Replete-Coder-Qwen2-1.5b-exl2
Model: Replete-Coder-Qwen2-1.5b
Model creator: Rombodawg
Based on original model: Qwen2-1.5B
Created by: Qwen
Quants
4bpw h6 (main)
4.25bpw h6
4.65bpw h6
5bpw h6
6bpw h6
8bpw h8
Quantization notes
Made with Exllamav2 0.1.6 with the default dataset.
Original model card
Replete-Coder-Qwen2-1.5b
Finetuned by: Rombodawg
More than just a coding model!
Although Replete-Coder has amazing coding capabilities, its trained on vaste amount of non-coding data, fully cleaned and uncensored. Dont just use it for coding, use it for all your needs! We are truly trying to make the GPT killer!
Thank you to TensorDock for sponsoring Replete-Coder-llama3-8b and Replete-Coder-Qwen2-1.5b you can check out their website for cloud compute rental bellow.
Replete-Coder-Qwen2-1.5b is a general purpose model that is specially trained in coding in over 100 coding languages. The data used to train the model contains 25% non-code instruction data and 75% coding instruction data totaling up to 3.9 million lines, roughly 1 billion tokens, or 7.27gb of instruct data. The data used to train this model was 100% uncensored, then fully deduplicated, before training happened.
The Replete-Coder models (including Replete-Coder-llama3-8b and Replete-Coder-Qwen2-1.5b) feature the following:
- Advanced coding capabilities in over 100 coding languages
- Advanced code translation (between languages)
- Security and vulnerability prevention related coding capabilities
- General purpose use
- Uncensored use
- Function calling
- Advanced math use
- Use on low end (8b) and mobile (1.5b) platforms
Notice: Replete-Coder series of models are fine-tuned on a context window of 8192 tokens. Performance past this context window is not guaranteed.
You can find the 25% non-coding instruction below:
And the 75% coding specific instruction data below:
These two datasets were combined to create the final dataset for training, which is linked below:
Prompt Template: ChatML
<|im_start|>system
{}<|im_end|>
<|im_start|>user
{}<|im_end|>
<|im_start|>assistant
{}
Note: The system prompt varies in training data, but the most commonly used one is:
Below is an instruction that describes a task, Write a response that appropriately completes the request.
End token:
<|endoftext|>
Thank you to the community for your contributions to the Replete-AI/code_bagel_hermes-2.5 dataset. Without the participation of so many members making their datasets free and open source for any to use, this amazing AI model wouldn't be possible.
Extra special thanks to Teknium for the Open-Hermes-2.5 dataset and jondurbin for the bagel dataset and the naming idea for the code_bagel series of datasets. You can find both of their huggingface accounts linked below:
Another special thanks to unsloth for being the main method of training for Replete-Coder. Bellow you can find their github, as well as the special Replete-Ai secret sause (Unsloth + Qlora + Galore) colab code document that was used to train this model.
- https://github.com/unslothai/unsloth
- https://colab.research.google.com/drive/1eXGqy5M--0yW4u0uRnmNgBka-tDk2Li0?usp=sharing
Join the Replete-Ai discord! We are a great and Loving community!
- Downloads last month
- 7
Model tree for cgus/Replete-Coder-Qwen2-1.5b-exl2
Datasets used to train cgus/Replete-Coder-Qwen2-1.5b-exl2
Evaluation results
- pass@1 on HumanEvalself-reported0.354
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboardnull
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboardnull
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboardnull
- multiple_choice_accuracy on TruthfulQA (0-shot)validation set Open LLM Leaderboardnull
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboardnull
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboardnull