Downloads · 30 days
145
7% of all-time downloads
ajibawa-2023_-_Code-Llama-3-8B-gguf
RichardErkhov/ajibawa-2023_-_Code-Llama-3-8B-gguf
ajibawa-2023_-_Code-Llama-3-8B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
2K
Public
Repo size
92.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf108 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 20, 2024
- Updated
- Aug 20, 2024
- SHA
- 60b7d5a4
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Code-Llama-3-8B - GGUF
- Model creator: https://huggingface.co/ajibawa-2023/
- Original model: https://huggingface.co/ajibawa-2023/Code-Llama-3-8B/
| Name | Quant method | Size |
|---|---|---|
| Code-Llama-3-8B.Q2_K.gguf | Q2_K | 2.96GB |
| Code-Llama-3-8B.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| Code-Llama-3-8B.IQ3_S.gguf | IQ3_S | 3.43GB |
| Code-Llama-3-8B.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| Code-Llama-3-8B.IQ3_M.gguf | IQ3_M | 3.52GB |
| Code-Llama-3-8B.Q3_K.gguf | Q3_K | 3.74GB |
| Code-Llama-3-8B.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| Code-Llama-3-8B.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| Code-Llama-3-8B.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| Code-Llama-3-8B.Q4_0.gguf | Q4_0 | 4.34GB |
| Code-Llama-3-8B.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| Code-Llama-3-8B.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| Code-Llama-3-8B.Q4_K.gguf | Q4_K | 4.58GB |
| Code-Llama-3-8B.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| Code-Llama-3-8B.Q4_1.gguf | Q4_1 | 4.78GB |
| Code-Llama-3-8B.Q5_0.gguf | Q5_0 | 5.21GB |
| Code-Llama-3-8B.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| Code-Llama-3-8B.Q5_K.gguf | Q5_K | 5.34GB |
| Code-Llama-3-8B.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| Code-Llama-3-8B.Q5_1.gguf | Q5_1 | 5.65GB |
| Code-Llama-3-8B.Q6_K.gguf | Q6_K | 6.14GB |
| Code-Llama-3-8B.Q8_0.gguf | Q8_0 | 7.95GB |
Original model description:
license: llama3 datasets:
- ajibawa-2023/Code-290k-ShareGPT
- m-a-p/CodeFeedback-Filtered-Instruction
- m-a-p/Code-Feedback
- microsoft/orca-math-word-problems-200k language:
- en tags:
- code
- Python
- Cpp
- PHP
- JS
- Java
- Rust
- Ruby
- SQL
- MySql
- R
- Julia
Code-Llama-3-8B
This Model is trained on refined version of my dataset Code-290k-ShareGPT.
Besides this it is trained on following datasets:
CodeFeedback-Filtered-Instruction
The idea was to check how this Model will perform with both Code & Maths datasets. This model is very good with Coding. Maths outputs are also very good. You can test out this model.
It is very very good in Code generation in various languages such as Python, Java, JavaScript, GO, C++, Rust, Ruby, Sql, MySql, R, Julia, Haskell, etc.. This model will also generate detailed explanation/logic behind each code.
This Model is trained on massive datasets so the results are very good. You can check the Examples given below.
I have used ChatML prompt format.
This is Fully Finetuned Model.
GGUF & Exllama
GGUF: Link
Exllama v2: Link
Special Thanks to Bartowski for quantizing this model.
Training:
Entire dataset was trained on 4 x A100 80GB. For 2 epoch, training took more than 160 Hours. Axolotl & Deepspeed codebase was used for training purpose. Entire data is trained on Llama-3-8B by Meta.
Example Prompt: This model uses ChatML prompt format.
<|im_start|>system
You are a helpful Coding assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
You can modify above Prompt as per your requirement. One example will be:
This is a conversation with your helpful Coding assistant. Assistant can generate Code in various Programming Languages along with necessary explanation.
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
Example 1
Example 2
Example 3
Example 4
Example 5
- Created
- Aug 20, 2024
- Updated
- Aug 20, 2024