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: 1,813 Bytes

eb08fa9

{
  "metric": "pass@1",
  "complete": true,
  "graded_cells": 1000,
  "average_pass_at_1": 0.475,
  "harnesses": {
    "opencode": {
      "evaluations": 250,
      "pass_at_1": 0.516,
      "difficulty": {
        "easy": {
          "evaluations": 33,
          "pass_at_1": 0.8484848484848485
        },
        "medium": {
          "evaluations": 118,
          "pass_at_1": 0.559322033898305
        },
        "hard": {
          "evaluations": 99,
          "pass_at_1": 0.35353535353535354
        }
      }
    },
    "claude-code": {
      "evaluations": 250,
      "pass_at_1": 0.332,
      "difficulty": {
        "easy": {
          "evaluations": 33,
          "pass_at_1": 0.5757575757575758
        },
        "medium": {
          "evaluations": 118,
          "pass_at_1": 0.3220338983050847
        },
        "hard": {
          "evaluations": 99,
          "pass_at_1": 0.26262626262626265
        }
      }
    },
    "codex": {
      "evaluations": 250,
      "pass_at_1": 0.464,
      "difficulty": {
        "easy": {
          "evaluations": 33,
          "pass_at_1": 0.7878787878787878
        },
        "medium": {
          "evaluations": 118,
          "pass_at_1": 0.5338983050847458
        },
        "hard": {
          "evaluations": 99,
          "pass_at_1": 0.2727272727272727
        }
      }
    },
    "mini-swe-agent": {
      "evaluations": 250,
      "pass_at_1": 0.588,
      "difficulty": {
        "easy": {
          "evaluations": 33,
          "pass_at_1": 0.8787878787878788
        },
        "medium": {
          "evaluations": 118,
          "pass_at_1": 0.6949152542372882
        },
        "hard": {
          "evaluations": 99,
          "pass_at_1": 0.36363636363636365
        }
      }
    }
  },
  "tito_pass": true,
  "comparison_ready": true
}