Instructions to use Compactbot/tinystories-40m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Compactbot/tinystories-40m with Transformers:

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

pipe = pipeline("text-generation", model="Compactbot/tinystories-40m", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("Compactbot/tinystories-40m", trust_remote_code=True)
model = AutoModel.from_pretrained("Compactbot/tinystories-40m", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Compactbot/tinystories-40m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Compactbot/tinystories-40m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Compactbot/tinystories-40m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Compactbot/tinystories-40m

SGLang

How to use Compactbot/tinystories-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 "Compactbot/tinystories-40m" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Compactbot/tinystories-40m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Compactbot/tinystories-40m" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Compactbot/tinystories-40m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Compactbot/tinystories-40m with Docker Model Runner:
```
docker model run hf.co/Compactbot/tinystories-40m
```

fix(generate): only feed the new token to forward() after the first step The loop was passing the full growing input_ids to forward() every step while also maintaining a KV cache, so at step i it reprocessed all i tokens on top of a cache that already held them — O(n^2) memory in the number of generated tokens. Short generations that hit EOS early survived; anything longer OOM'd (25.8 GiB allocated for a 158 MB model). Pass only ids[:, -1:] after the first step; the RoPE positions already account for the cache length via `start`. Verified: model.generate() now runs to full length (120+ tokens) with no OOM.

by Compactbot - opened about 16 hours ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

Files changed (1) hide show

modeling_tinystories.py +2 -1

modeling_tinystories.py CHANGED Viewed

@@ -167,7 +167,8 @@ class TinyStoriesGPT(PreTrainedModel):
         ids = input_ids
         past = None
         for _ in range(max_new_tokens):
-            out = self(ids, past_key_values=past, use_cache=True)
             past = out.past_key_values
             logits = out.logits[:, -1, :]
             if temperature and temperature != 1.0:

         ids = input_ids
         past = None
         for _ in range(max_new_tokens):
+            inp = ids if past is None else ids[:, -1:]
+            out = self(inp, past_key_values=past, use_cache=True)
             past = out.past_key_values
             logits = out.logits[:, -1, :]
             if temperature and temperature != 1.0: