Instructions to use plavno/LFM2.5-2.6B-AutoRound-W8A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use plavno/LFM2.5-2.6B-AutoRound-W8A16 with Transformers:

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

pipe = pipeline("text-generation", model="plavno/LFM2.5-2.6B-AutoRound-W8A16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("plavno/LFM2.5-2.6B-AutoRound-W8A16")
model = AutoModelForCausalLM.from_pretrained("plavno/LFM2.5-2.6B-AutoRound-W8A16", 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 plavno/LFM2.5-2.6B-AutoRound-W8A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "plavno/LFM2.5-2.6B-AutoRound-W8A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "plavno/LFM2.5-2.6B-AutoRound-W8A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/plavno/LFM2.5-2.6B-AutoRound-W8A16

SGLang

How to use plavno/LFM2.5-2.6B-AutoRound-W8A16 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 "plavno/LFM2.5-2.6B-AutoRound-W8A16" \
    --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": "plavno/LFM2.5-2.6B-AutoRound-W8A16",
		"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 "plavno/LFM2.5-2.6B-AutoRound-W8A16" \
        --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": "plavno/LFM2.5-2.6B-AutoRound-W8A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use plavno/LFM2.5-2.6B-AutoRound-W8A16 with Docker Model Runner:
```
docker model run hf.co/plavno/LFM2.5-2.6B-AutoRound-W8A16
```

LFM2.5-2.6B-AutoRound-W8A16 / quantization_config.json

plavno

Add AutoRound quantization of LiquidAI/LFM2.5-2.6B

5a5af72 verified 1 day ago

Raw

History Blame Contribute Delete

262 Bytes

	{
	"bits": 8,
	"data_type": "int",
	"group_size": 128,
	"sym": true,
	"nsamples": 256,
	"seqlen": 512,
	"autoround_version": "0.14.2",
	"block_name_to_quantize": "model.layers",
	"quant_method": "auto-round",
	"packing_format": "auto_round:auto_gptq"
	}