README.md

Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


tiny_starcoder_py - GGUF
- Model creator: https://huggingface.co./bigcode/
- Original model: https://huggingface.co./bigcode/tiny_starcoder_py/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [tiny_starcoder_py.Q2_K.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q2_K.gguf) | Q2_K | 0.1GB |
| [tiny_starcoder_py.IQ3_XS.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.IQ3_XS.gguf) | IQ3_XS | 0.1GB |
| [tiny_starcoder_py.IQ3_S.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.IQ3_S.gguf) | IQ3_S | 0.1GB |
| [tiny_starcoder_py.Q3_K_S.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q3_K_S.gguf) | Q3_K_S | 0.1GB |
| [tiny_starcoder_py.IQ3_M.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.IQ3_M.gguf) | IQ3_M | 0.11GB |
| [tiny_starcoder_py.Q3_K.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q3_K.gguf) | Q3_K | 0.11GB |
| [tiny_starcoder_py.Q3_K_M.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q3_K_M.gguf) | Q3_K_M | 0.11GB |
| [tiny_starcoder_py.Q3_K_L.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q3_K_L.gguf) | Q3_K_L | 0.12GB |
| [tiny_starcoder_py.IQ4_XS.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.IQ4_XS.gguf) | IQ4_XS | 0.11GB |
| [tiny_starcoder_py.Q4_0.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q4_0.gguf) | Q4_0 | 0.12GB |
| [tiny_starcoder_py.IQ4_NL.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.IQ4_NL.gguf) | IQ4_NL | 0.12GB |
| [tiny_starcoder_py.Q4_K_S.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q4_K_S.gguf) | Q4_K_S | 0.12GB |
| [tiny_starcoder_py.Q4_K.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q4_K.gguf) | Q4_K | 0.12GB |
| [tiny_starcoder_py.Q4_K_M.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q4_K_M.gguf) | Q4_K_M | 0.12GB |
| [tiny_starcoder_py.Q4_1.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q4_1.gguf) | Q4_1 | 0.12GB |
| [tiny_starcoder_py.Q5_0.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q5_0.gguf) | Q5_0 | 0.13GB |
| [tiny_starcoder_py.Q5_K_S.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q5_K_S.gguf) | Q5_K_S | 0.13GB |
| [tiny_starcoder_py.Q5_K.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q5_K.gguf) | Q5_K | 0.14GB |
| [tiny_starcoder_py.Q5_K_M.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q5_K_M.gguf) | Q5_K_M | 0.14GB |
| [tiny_starcoder_py.Q5_1.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q5_1.gguf) | Q5_1 | 0.14GB |
| [tiny_starcoder_py.Q6_K.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q6_K.gguf) | Q6_K | 0.15GB |
| [tiny_starcoder_py.Q8_0.gguf](https://huggingface.co./RichardErkhov/bigcode_-_tiny_starcoder_py-gguf/blob/main/tiny_starcoder_py.Q8_0.gguf) | Q8_0 | 0.18GB |




Original model description:
---
pipeline_tag: text-generation
inference: true
widget:
- text: 'def print_hello_world():'
  example_title: Hello world
  group: Python
license: bigcode-openrail-m
datasets:
- bigcode/the-stack-dedup
metrics:
- code_eval
library_name: transformers
tags:
- code
model-index:
- name: Tiny-StarCoder-Py
  results:
  - task:
      type: text-generation
    dataset:
      type: openai_humaneval
      name: HumanEval
    metrics:
    - name: pass@1
      type: pass@1
      value: 7.84%
      verified: false
---

# TinyStarCoderPy

This is a 164M parameters model with the same architecture as [StarCoder](https://huggingface.co./bigcode/starcoder) (8k context length, MQA & FIM). It was trained on the Python data from [StarCoderData](https://huggingface.co./datasets/bigcode/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](https://huggingface.co./blog/assisted-generation). For pure code completion, we advise using our 15B models [StarCoder]() or [StarCoderBase]().


### Generation
```python
# pip install -q transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

checkpoint = "bigcode/tiny_starcoder_py"
device = "cuda" # for GPU usage or "cpu" for CPU usage

tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)

inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```

### Fill-in-the-middle
Fill-in-the-middle uses special tokens to identify the prefix/middle/suffix part of the input and output:

```python
input_text = "<fim_prefix>def print_one_two_three():\n    print('one')\n    <fim_suffix>\n    print('three')<fim_middle>"
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```

# 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](https://github.com/bigcode-project/Megatron-LM)
- **Neural networks:** [PyTorch](https://github.com/pytorch/pytorch)
- **BP16 if applicable:** [apex](https://github.com/NVIDIA/apex)

# License
The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement [here](https://huggingface.co./spaces/bigcode/bigcode-model-license-agreement).