Downloads · 30 days
265
8% of all-time downloads
NotASI_-_Qwen2-0.5B-Math-gguf
RichardErkhov/NotASI_-_Qwen2-0.5B-Math-gguf
NotASI_-_Qwen2-0.5B-Math-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
3.3K
Public
Repo size
7.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf8.5 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 4, 2024
- Updated
- Oct 4, 2024
- SHA
- 1f8253d8
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Qwen2-0.5B-Math - GGUF
- Model creator: https://huggingface.co/NotASI/
- Original model: https://huggingface.co/NotASI/Qwen2-0.5B-Math/
| Name | Quant method | Size |
|---|---|---|
| Qwen2-0.5B-Math.Q2_K.gguf | Q2_K | 0.32GB |
| Qwen2-0.5B-Math.IQ3_XS.gguf | IQ3_XS | 0.32GB |
| Qwen2-0.5B-Math.IQ3_S.gguf | IQ3_S | 0.32GB |
| Qwen2-0.5B-Math.Q3_K_S.gguf | Q3_K_S | 0.32GB |
| Qwen2-0.5B-Math.IQ3_M.gguf | IQ3_M | 0.32GB |
| Qwen2-0.5B-Math.Q3_K.gguf | Q3_K | 0.33GB |
| Qwen2-0.5B-Math.Q3_K_M.gguf | Q3_K_M | 0.33GB |
| Qwen2-0.5B-Math.Q3_K_L.gguf | Q3_K_L | 0.34GB |
| Qwen2-0.5B-Math.IQ4_XS.gguf | IQ4_XS | 0.33GB |
| Qwen2-0.5B-Math.Q4_0.gguf | Q4_0 | 0.33GB |
| Qwen2-0.5B-Math.IQ4_NL.gguf | IQ4_NL | 0.33GB |
| Qwen2-0.5B-Math.Q4_K_S.gguf | Q4_K_S | 0.36GB |
| Qwen2-0.5B-Math.Q4_K.gguf | Q4_K | 0.37GB |
| Qwen2-0.5B-Math.Q4_K_M.gguf | Q4_K_M | 0.37GB |
| Qwen2-0.5B-Math.Q4_1.gguf | Q4_1 | 0.35GB |
| Qwen2-0.5B-Math.Q5_0.gguf | Q5_0 | 0.37GB |
| Qwen2-0.5B-Math.Q5_K_S.gguf | Q5_K_S | 0.38GB |
| Qwen2-0.5B-Math.Q5_K.gguf | Q5_K | 0.39GB |
| Qwen2-0.5B-Math.Q5_K_M.gguf | Q5_K_M | 0.39GB |
| Qwen2-0.5B-Math.Q5_1.gguf | Q5_1 | 0.39GB |
| Qwen2-0.5B-Math.Q6_K.gguf | Q6_K | 0.47GB |
| Qwen2-0.5B-Math.Q8_0.gguf | Q8_0 | 0.49GB |
Original model description:
language:
- en license: apache-2.0 tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- sft base_model: unsloth/Qwen2-0.5B-Instruct-bnb-4bit datasets:
- microsoft/orca-math-word-problems-200k
Coding model comming soon!
Uploaded model
- Developed by: NotAiLOL
- License: apache-2.0
- Finetuned from model : unsloth/Qwen2-0.5B-Instruct-bnb-4bit
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Details
This model was trained on microsoft/orca-math-word-problems-200k for 3 epochs with rsLoRA + QLoRA.
Training Loss Graph
The model follows the Alpaca format:
<|im_start|>system
You are a professional mathematician.|im_end|>
<|im_start|>user
{}<|im_end|>
<|im_start|>assistant
{}
- Created
- Oct 4, 2024
- Updated
- Oct 4, 2024