Instructions to use GautierP/MiniLLM-150M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GautierP/MiniLLM-150M with Transformers:

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

pipe = pipeline("text-generation", model="GautierP/MiniLLM-150M", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("GautierP/MiniLLM-150M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GautierP/MiniLLM-150M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GautierP/MiniLLM-150M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GautierP/MiniLLM-150M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GautierP/MiniLLM-150M

SGLang

How to use GautierP/MiniLLM-150M 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 "GautierP/MiniLLM-150M" \
    --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": "GautierP/MiniLLM-150M",
		"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 "GautierP/MiniLLM-150M" \
        --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": "GautierP/MiniLLM-150M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GautierP/MiniLLM-150M with Docker Model Runner:
```
docker model run hf.co/GautierP/MiniLLM-150M
```

GautierP commited on 8 days ago

Commit

d36bb01

verified ·

1 Parent(s): a43ed10

docs: document the base model in base/

Browse files

Files changed (1) hide show

README.md +23 -2

README.md CHANGED Viewed

@@ -15,8 +15,8 @@ PyTorch — no pretrained weights, no distillation. Tokenizer, pretraining and
 supervised fine-tuning all belong to the
 [Mini-LLM](https://github.com/Mini-llm-lab/Mini-LLM) project.
-This repository is the SFT assistant derived from the `mini-llm-base-150M-34332steps.pt`
-base checkpoint (not published).
 ## Model details
@@ -29,6 +29,26 @@ base checkpoint (not published).
 | Pretraining    | ~4.50B tokens (FineWeb-Edu + Wikipedia), 34,332 steps — base val loss 2.941 (32k vocabulary)                                    |
 | Fine-tuning    | 2 epochs of SFT on Dolly-15k, No Robots, OpenAssistant oasst2, alpaca-cleaned and identity/small-talk examples — val loss 2.780 |
 ## Usage
 ```python
@@ -67,4 +87,5 @@ lookup or any production task. English only.
 ## Links
 - Code, training pipeline and full documentation: https://github.com/Mini-llm-lab/Mini-LLM

 supervised fine-tuning all belong to the
 [Mini-LLM](https://github.com/Mini-llm-lab/Mini-LLM) project.
+This repository hosts both the SFT assistant (repository root) and the base model it
+was fine-tuned from ([`base/`](base)).
 ## Model details
 | Pretraining    | ~4.50B tokens (FineWeb-Edu + Wikipedia), 34,332 steps — base val loss 2.941 (32k vocabulary)                                    |
 | Fine-tuning    | 2 epochs of SFT on Dolly-15k, No Robots, OpenAssistant oasst2, alpaca-cleaned and identity/small-talk examples — val loss 2.780 |
+## Base model
+The [`base/`](base) subfolder contains the pretrained checkpoint
+(`mini-llm-base-150M-34332steps.pt`) before SFT: 152,596,224 parameters, 32,768-token
+BPE vocabulary, ~4.50B tokens (FineWeb-Edu + Wikipedia), 34,332 steps — base val loss
+2.941. It is a raw completion model, not an assistant: `base/` ships without a chat
+template and without the assistant's sampling defaults.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+repo = "GautierP/MiniLLM-150M"
+tok = AutoTokenizer.from_pretrained(repo, subfolder="base", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(repo, subfolder="base", trust_remote_code=True)
+inputs = tok("The capital of France is", return_tensors="pt")
+out = model.generate(**inputs, max_new_tokens=64, do_sample=True, temperature=0.8, top_k=50)
+print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+```
 ## Usage
 ```python
 ## Links
+- Base model weights: https://huggingface.co/GautierP/MiniLLM-150M/tree/main/base
 - Code, training pipeline and full documentation: https://github.com/Mini-llm-lab/Mini-LLM