Instructions to use saidutta69/LFM3-1.7B-Claude-Fable5.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saidutta69/LFM3-1.7B-Claude-Fable5.1 with Transformers:

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

pipe = pipeline("text-generation", model="saidutta69/LFM3-1.7B-Claude-Fable5.1", trust_remote_code=True)
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("saidutta69/LFM3-1.7B-Claude-Fable5.1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("saidutta69/LFM3-1.7B-Claude-Fable5.1", trust_remote_code=True, 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]:]))

PEFT
How to use saidutta69/LFM3-1.7B-Claude-Fable5.1 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use saidutta69/LFM3-1.7B-Claude-Fable5.1 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 saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M

Use Docker

docker model run hf.co/saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use saidutta69/LFM3-1.7B-Claude-Fable5.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saidutta69/LFM3-1.7B-Claude-Fable5.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saidutta69/LFM3-1.7B-Claude-Fable5.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M

SGLang

How to use saidutta69/LFM3-1.7B-Claude-Fable5.1 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 "saidutta69/LFM3-1.7B-Claude-Fable5.1" \
    --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": "saidutta69/LFM3-1.7B-Claude-Fable5.1",
		"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 "saidutta69/LFM3-1.7B-Claude-Fable5.1" \
        --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": "saidutta69/LFM3-1.7B-Claude-Fable5.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use saidutta69/LFM3-1.7B-Claude-Fable5.1 with Ollama:
```
ollama run hf.co/saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M
```
Unsloth Desktop

How to use saidutta69/LFM3-1.7B-Claude-Fable5.1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use saidutta69/LFM3-1.7B-Claude-Fable5.1 with Docker Model Runner:
```
docker model run hf.co/saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M
```

Lemonade

How to use saidutta69/LFM3-1.7B-Claude-Fable5.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M

Run and chat with the model

lemonade run user.LFM3-1.7B-Claude-Fable5.1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use saidutta69/LFM3-1.7B-Claude-Fable5.1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/LFM3-1.7B-Claude-Fable5.1: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 saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use saidutta69/LFM3-1.7B-Claude-Fable5.1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LFM3-1.7B-Claude-Fable5.1

A tool-calling fine-tune of LiquidAI/LFM3-1.7B on the claude_code split of saidutta69/fable-5.1-premium-v2.

It teaches the 1.7B LFM3 hybrid to emit Claude Code tool calls - Bash, Read, Write, Edit, Glob, Grep, WebFetch, WebSearch, TodoWrite, TaskCreate, TaskUpdate, TaskOutput, ToolSearch - with valid tool names and typed arguments. The base model is already agentic; this checkpoint is tuned for schema fidelity inside a Claude-Code-style harness.

Who this is for

Running a Claude-Code-style tool protocol on a local 1.7B model - Q4_K_M is 1.10 GB.
Harnesses where an invalid tool name breaks the loop. The base model invents a tool on ~23% of parsed calls; this checkpoint does not.
Not a general-purpose LFM3 upgrade. Free-form text modelling shifted; use the base for general writing.

Why this fine-tune

The dataset's fable_code split is unusable for argument fidelity: 203,750 of 203,794 tool calls carry whole-value placeholders such as <file_path> and <bash_command> (44 clean calls total). The claude_code split carries real values (tasks/SEED_SPEC.md, real shell commands), so training used that split.

The schemas in this dataset are reconstructed, not original Claude Code schemas. They are close enough for the protocol, but do not assume byte-identical parity with a live Claude Code install.

Training


Method	bf16 LoRA, no quantization
LoRA	r=32, alpha=64, dropout 0.05
Targets	`q/k/v/o_proj`, conv `in_proj`/`out_proj`, MLP `w1/w2/w3`
Data	48,467 segments from 4,132 traces, 4,096-token windows
Masking	assistant turn only; tool outputs and user/system tokens are `-100`
Schedule	3,030 steps, effective batch 16, LR 1e-4 cosine, 3% warmup
Hardware	1x RTX PRO 6000 Blackwell (102 GB), 6 h 39 m, peak 31 GB
Final loss	0.200

Samples are one assistant action each, with the conversation window trimmed to 4,096 tokens. The tool schemas are injected through LFM3's own chat template, with enable_thinking=False.

Performance

Same harness for both models: 100 held-out claude_code test samples, greedy decoding, 2,048-token budget.

Metric	Base LFM3-1.7B	This model
Held-out supervised loss	1.731	0.233
Starts a tool call	97%	100%
Parseable call	97%	95%
Tool name valid (per sample)	75%	95%
Tool name valid (of parsed)	77.3%	100%
Required args present (of parsed)	96.9%	100%
Argument types correct (of parsed)	100%	100%
Chat/math sample	11/11 factual	11/11 factual
Wikitext perplexity	17.35	23.32

The 5% parse gap is truncated output at the 2,048-token cap: this model writes fuller Write and Bash bodies, so some calls do not close inside the budget. Every parsed call has a valid name, required arguments, and correct types. Raise the budget or stream the call and the gap closes.

