Model reference · open weights

tiny_starcoder_py

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.

Licence fee required LLMs bigcode 1 variants 221k downloads/mo
Request a licence + hosting quote All served models Not on the shared API today — deployed on request.

About

What tiny_starcoder_py is

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

What it is

Makerbigcode
TypeLanguage models
Parameters (lead)164M
Context8k tokens
Variants1
Runs withtransformers
Released2023-05-15
Popularity221k downloads / month
Likes74
LicenceCommercial licence needed

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.

Variants

Sizes & precisions

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.

VariantParamsPrecisionVRAMFits 16 GBWeights
tiny_starcoder_py164MBF16~0.4 GBWeights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
text-generationHumanEvalpass@17.84%

Using it via the API

Call it like any OpenAI endpoint

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

Languages, data & research

Trained / evaluated on

bigcode/the-stack-dedup

Tags

transformers pytorch safetensors gpt_bigcode text-generation code dataset:bigcode/the-stack-dedup model-index text-generation-inference endpoints_compatible deploy:azure

Licence

Commercial licence needed

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 ↗

Sources

Weights & code

Want tiny_starcoder_py on EU-owned hardware?

Request a licence + hosting quote See what’s served now

Explore

More language models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms