Code-290k-13B/README.md

language, license, tags, datasets, model-index

language	license	tags	datasets	model-index
en	cc-by-nc-nd-4.0	code	ajibawa-2023/Code-290k-ShareGPT	name results Code-290k-13B task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 56.06 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 81.55 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 51.99 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 37.65 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 72.69 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 17.82 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Code-290k-13B Open LLM Leaderboard

Code-290k-13B

Large Language Models (LLMs) are good with code generations. Sometimes they do make mistakes in code generation. How about if they can give detailed explanation along with the code. This is what I have tried over here. The base Llama-2 model was used for training purpose. It is trained on around 290000 set of codes. Each set having 2 conversations. Along with Python, Java, JavaScript, GO, C++, Rust, Ruby, Sql, MySql, R, Julia, Haskell, etc. code with detailed explanation is used for training purpose. It is built upon using my existing Datasets Python-Code-23k-ShareGPT and Code-74k-ShareGPT . This conversation is in Vicuna/ShareGPT format. Each set, along with code, has detailed explanation.

I have released the new data Code-290k-ShareGPT on which this Model is trained.

Training:

Entire dataset was trained on 4 x A100 80GB. For 3 epoch, training took 165 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-2 by Meta.

This is a full fine tuned model. Links for quantized models are given below.

GPTQ, GGUF, AWQ & Exllama

GPTQ: Link

GGUF: Link

AWQ: Link

Exllama v2: Link

Extremely thankful to TheBloke and Bartowski for making Quantized versions of the model.

Example Prompt:

This is a conversation with your helpful AI assistant. AI assistant can generate Code in various Programming Languages along with necessary explanation.

Context
You are a helpful AI assistant.

USER: <prompt>
ASSISTANT:

You can modify above Prompt as per your requirement. I have used ShareGPT/Vicuna format v1.1 .

I want to say special Thanks to the Open Source community for helping & guiding me to better understand the AI/Model development.

Thank you for your love & support.

Example Output

Will update soon.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	52.96
AI2 Reasoning Challenge (25-Shot)	56.06
HellaSwag (10-Shot)	81.55
MMLU (5-Shot)	51.99
TruthfulQA (0-shot)	37.65
Winogrande (5-shot)	72.69
GSM8k (5-shot)	17.82