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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("h4bbo/FuseLLM-112M-Completion")
model = AutoModelForCausalLM.from_pretrained("h4bbo/FuseLLM-112M-Completion", 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 h4bbo/FuseLLM-112M-Completion with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "h4bbo/FuseLLM-112M-Completion"
# 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-Completion",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

h4bbo commited on 22 days ago

Commit

87e6a8e

verified ·

1 Parent(s): df99ae9

README: GGUFs no longer shipped; document local conversion to llama.cpp

Browse files

Files changed (1) hide show

README.md +9 -5

README.md CHANGED Viewed

@@ -69,11 +69,17 @@ print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))
 ### llama.cpp (completion mode)
-The repo includes GGUF files (`FuseLLM-112M.fp16.gguf`, `FuseLLM-112M.Q4_K_M.gguf`)
-verified to load and generate in `llama.cpp`.
 ```bash
-# Completion mode — pass the raw code seed, do NOT use chat/conversation mode.
 llama-cli -m FuseLLM-112M.Q4_K_M.gguf -cnv -st --no-jinja \
   -f seed.txt -n 64 --temp 0.0 --repeat-penalty 1.1 --no-display-prompt < /dev/null
 ```
@@ -85,8 +91,6 @@ isn't chat-tuned, so conversation mode is not meaningful for this model).
 - `model.safetensors`, `config.json`, `generation_config.json` — HF model
 - `tokenizer.json`, `tokenizer_config.json`, `chat_template.jinja` — tokenizer + ChatML template
-- `FuseLLM-112M.fp16.gguf` — lossless fp16 GGUF (~220 MB)
-- `FuseLLM-112M.Q4_K_M.gguf` — 4-bit quantized GGUF (~88 MB), the practical llama.cpp file
 ## Notes

 ### llama.cpp (completion mode)
+No GGUF is shipped in this repo. The HF model is **verified** to convert and run in
+`llama.cpp`; generate the GGUF locally:
 ```bash
+# 1) convert HF -> lossless fp16 GGUF
+python convert_hf_to_gguf.py h4bbo/FuseLLM-112M --outtype f16 \
+  --model-name FuseLLM-112M --outfile FuseLLM-112M.fp16.gguf
+# (optional) 4-bit quantize
+llama-quantize FuseLLM-112M.fp16.gguf FuseLLM-112M.Q4_K_M.gguf Q4_K_M
+# 2) completion mode — pass the raw code seed, do NOT use chat/conversation mode.
 llama-cli -m FuseLLM-112M.Q4_K_M.gguf -cnv -st --no-jinja \
   -f seed.txt -n 64 --temp 0.0 --repeat-penalty 1.1 --no-display-prompt < /dev/null
 ```
 - `model.safetensors`, `config.json`, `generation_config.json` — HF model
 - `tokenizer.json`, `tokenizer_config.json`, `chat_template.jinja` — tokenizer + ChatML template
 ## Notes