Instructions to use h4bbo/FuseLLM-112M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use h4bbo/FuseLLM-112M with Transformers:

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

pipe = pipeline("text-generation", model="h4bbo/FuseLLM-112M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("h4bbo/FuseLLM-112M")
model = AutoModelForCausalLM.from_pretrained("h4bbo/FuseLLM-112M")
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]:]))

llama-cpp-python

How to use h4bbo/FuseLLM-112M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="h4bbo/FuseLLM-112M",
	filename="FuseLLM-112M.bf16.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 h4bbo/FuseLLM-112M 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 h4bbo/FuseLLM-112M:BF16
# Run inference directly in the terminal:
llama cli -hf h4bbo/FuseLLM-112M:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf h4bbo/FuseLLM-112M:BF16
# Run inference directly in the terminal:
llama cli -hf h4bbo/FuseLLM-112M:BF16

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 h4bbo/FuseLLM-112M:BF16
# Run inference directly in the terminal:
./llama-cli -hf h4bbo/FuseLLM-112M:BF16

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 h4bbo/FuseLLM-112M:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf h4bbo/FuseLLM-112M:BF16

Use Docker

docker model run hf.co/h4bbo/FuseLLM-112M:BF16

LM Studio
Jan

vLLM

How to use h4bbo/FuseLLM-112M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "h4bbo/FuseLLM-112M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "h4bbo/FuseLLM-112M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/h4bbo/FuseLLM-112M:BF16

SGLang

How to use h4bbo/FuseLLM-112M 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 "h4bbo/FuseLLM-112M" \
    --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": "h4bbo/FuseLLM-112M",
		"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 "h4bbo/FuseLLM-112M" \
        --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": "h4bbo/FuseLLM-112M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use h4bbo/FuseLLM-112M with Ollama:
```
ollama run hf.co/h4bbo/FuseLLM-112M:BF16
```

Unsloth Studio

How to use h4bbo/FuseLLM-112M 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 h4bbo/FuseLLM-112M 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 h4bbo/FuseLLM-112M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for h4bbo/FuseLLM-112M to start chatting

How to use h4bbo/FuseLLM-112M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf h4bbo/FuseLLM-112M:BF16

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": "h4bbo/FuseLLM-112M:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use h4bbo/FuseLLM-112M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf h4bbo/FuseLLM-112M:BF16

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 h4bbo/FuseLLM-112M:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use h4bbo/FuseLLM-112M with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf h4bbo/FuseLLM-112M:BF16

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 "h4bbo/FuseLLM-112M:BF16" \
  --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"

Docker Model Runner
How to use h4bbo/FuseLLM-112M with Docker Model Runner:
```
docker model run hf.co/h4bbo/FuseLLM-112M:BF16
```

Lemonade

How to use h4bbo/FuseLLM-112M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull h4bbo/FuseLLM-112M:BF16

Run and chat with the model

lemonade run user.FuseLLM-112M-BF16

List all available models

lemonade list

FuseLLM-112M / README.md

h4bbo

README: document the non-quantized bf16 GGUF variant

9b01f61 verified about 8 hours ago

preview code

Raw

History Blame Contribute Delete

6.45 kB

metadata

library_name: transformers
license: apache-2.0
base_model: h4bbo/FuseLLM-112M-Completion
tags:
  - habbo
  - code
  - chatml
  - sft
language:
  - en
pipeline_tag: text-generation

FuseLLM-112M (Chat)

This is the ChatML chat variant of FuseLLM-112M — a 112M-parameter, from-scratch Qwen3-architecture decoder-only model supervised-fine-tuned (SFT) on on-domain Habbo instruction pairs derived from the Habbo source corpus itself (no external/teacher data).

The base model, h4bbo/FuseLLM-112M-Completion, was trained only on raw Habbo code in completion mode. Its tokenizer already shipped a Qwen3 ChatML template, but the weights had never seen a chat turn, so chat-formatted prompts produced poor, repetitive output. This checkpoint teaches the weights to follow ChatML turns and to emit <|im_end|> at the end of an assistant answer (the turn terminator — conveniently the same token, 151645, the base model was trained to use as a document boundary), which is what stops the runaway repetition.

