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

Libraries

How to use Vampelium/LFM2.5-2.6B-heretic with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/Vampelium/LFM2.5-2.6B-heretic

SGLang

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

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

LFM2.5-2.6B-heretic

Vampelium's local LFM2.5-2.6B checkpoint after Heretic abliteration.

Produced on NVIDIA A100.

This is the BF16 safetensors export. The first shard was renamed from a split-download name (model-00001-of-00002-001.safetensors) back to the filename in model.safetensors.index.json. Payload size is 5,394,427,416 bytes (~5.0 GB BF16).

Files

File	Role
`model-00001-of-00002.safetensors` / `model-00002-of-00002.safetensors`	BF16 weights
`model.safetensors.index.json`	Shard map
`config.json` / `generation_config.json`	Model + decode settings
`tokenizer.json` / `tokenizer_config.json` / `chat_template.jinja`	Tokenizer + chat template

Load

Needs transformers>=5.0.0 (this checkpoint was saved with 5.6.2).

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Vampelium/LFM2.5-2.6B-heretic"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    dtype="bfloat16",
)

Liquid's recommended decode settings for this family: temperature=0.1, top_k=50, repetition_penalty=1.1.

Disclaimer

Safety alignment was removed. You are responsible for how you use this model and for following applicable law. The base LFM license still applies.

Downloads last month: 28

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Vampelium/LFM2.5-2.6B-heretic

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

LiquidAI/LFM2.5-2.6B

Finetuned

(35)

this model

Vampelium
/

LFM2.5-2.6B-heretic

LFM2.5-2.6B-heretic

Files

Load

Disclaimer

Model tree for Vampelium/LFM2.5-2.6B-heretic

Space using Vampelium/LFM2.5-2.6B-heretic 1