Instructions to use AKMESSI/lfm2.5-230m-fable-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use AKMESSI/lfm2.5-230m-fable-5 with PEFT:
```
Task type is invalid.
```

How to use AKMESSI/lfm2.5-230m-fable-5 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AKMESSI/lfm2.5-230m-fable-5",
	filename="lfm2.5-230m-fable-5-f16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AKMESSI/lfm2.5-230m-fable-5 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AKMESSI/lfm2.5-230m-fable-5:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AKMESSI/lfm2.5-230m-fable-5:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AKMESSI/lfm2.5-230m-fable-5:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AKMESSI/lfm2.5-230m-fable-5:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf AKMESSI/lfm2.5-230m-fable-5:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AKMESSI/lfm2.5-230m-fable-5:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf AKMESSI/lfm2.5-230m-fable-5:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AKMESSI/lfm2.5-230m-fable-5:Q4_K_M

Use Docker

docker model run hf.co/AKMESSI/lfm2.5-230m-fable-5:Q4_K_M

LM Studio
Jan

vLLM

How to use AKMESSI/lfm2.5-230m-fable-5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AKMESSI/lfm2.5-230m-fable-5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AKMESSI/lfm2.5-230m-fable-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AKMESSI/lfm2.5-230m-fable-5:Q4_K_M

Ollama
How to use AKMESSI/lfm2.5-230m-fable-5 with Ollama:
```
ollama run hf.co/AKMESSI/lfm2.5-230m-fable-5:Q4_K_M
```

Unsloth Studio

How to use AKMESSI/lfm2.5-230m-fable-5 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AKMESSI/lfm2.5-230m-fable-5 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AKMESSI/lfm2.5-230m-fable-5 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AKMESSI/lfm2.5-230m-fable-5 to start chatting

How to use AKMESSI/lfm2.5-230m-fable-5 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AKMESSI/lfm2.5-230m-fable-5:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AKMESSI/lfm2.5-230m-fable-5:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AKMESSI/lfm2.5-230m-fable-5 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AKMESSI/lfm2.5-230m-fable-5:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default AKMESSI/lfm2.5-230m-fable-5:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use AKMESSI/lfm2.5-230m-fable-5 with Docker Model Runner:
```
docker model run hf.co/AKMESSI/lfm2.5-230m-fable-5:Q4_K_M
```

Lemonade

How to use AKMESSI/lfm2.5-230m-fable-5 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AKMESSI/lfm2.5-230m-fable-5:Q4_K_M

Run and chat with the model

lemonade run user.lfm2.5-230m-fable-5-Q4_K_M

List all available models

lemonade list

LFM2.5-230M Fable-5 GGUF

Fine-tuned GGUF release of LiquidAI/LFM2.5-230M on Glint-Research/Fable-5-traces.

Files

lfm2.5-230m-fable-5-f16.gguf — highest quality, largest file
lfm2.5-230m-fable-5-q8_0.gguf — high quality, smaller
lfm2.5-230m-fable-5-q4_k_m.gguf — best default for local inference

Training

Base model: LiquidAI/LFM2.5-230M
Dataset: Glint-Research/Fable-5-traces
File used: fable5_cot_merged.jsonl
Method: PEFT LoRA SFT
Max sequence length: 4096
Epochs: 1
LoRA rank: 32
LoRA alpha: 64
LoRA dropout: 0.05
Precision: FP16 base model, FP32 LoRA trainable weights
Hardware: Google Colab T4
Format: Chat template system/user/assistant, preserving Fable context -> completion

Final training loss samples

step 555: 1.7037
step 560: 1.5968
step 565: 1.6435
step 570: 1.6109
step 575: 1.6589
step 580: 1.6439

Evaluation

We evaluated AKMESSI/lfm2.5-230m-fable-5:F16 against the original base model, LiquidAI/LFM2.5-230M-GGUF:BF16, using local llama.cpp server inference.

These are not official leaderboard submissions. They are lightweight local evaluations intended to compare the fine-tuned model against the base model under the same prompts, decoding settings, and hardware setup.

Summary

The Fable-5 fine-tune improves repository-context code continuation on RepoBench-C-lite Python, while mostly preserving the base model's generic function-calling behavior on BFCL-lite Simple.

Benchmark	Result
RepoBench-C-lite Python	Fine-tuned model outperforms base model
BFCL-lite Simple	Fine-tuned model mostly preserves base function-calling ability
CodeXGLUE Line Completion Python	Neutral / unchanged
CRUXEval-lite	Not a good fit for this trace-style model

RepoBench-C-lite Python

RepoBench-C-style next-line code completion was used to evaluate repository-context code continuation. We sampled 100 examples each from python_if, python_cff, and python_cfr, for 300 total examples.

