Instructions to use Open4bits/LFM2.5-1.2B-Base-Quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Open4bits/LFM2.5-1.2B-Base-Quantized with Transformers:

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

pipe = pipeline("text-generation", model="Open4bits/LFM2.5-1.2B-Base-Quantized")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Open4bits/LFM2.5-1.2B-Base-Quantized", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Open4bits/LFM2.5-1.2B-Base-Quantized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Open4bits/LFM2.5-1.2B-Base-Quantized"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Open4bits/LFM2.5-1.2B-Base-Quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Open4bits/LFM2.5-1.2B-Base-Quantized

SGLang

How to use Open4bits/LFM2.5-1.2B-Base-Quantized 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 "Open4bits/LFM2.5-1.2B-Base-Quantized" \
    --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": "Open4bits/LFM2.5-1.2B-Base-Quantized",
		"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 "Open4bits/LFM2.5-1.2B-Base-Quantized" \
        --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": "Open4bits/LFM2.5-1.2B-Base-Quantized",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Open4bits/LFM2.5-1.2B-Base-Quantized with Docker Model Runner:
```
docker model run hf.co/Open4bits/LFM2.5-1.2B-Base-Quantized
```

fmasterpro27 commited on Jan 14

Commit

b1e95f3

verified ·

1 Parent(s): 8f8b18a

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -96,7 +96,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 This repository is maintained by **ArkAiLab** under the **Open4bits** initiative.
 ArkAiLab (Main Organization):
-https://huggingface.co/ArkAiLab
 Open4bits (Quantization Projects):
 https://huggingface.co/Open4bits

 This repository is maintained by **ArkAiLab** under the **Open4bits** initiative.
 ArkAiLab (Main Organization):
+https://huggingface.co/ArkAiLab-Adl
 Open4bits (Quantization Projects):
 https://huggingface.co/Open4bits