Instructions to use GautierP/MiniLLM-40M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GautierP/MiniLLM-40M with Transformers:

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

pipe = pipeline("text-generation", model="GautierP/MiniLLM-40M", 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-40M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GautierP/MiniLLM-40M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GautierP/MiniLLM-40M"
# 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-40M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GautierP/MiniLLM-40M

SGLang

How to use GautierP/MiniLLM-40M 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-40M" \
    --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-40M",
		"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-40M" \
        --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-40M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GautierP/MiniLLM-40M with Docker Model Runner:
```
docker model run hf.co/GautierP/MiniLLM-40M
```

GautierP commited on 3 days ago

Commit

b06def8

verified ·

1 Parent(s): eed943d

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +10 -10

README.md CHANGED Viewed

@@ -12,11 +12,11 @@ tags:
 A ~40M parameter conversational assistant with a full training pipeline implemented
 end-to-end in PyTorch — BPE tokenizer, pretraining and supervised fine-tuning, no
-pretrained backbone. Part of 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
@@ -24,7 +24,7 @@ was fine-tuned from ([`base/`](base)).
 | -------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
 | Parameters     | 42,476,032 (input embedding shared with the output head)                                                                                 |
 | Architecture   | Transformer decoder: RMSNorm, RoPE, causal attention, SwiGLU                                                                              |
-| Context length | 1,024 tokens — twice the 512 of the older 34M/70M/150M family runs                                                                        |
 | Vocabulary     | 32,768 (BPE)                                                                                                                              |
 | Pretraining    | ~4.60B tokens (FineWeb-Edu + Wikipedia), 35,096 steps (~115 tokens/param) — base val loss 3.202                                           |
 | Fine-tuning    | 2 epochs of SFT on Dolly-15k, No Robots, OpenAssistant oasst2, alpaca-cleaned and identity/small-talk examples — val loss 3.058             |
@@ -32,18 +32,18 @@ was fine-tuned from ([`base/`](base)).
 ## Base model
-The [`base/`](base) subfolder contains the pretrained checkpoint
 (`mini-llm-base-40M-35096steps.pt`) before SFT: 42,476,032 parameters, 32,768-token
 BPE vocabulary, ~4.60B tokens (FineWeb-Edu + Wikipedia), 35,096 steps — base val loss
-3.202. 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-40M"
-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)

 A ~40M parameter conversational assistant with a full training pipeline implemented
 end-to-end in PyTorch — BPE tokenizer, pretraining and supervised fine-tuning, no
+pretrained backbone. Code, training pipeline and documentation:
+[github.com/Mini-llm-lab/Mini-LLM](https://github.com/Mini-llm-lab/Mini-LLM).
+This repository hosts the SFT assistant. The base model it was fine-tuned from is
+published separately: [GautierP/MiniLLM-40M-base](https://huggingface.co/GautierP/MiniLLM-40M-base).
 ## Model details
 | -------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
 | Parameters     | 42,476,032 (input embedding shared with the output head)                                                                                 |
 | Architecture   | Transformer decoder: RMSNorm, RoPE, causal attention, SwiGLU                                                                              |
+| Context length | 1,024 tokens — twice the 512 of the earlier 1.0-generation runs                                                                        |
 | Vocabulary     | 32,768 (BPE)                                                                                                                              |
 | Pretraining    | ~4.60B tokens (FineWeb-Edu + Wikipedia), 35,096 steps (~115 tokens/param) — base val loss 3.202                                           |
 | Fine-tuning    | 2 epochs of SFT on Dolly-15k, No Robots, OpenAssistant oasst2, alpaca-cleaned and identity/small-talk examples — val loss 3.058             |
 ## Base model
+The base repository contains the pretrained checkpoint
 (`mini-llm-base-40M-35096steps.pt`) before SFT: 42,476,032 parameters, 32,768-token
 BPE vocabulary, ~4.60B tokens (FineWeb-Edu + Wikipedia), 35,096 steps — base val loss
+3.202. It is a raw completion model, not an assistant: the base ships without a chat
 template and without the assistant's sampling defaults.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+repo = "GautierP/MiniLLM-40M-base"
+tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(repo, 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)