arpieb/peft-lora-starcoderbase-7b-personal-copilot-elixir

Model Card for Model ID

First pass at finetuning bigcode/starcoderbase-7b on the Elixir language subset of bigcode/the-stack-dedup

Model Details

Model Description

• —Developed by: [More Information Needed]
• —Shared by [optional]: [More Information Needed]
• —Model type: [More Information Needed]
• —Language(s) (NLP): [More Information Needed]
• —License: [More Information Needed]
• —Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• —Repository: arpieb/peft-lora-starcoderbase-7b-personal-copilot-elixir

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

bigcode/the-stack-dedup

Training Procedure

Based on the finetuning workflow detailed in Personal Copilot: Train Your Own Coding Assistant, specifically the training code found under personal_copilot/training in the repo pacman100/DHS-LLM-Workshop.

Script used to train the model:

python train.py \
    --model_path "bigcode/starcoderbase-7b" \
    --dataset_name "bigcode/the-stack-dedup" \
    --subset "data/elixir" \
    --data_column "content" \
    --split "train" \
    --seq_length 2048 \
    --max_steps 2000 \
    --batch_size 4 \
    --gradient_accumulation_steps 4 \
    --learning_rate 5e-4 \
    --lr_scheduler_type "cosine" \
    --weight_decay 0.01 \
    --num_warmup_steps 30 \
    --eval_freq 100 \
    --save_freq 100 \
    --log_freq 25 \
    --num_workers 4 \
    --bf16 \
    --no_fp16 \
    --output_dir "peft-lora-starcoderbase-7b-personal-copilot-rtx4090-elixir" \
    --push_to_hub "false" \
    --fim_rate 0.5 \
    --fim_spm_rate 0.5 \
    --use_flash_attn \
    --use_peft_lora \
    --lora_r 32 \
    --lora_alpha 64 \
    --lora_dropout 0.0 \
    --lora_target_modules "c_proj,c_attn,q_attn,c_fc,c_proj" \
    --use_4bit_qunatization \
    --use_nested_quant \
    --bnb_4bit_compute_dtype "bfloat16"

Preprocessing

N/A

Training Hyperparameters

• —Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

Testing Data, Factors & Metrics

Testing Data

<!-- This should link to a Data Card if possible. -->

[More Information Needed]

Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

NOTE the RTX-4090 is not available in the above estimator; will update once there is data available.

• —Hardware Type: NVIDIA GeForce RTX 4090
• —Hours used: ~9h (actual run timing lost :facepalm:)
• —Cloud Provider: Local rig
• —Compute Region: N/A
• —Carbon Emitted: N/A

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

Hardware

Local DL rig with the following configuration:

• —NVIDIA GeForce RTX 4090
• —Intel(R) Core(TM) i7-7800X CPU @ 3.50GHz
• —128GB RAM

Software

[More Information Needed]

Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Training procedure

The following bitsandbytes quantization config was used during training:

• —quant_method: bitsandbytes
• —loadin8bit: False
• —loadin4bit: True
• —llmint8threshold: 6.0
• —llmint8skip_modules: None
• —llmint8enablefp32cpu_offload: False
• —llmint8hasfp16weight: False
• —bnb4bitquant_type: nf4
• —bnb4bitusedoublequant: True
• —bnb4bitcompute_dtype: bfloat16

Framework versions

• —PEFT 0.6.2.dev0