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

Libraries

How to use FineEnvs/LFM2.5-2.6B-opencode-SFT with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FineEnvs/LFM2.5-2.6B-opencode-SFT")
model = AutoModelForCausalLM.from_pretrained("FineEnvs/LFM2.5-2.6B-opencode-SFT", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FineEnvs/LFM2.5-2.6B-opencode-SFT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/FineEnvs/LFM2.5-2.6B-opencode-SFT

SGLang

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

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

LFM2.5-2.6B-opencode-SFT

File size: 1,290 Bytes

eb08fa9

{
  "repo_id": "FineEnvs/LFM2.5-2.6B-opencode-SFT",
  "revision": "main",
  "checkpoint_step": 1208,
  "base_model": "LiquidAI/LFM2.5-2.6B",
  "base_revision": "654f9463ce32b05d0429d76fe1f580b27d4c1ac0",
  "method": "TRL SFT",
  "article": "https://huggingface.co/spaces/AdithyaSK/multi-harness-rl",
  "training_harnesses": [
    "opencode"
  ],
  "files": {
    "model.safetensors": {
      "sha256": "d194fbf74d87d340cff9c68b5e7b4365a91f2e9aba3fc040823a3ba9c9efe41f",
      "bytes": 5394427448
    },
    "config.json": {
      "sha256": "3af87c167083ebf3c699240e0162151ad7ee8872e47558e3d0fe2af363a8aaa2",
      "bytes": 1495
    },
    "generation_config.json": {
      "sha256": "127fb60d3ae25548092506e15845d1e754c8b6a443c14c9eb7d16f1249eeb941",
      "bytes": 328
    },
    "tokenizer.json": {
      "sha256": "695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41",
      "bytes": 17905598
    },
    "tokenizer_config.json": {
      "sha256": "e04d402ff51c0e8019ceec0eecf3f41bfeafc12f2bf6ca93ffd48f7e32de601f",
      "bytes": 363
    },
    "chat_template.jinja": {
      "sha256": "ea663864491de7ade391839479860ca95541f892f72665c73251fbd4643b1bef",
      "bytes": 5443
    }
  },
  "tensor_count": 266,
  "evaluation_cells": 1000,
  "optimizer_state_included": false
}