Use

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "h4bbo/FuseLLM-112M"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto", attn_implementation="sdpa")

messages = [
    {"role": "system", "content": "You are a Habbo Hotel emulator code assistant. Reply with concise, correct code or a brief explanation."},
    {"role": "user", "content": "Implement this Java method:\n```java\npublic static void sendRoomPacket(Session s, int header) { }\n```"},
]
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
ids = tok(text, return_tensors="pt").to(model.device)
out = model.generate(**ids, max_new_tokens=256, eos_token_id=151645, pad_token_id=151643,
                     do_sample=True, temperature=0.7, top_p=0.9, repetition_penalty=1.05)
print(tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True))

It is designed for Habbo-coding instructions (method/class completion, code continuation, doc→code). It is not a general assistant — outside its narrow domain it will produce poor or repetitive output.

Architecture

Qwen3ForCausalLM, hidden 512, 8 layers (full attention), 8 heads / 8 KV heads, intermediate 1408, vocab 151,936, max context 2048, tie_word_embeddings=true. Trained in bf16.

Training data

10,000 ChatML conversations derived deterministically from the Habbo corpus (the same corpus the base was trained on — 84,925 unique files, ~210M est. tokens; top languages Java 26,335 / C# 19,048 / PHP 10,969 / ActionScript 3,801). No external data, no teacher model. Templates:

Method completion — given a method signature with empty body, return the real body.
Code continuation — given a file prefix, return the real suffix.
Doc → method — given a Javadoc/PHPDoc//// summary, return the real method.

Distribution in this build: Java ~4,936 · C# ~3,752 · PHP ~989 · ActionScript ~323. Decompiler noise (JD-Core /* N:M */ line markers and /* Location: … */ footers) is stripped. Secrets are scrubbed to [REDACTED] (currently xX!elgps) before extraction; the training file is verified to contain 0 secret occurrences.

Training config

Full fine-tune (no LoRA — 112M is small enough to train every weight on 24 GB).
TRL SFTTrainer + SFTConfig, messages format auto-detected, ChatML applied by the base tokenizer's chat template. packing=False, max_length=2048 (model's native max position; only 11/10,000 conversations exceed it). Full-sequence causal-LM loss (the Qwen3 chat template has no {% generation %} markers, so assistant_only_loss is unset — at inference we prompt through <|im_start|>assistant\n and stop at <|im_end|>).
bf16, sdpa attention, adamw_torch, cosine schedule, 3 epochs, LR 2e-5, warmup 0.03, effective batch 16 (BS 4 × GA 4), max_grad_norm=1.0, seed 42. 1,875 steps.
generation_config.json is written with eos_token_id=151645 (<|im_end|>), pad_token_id=151643, temperature=0.7, top_p=0.9, repetition_penalty=1.05.

Training result

Loss dropped from ~1.83 (step 10) to ~0.45 by the end of epoch 1 and held in the ~0.4–0.5 range through epochs 2–3. Final: train_loss 0.521, mean_token_accuracy 0.9144, 1,875 steps, ~16.5 min on a single RX 7900 XTX (ROCm). Verified behavior: method-completion and code-continuation prompts produce coherent on-domain Habbo code, close the fenced block, and stop at <|im_end|>; doc→method and free-form explanation prompts tend to ramble (see Limitations).

Redaction

Secrets (currently xX!elgps) are scrubbed to [REDACTED] in all training content before tokenisation. The output training file is checked to contain 0 occurrences. No known credentials enter the weights.

License

Released under Apache-2.0. See the base model h4bbo/FuseLLM-112M-Completion for its license terms.

GGUF

A non-quantized bf16 GGUF — FuseLLM-112M.bf16.gguf (~220 MB, a bit-exact copy of the bf16 safetensors weights, so truly lossless) — is included in this repo for use with llama.cpp / Ollama. The ChatML chat template and the EOS token (<|im_end|>, 151645) are embedded as GGUF metadata, so the model loads in chat mode automatically. No quantized (Q4/Q5/Q8) variant is shipped here.

Example with llama.cpp:

llama-cli -m FuseLLM-112M.bf16.gguf -cnv \
  --temp 0.7 --top-p 0.9 --repeat-penalty 1.05 -n 256 \
  -p "Implement this Java method:\n```java\npublic static void sendRoomPacket(Session s, int h) { }\n```"

Intended use

Domain-specialist code assistant for the Habbo Hotel emulator ecosystem (server/client tooling). Not affiliated with or endorsed by Sulake/Habbo.

Limitations

112M parameters — narrow capacity; expect errors and repetition on long or off-domain prompts.
Trained only on on-domain code-instruction pairs; not a general chat / instruction model.
Doc→method and free-form explanation prompts often ramble past <|im_end|> despite repetition_penalty; keep max_new_tokens modest and prefer the SFT templates (method completion / code continuation).