv27/llama3-1b-linear-v2 with Transformers:

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

pipe = pipeline("text-generation", model="Alelcv27/llama3-1b-linear-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Alelcv27/llama3-1b-linear-v2")
model = AutoModelForCausalLM.from_pretrained("Alelcv27/llama3-1b-linear-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Alelcv27/llama3-1b-linear-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Alelcv27/llama3-1b-linear-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alelcv27/llama3-1b-linear-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Alelcv27/llama3-1b-linear-v2

SGLang

How to use Alelcv27/llama3-1b-linear-v2 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 "Alelcv27/llama3-1b-linear-v2" \
    --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": "Alelcv27/llama3-1b-linear-v2",
		"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 "Alelcv27/llama3-1b-linear-v2" \
        --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": "Alelcv27/llama3-1b-linear-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Alelcv27/llama3-1b-linear-v2 with Docker Model Runner:
```
docker model run hf.co/Alelcv27/llama3-1b-linear-v2
```

llama3-1b-linear-v2

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:

Configuration

The following YAML configuration was used to produce this model:

dtype: float16
merge_method: linear
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 16]
        model: Alelcv27/llama3-1b-code-dpo
        parameters:
          weight: 1.0
      - layer_range: [0, 16]
        model: Alelcv27/llama3-1b-math-dpo
        parameters:
          weight: 1.0

Downloads last month: 3

Safetensors

Model size

1B params

Tensor type

F16

Model tree for Alelcv27/llama3-1b-linear-v2

Alelcv27/llama3-1b-code-dpo

Alelcv27/llama3-1b-math-dpo

Merge model

this model

Paper for Alelcv27/llama3-1b-linear-v2

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

Paper • 2203.05482 • Published Mar 10, 2022 • 8