The perplexity rise is real: this is a specialist, not a general upgrade. The chat/math gate is unchanged (11/11 factual, 20/20 answered).

Files

File	Size	Notes
`model.safetensors`	3.46 GB	bf16 reference, use with `trust_remote_code=True`
`LFM3-1.7B-Claude-Fable5.1-f16.gguf`	3.47 GB	GGUF reference
`LFM3-1.7B-Claude-Fable5.1-Q8_0.gguf`	1.85 GB	near-lossless
`LFM3-1.7B-Claude-Fable5.1-Q6_K.gguf`	1.43 GB	high quality
`LFM3-1.7B-Claude-Fable5.1-Q5_K_M.gguf`	1.26 GB	balanced
`LFM3-1.7B-Claude-Fable5.1-Q4_K_M.gguf`	1.10 GB	default for local use

All five GGUFs report arch=lfm3, 287 tensors, and context_length=262144, and were load-tested with llama.cpp built from master (LFM3 support is recent - update llama.cpp before using these files).

Quickstart

llama.cpp

llama serve -hf saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M --jinja \
  --chat-template-kwargs '{"enable_thinking":false}'

Transformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

repo = "saidutta69/LFM3-1.7B-Claude-Fable5.1"
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo, dtype=torch.bfloat16, device_map="auto", trust_remote_code=True
)

messages = [{"role": "user", "content": "List the files in tasks/"}]
tools = [{
    "type": "function",
    "function": {
        "name": "Bash",
        "description": "Run a shell command.",
        "parameters": {
            "type": "object",
            "properties": {"command": {"type": "string"}},
            "required": ["command"],
        },
    },
}]

prompt = tok.apply_chat_template(
    messages, tools=tools, tokenize=False,
    add_generation_prompt=True, enable_thinking=False,
)
inputs = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512, do_sample=False)
print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False))

Tool calls render as:

<tool_call>
<function=Bash>
<parameter=command>
ls tasks/
</parameter>
</function>
</tool_call>

FAQ

What is LFM3-1.7B-Claude-Fable5.1?

It is a bf16 LoRA fine-tune of LiquidAI/LFM3-1.7B, merged into the base and trained on the claude_code configuration of saidutta69/fable-5.1-premium-v2. The goal is strict Claude-Code-style tool calling on a 1.7B model, not a new general model.

How does it compare to the base LFM3-1.7B?

On 100 held-out samples, tool-name validity rises from 77.3% to 100% of parsed calls, required arguments from 96.9% to 100%, and held-out loss falls from 1.731 to 0.233. It starts a call on 100% of samples vs 97% for the base. Raw parse is 95% vs 97% because this model writes longer tool bodies that truncate at the 2,048-token evaluation cap. Chat/math accuracy is unchanged at 11/11.

How do I run LFM3-1.7B-Claude-Fable5.1 locally?

Use llama.cpp from master (LFM3 support is recent):

llama serve -hf saidutta69/LFM3-1.7B-Claude-Fable5.1:Q4_K_M --jinja \
  --chat-template-kwargs '{"enable_thinking":false}'

Q4_K_M is 1.10 GB. For the reference weights use :F16 or the bf16 safetensors with trust_remote_code=True.

Responsible use

Tool calls execute real commands and write real files. Run this model in a sandbox, review Bash commands before execution, and never expose it to untrusted input without a permission layer.

Limitations, stated plainly:

Evaluation is in-distribution: 100 held-out samples from the same dataset, greedy decoding, 2,048-token budget. No independent agent benchmark or multi-turn end-to-end task suite was run.
The tool schemas are reconstructed from the dataset, not copied from Claude Code.
4,096-token training window.
General free-form text modelling regressed (wikitext perplexity 17.35 -> 23.32).

Made with ❤️ by RACER IS OP (saidutta69)

License

LFM Open License v1.0 - license: other, license_name: lfm1.0.

This is not Apache-2.0. The full text is in LICENSE and the terms are Liquid AI's; review them before commercial use. The base model is LiquidAI/LFM3-1.7B, and this derivative keeps its license.

LiquidAI/LFM3-1.7B - the base model this checkpoint derives from
saidutta69/fable-5.1-premium-v2 - the training data (claude_code configuration)

Downloads last month: 2,240

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for saidutta69/LFM3-1.7B-Claude-Fable5.1

Base model

LiquidAI/LFM3-1.7B-Base

Finetuned

LiquidAI/LFM3-1.7B

Adapter

(19)

this model

Merges

1 model

Quantizations

1 model

saidutta69
/

LFM3-1.7B-Claude-Fable5.1

LFM3-1.7B-Claude-Fable5.1

Who this is for

Why this fine-tune

Training

Performance

Files

Quickstart

llama.cpp

Transformers

FAQ

What is LFM3-1.7B-Claude-Fable5.1?

How does it compare to the base LFM3-1.7B?

How do I run LFM3-1.7B-Claude-Fable5.1 locally?

Responsible use

License

Related

Model tree for saidutta69/LFM3-1.7B-Claude-Fable5.1

Dataset used to train saidutta69/LFM3-1.7B-Claude-Fable5.1