qwp4w3hyb/Replete-Coder-Qwen2-1.5b-iMat-GGUF

Quant Infos

• quants done with an importance matrix for improved quantization loss
• ggufs & imatrix generated from bf16 for "optimal" accuracy loss
• Wide coverage of different gguf quant types from Q_8_0 down to IQ1_S
• Quantized with llama.cpp commit 4bfe50f741479c1df1c377260c3ff5702586719e (master as of 2024-06-11)
• Imatrix generated with this multi-purpose dataset by bartowski.

  ./imatrix -c 512 -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix
  

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.

• https://tensordock.com

---

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:

• https://huggingface.co/datasets/Replete-AI/OpenHermes-2.5-Uncensored

And the 75% coding specific instruction data below:

• https://huggingface.co/datasets/Replete-AI/code_bagel

These two datasets were combined to create the final dataset for training, which is linked below:

• https://huggingface.co/datasets/Replete-AI/code_bagel_hermes-2.5

---

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:

• https://huggingface.co/teknium
• https://huggingface.co/jondurbin

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!

• https://discord.gg/ZZbnsmVnjD