Model	Examples	Exact Match	Prefix Match	Edit Similarity
`LiquidAI/LFM2.5-230M-GGUF:BF16`	300	10.33%	10.67%	46.85%
`AKMESSI/lfm2.5-230m-fable-5:F16`	300	14.67%	15.33%	50.17%

Compared with the base model, the Fable-5 fine-tune improved:

Exact match by +4.33 percentage points
Prefix match by +4.67 percentage points
Edit similarity by +3.32 points

Breakdown by config:

Config	Base Exact	Fable Exact	Base Edit Sim	Fable Edit Sim
`python_if`	21.00%	27.00%	55.14%	57.31%
`python_cff`	3.00%	5.00%	37.45%	38.10%
`python_cfr`	7.00%	12.00%	47.96%	55.10%

BFCL-lite Simple

We also ran a local BFCL-lite Simple function-calling evaluation over 400 examples as a generic tool-calling control.

Model	Examples	Parse-valid JSON	Function-name Match	Argument Recall	Rough Score
`LiquidAI/LFM2.5-230M-GGUF:BF16`	400	97.75%	97.50%	71.60%	88.44%
`AKMESSI/lfm2.5-230m-fable-5:F16`	400	98.25%	95.00%	67.70%	85.44%

The fine-tuned model preserves most of the base model's generic function-calling behavior, but does not improve BFCL-style API-schema-to-JSON calling. This is expected because the training data consists of coding-agent traces rather than clean function-calling examples.

CodeXGLUE Line Completion Python

We ran a 1,000-example local CodeXGLUE line-completion evaluation as a general code-completion control.

Model	Examples	Exact Match	Prefix Match	Edit Similarity
`LiquidAI/LFM2.5-230M-GGUF:BF16`	1000	23.60%	0.00%	23.60%
`AKMESSI/lfm2.5-230m-fable-5:F16`	1000	23.50%	0.00%	23.50%

This result is effectively neutral. The Fable-5 fine-tune does not materially change general line-completion performance on this setup.

CRUXEval-lite

We also tried a 200-example CRUXEval-lite run for Python execution reasoning.

Model	Task O Accuracy	Task I Accuracy	Overall Accuracy
`LiquidAI/LFM2.5-230M-GGUF:BF16`	8.50%	4.00%	6.25%
`AKMESSI/lfm2.5-230m-fable-5:F16`	0.00%	0.00%	0.00%

This benchmark was not a good fit for the fine-tuned model. The Fable-5 model often entered explanation or trace-style response mode instead of returning only the exact literal Python value expected by CRUXEval.

Interpretation

The Fable-5 fine-tune appears to shift the base model toward coding-agent and repository-context continuation behavior.

It improves RepoBench-C-lite Python next-line completion, while mostly preserving generic function-calling ability on BFCL-lite Simple. The main regression is in exact BFCL-style argument filling, which is not the main target of the Fable-5 trace dataset.

The model is best understood as a tiny coding-agent trace model, not a general-purpose reasoning model or a benchmark-specialized function-calling model.

Evaluation Caveats

These are local lightweight evaluations, not official leaderboard submissions.
Results were produced with llama.cpp server inference.
Scores may vary with prompting, decoding settings, quantization level, and benchmark harness details.
BFCL-lite and RepoBench-C-lite use simplified local scoring scripts rather than official leaderboard infrastructure.
Only the F16 model was benchmarked here; quantized GGUF variants may differ slightly.

Usage

Recommended local file:

lfm2.5-230m-fable-5-q4_k_m.gguf

Caveats

This model is trained on coding-agent trace telemetry. It may emit tool-call-like actions, shell commands, file paths, or long reasoning-style continuations. Review outputs before executing commands.

The dataset contains coding-agent traces and should not be treated as a clean benchmark or a safety-filtered assistant dataset.

License notes

Base model: LiquidAI LFM Open License v1.0
Dataset: AGPL-3.0
This repo preserves upstream license notices. Check compatibility before commercial or closed-source use.

Downloads last month: 238

GGUF

Model size

0.2B params

Architecture

lfm2

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for AKMESSI/lfm2.5-230m-fable-5

Base model

LiquidAI/LFM2.5-230M-Base

Finetuned

LiquidAI/LFM2.5-230M

Adapter

(1)

this model

AKMESSI
/

lfm2.5-230m-fable-5