metadata

datasets:
  - bigcode/starcoderdata
language:
  - code
tags:
  - causal-lm
license: cc-by-sa-4.0

`StableCode-Completion-Alpha-3B`

Model Description

StableCode-Completion-Alpha-3B is a 3 billion parameter decoder-only code completion model pre-trained on diverse set of programming languages that topped the stackoverflow developer survey.

Usage

The model is intended to do single/multiline code completion from a long context window upto 4k tokens. Get started generating code with StableCode-Completion-Alpha-3B-4k by using the following code snippet:

from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablecode-completion-alpha-3b-4k")
model = AutoModelForCausalLM.from_pretrained(
  "stabilityai/stablecode-completion-alpha-3b-4k",
  trust_remote_code=True,
  torch_dtype="auto",
)
model.cuda()
inputs = tokenizer("import torch\nimport torch.nn as nn", return_tensors="pt").to("cuda")
tokens = model.generate(
  **inputs,
  max_new_tokens=48,
  temperature=0.2,
  do_sample=True,
)
print(tokenizer.decode(tokens[0], skip_special_tokens=True))

Model Details

Developed by: Stability AI
Model type: StableCode-Completion-Alpha-3B-4k models are auto-regressive language models based on the transformer decoder architecture.
Language(s): Code
Library: GPT-NeoX
License: Model checkpoints are licensed under the Creative Commons license (CC BY-SA-4.0). Under this license, you must give credit to Stability AI, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the Stability AI endorses you or your use.
Contact: For questions and comments about the model, please email lm@stability.ai

Model Architecture

Parameters	Hidden Size	Layers	Heads	Sequence Length
2,796,431,360	2560	32	32	4096

Decoder Layer: Parallel Attention and MLP residuals with a single input LayerNorm (Wang & Komatsuzaki, 2021)
Position Embeddings: Rotary Position Embeddings (Su et al., 2021)
Bias: LayerNorm bias terms only

Training

StableCode-Completion-Alpha-3B-4k is pre-trained at a context length of 4096 for 300 billion tokens on the bigcode/starcoder-data.

Training Dataset

The first pre-training stage relies on 300B tokens sourced from various top programming languages occuring in the stackoverflow developer survey present in the starcoder-data dataset.

Training Procedure

The model is pre-trained on the dataset mixes mentioned above in mixed-precision BF16), optimized with AdamW, and trained using the StarCoder tokenizer with a vocabulary size of 49k.

Software: We use a fork of gpt-neox (EleutherAI, 2021) and train under 2D parallelism (Data and Tensor Parallel) with ZeRO-1 (Rajbhandari et al., 2019) and rely on flash-attention as well as rotary embedding kernels from FlashAttention-2 (Dao et al., 2023)

stabilityai
/

stablecode-completion-alpha-3b-4k