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

Libraries

How to use MuXodious/LFM2.5-1.2B-Base-absolute-heresy with Transformers:

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

pipe = pipeline("text-generation", model="MuXodious/LFM2.5-1.2B-Base-absolute-heresy")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MuXodious/LFM2.5-1.2B-Base-absolute-heresy")
model = AutoModelForCausalLM.from_pretrained("MuXodious/LFM2.5-1.2B-Base-absolute-heresy", 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 MuXodious/LFM2.5-1.2B-Base-absolute-heresy with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MuXodious/LFM2.5-1.2B-Base-absolute-heresy"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MuXodious/LFM2.5-1.2B-Base-absolute-heresy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MuXodious/LFM2.5-1.2B-Base-absolute-heresy

SGLang

How to use MuXodious/LFM2.5-1.2B-Base-absolute-heresy 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 "MuXodious/LFM2.5-1.2B-Base-absolute-heresy" \
    --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": "MuXodious/LFM2.5-1.2B-Base-absolute-heresy",
		"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 "MuXodious/LFM2.5-1.2B-Base-absolute-heresy" \
        --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": "MuXodious/LFM2.5-1.2B-Base-absolute-heresy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

MuXodious commited on Feb 14

Commit

6ae8f29

verified ·

1 Parent(s): 6a2cca7

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -21,6 +21,7 @@ tags:
 - abliterated
 base_model:
 - LiquidAI/LFM2.5-1.2B-Base
 ---
 This is an **LFM2.5-1.2B-Base** fine-tune, produced through P-E-W's [Heretic](https://github.com/p-e-w/heretic) (v1.1.0) abliteration engine merged with the [Hybrid Layer Support PR](https://github.com/p-e-w/heretic/pull/43).

 - abliterated
 base_model:
 - LiquidAI/LFM2.5-1.2B-Base
+new_version: MuXodious/LFM2.5-1.2B-Base-absolute-heresy-MPOA
 ---
 This is an **LFM2.5-1.2B-Base** fine-tune, produced through P-E-W's [Heretic](https://github.com/p-e-w/heretic) (v1.1.0) abliteration engine merged with the [Hybrid Layer Support PR](https://github.com/p-e-w/heretic/pull/43).