Model reference · open weights
tiny_starcoder_py is an open-weight language model from bigcode, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
TinyStarCoderPy This is a 164M parameters model with the same architecture as StarCoder (8k context length, MQA & FIM). It was trained on the Python data from StarCoderData for ~6 epochs which amounts to 100B tokens. Use Intended use The model was trained on GitHub code, to assist with some tasks like Assisted Generation. For pure code completion, we advise using our 15B models [StarCoder]() or [StarCoderBase](). Generation Fill-in-the-middle Fill-in-the-middle uses special tokens to identify the prefix/middle/suffix part of the input and output: Training Model - Architecture: GPT-2 model with multi-query attention and Fill-in-the-Middle objective - Pretraining steps: 50k - Pretraining tokens: 100 billion - Precision: bfloat16 Hardware - GPUs: 32 Tesla A100 - Training time: 18 hours Software - Orchestration: Megatron-LM - Neural networks: PyTorch - BP16 if applicable: apex License The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement here.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | bigcode |
|---|---|
| Type | Language models |
| Parameters (lead) | 164M |
| Context | 8k tokens |
| Variants | 1 |
| Runs with | transformers |
| Released | 2023-05-15 |
| Popularity | 221k downloads / month |
| Likes | 74 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| tiny_starcoder_py | 164M | BF16 | ~0.4 GB | ✓ | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| text-generation | HumanEval | pass@1 | 7.84% |
Using it via the API
Once AxForge deploys tiny-starcoder-py for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (tiny-starcoder-py below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tiny-starcoder-py","messages":[{"role":"user","content":"Hello"}]}'
Details
Trained / evaluated on
Tags
Licence
The weights are open but bigcode-openrail-m needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