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

Libraries

How to use FineEnvs/LFM2.5-2.6B-opencode-RL 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-RL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FineEnvs/LFM2.5-2.6B-opencode-RL")
model = AutoModelForCausalLM.from_pretrained("FineEnvs/LFM2.5-2.6B-opencode-RL", 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 FineEnvs/LFM2.5-2.6B-opencode-RL 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-RL"
# 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-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

Docker Model Runner
How to use FineEnvs/LFM2.5-2.6B-opencode-RL with Docker Model Runner:
```
docker model run hf.co/FineEnvs/LFM2.5-2.6B-opencode-RL
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LFM2.5-2.6B-opencode-RL

A full fine-tune of LiquidAI/LFM2.5-2.6B for agentic data-analysis tasks, trained with asynchronous GRPO (TRL Async GRPO) using OpenCode. This release is step 1,000 on main, scoring 52.3% pass@1 across four evaluation harnesses.

Article · Collection · Evaluation tasks · Training dashboard

Training and evaluation curves

Training curves use a trailing 50-step mean (at least 10 observations). Evaluation markers show measured checkpoints; hollow markers and dotted segments indicate incomplete coverage. Faint background lines show the full recorded trajectory; colored lines reveal the measured checkpoints. The first frame shows the completed chart before replaying, so previews also contain the full curves. Tool-call savings compare tasks solved by both the base model and checkpoint, with a different matched cohort at each checkpoint. The animation stops at this revision's step 1,000.

Static chart · Plotted data · Interactive article

Training

TRL Async GRPO with correctness plus a tool-call efficiency bonus, initialized from the base model. All training rollouts use OpenCode. Rollouts run through OpenEnv × Harbor in E2B sandboxes.

Setting	Value
Training task pool	1,000 tasks: 400 medium / 600 hard
Checkpoint	1,000 optimizer steps
Learning rate	3e-6
Rollouts per GRPO group / maximum staleness	8 / 4 optimizer steps
Optimizer / precision	paged AdamW 8-bit / bfloat16
Training harnesses	OpenCode
Sampling temperature / top-p	0.8 / 1.0
Per-call output budget, training / evaluation	4,096 / 4,096 tokens

The reward is correctness × (1 + 0.1 × 15 / (15 + tool_calls)), using verified native harness action counts. Incorrect answers receive zero; missing or unverified action counts receive no efficiency bonus. Reported pass@1 measures correctness only. The 1,000-task pool is not a claim that every task contributed an optimizer update.

Evaluation

250 fixed SmolDataEnvs test tasks (33 easy, 118 medium, 99 hard), each evaluated under four harnesses: 1,000 graded task/harness cells. Pass@1 uses the first graded attempt per cell; infrastructure retries do not turn it into pass@k. All cells below are graded.

Harness	Correct / evaluated	Pass@1
OpenCode	145 / 250	58.0%
Claude Code	105 / 250	42.0%
Codex	108 / 250	43.2%
Mini-SWE-Agent	165 / 250	66.0%
Overall	523 / 1,000	52.3%

Harness versions: OpenCode 1.18.31, Claude Code 2.1.270, Codex 0.154.0, Mini-SWE-Agent 2.4.6. Full scores, including difficulty breakdowns, are in eval_results.json.

The main branch contains the final step-1,000 checkpoint (52.3%). The step-900 branch contains the best observed checkpoint (52.4%), used in the article's SFT-versus-RL comparison. Best checkpoint selection used this test set, not a separate validation set.

These are single-run results on a specific task set and harness versions. Harness mix, training exposure and compute differ across runs; the scores do not isolate a causal effect of the harness or objective.

Load the checkpoint

The repository contains full saved model weights and the saved tokenizer/chat template, not a LoRA adapter. Training used Transformers 5.14.1; use a compatible Transformers release.

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "FineEnvs/LFM2.5-2.6B-opencode-RL"
revision = "main"
tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)
model = AutoModelForCausalLM.from_pretrained(
    model_id, revision=revision, dtype=torch.bfloat16, device_map="auto"
)

Reproducing the task scores requires the agent harness and tools described in the article; a plain chat prompt is not the same evaluation.

Related releases

All models, datasets, environments and the article are linked in the multi-harness RL collection.

License and provenance

Derived from LiquidAI/LFM2.5-2.6B under the LFM Open License v1.0. The base model's license is included unchanged in LICENSE. FineEnvs modified the weights by reinforcement learning; this is not an official Liquid AI release. See NOTICE and release_manifest.json for modification notices, the pinned base revision, checkpoint identity and file checksums. Optimizer, scheduler, RNG and trainer state are excluded.

Citation

For the experiment, methodology and interpretation, cite the main article:

@misc{kolavi2026multiharnessrl,
  author = {Adithya S Kolavi},
  title = {The ultimate guide to multi-harness RL},
  year = {2026},
  url = {https://huggingface.co/spaces/AdithyaSK/multi-harness-rl}
}

Downloads last month: 245

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for FineEnvs/LFM2.5-2.6B-opencode-RL

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

LiquidAI/LFM2.5-2.6B

Finetuned

(60)

this model

Quantizations

2 models

Dataset used to train FineEnvs/LFM2.5-2.6B-opencode-RL

Collection including FineEnvs/LFM2.5-2.6B-opencode-RL

SmolDataEnvs Multi-harness RL

Collection

Try the three environments, follow the tutorial, and explore the datasets, models and historical RL/SFT results. • 21 items • Updated 1 day ago • 2

Evaluation results

Pass@1 (%) — Overall on SmolDataEnvs (250 fixed test tasks)
test set self-reported

52.300
Pass@1 (%) — OpenCode on SmolDataEnvs (250 fixed test tasks)
test set self-reported

58.000
Pass@1 (%) — Claude Code on SmolDataEnvs (250 fixed test tasks)
test set self-reported

42.000
Pass@1 (%) — Codex on SmolDataEnvs (250 fixed test tasks)
test set self-reported

43.200
Pass@1 (%) — Mini-SWE-Agent on SmolDataEnvs (250 fixed test tasks)
test set self-reported

66.000