Downloads · 30 days
127
22% of all-time downloads
TeeZee_-_Qra-13B-chat-gguf
RichardErkhov/TeeZee_-_Qra-13B-chat-gguf
TeeZee_-_Qra-13B-chat-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
590
Public
Repo size
147 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf171 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 18, 2024
- Updated
- Sep 18, 2024
- SHA
- f27d7264
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Qra-13B-chat - GGUF
- Model creator: https://huggingface.co/TeeZee/
- Original model: https://huggingface.co/TeeZee/Qra-13B-chat/
| Name | Quant method | Size |
|---|---|---|
| Qra-13B-chat.Q2_K.gguf | Q2_K | 4.52GB |
| Qra-13B-chat.IQ3_XS.gguf | IQ3_XS | 4.99GB |
| Qra-13B-chat.IQ3_S.gguf | IQ3_S | 5.27GB |
| Qra-13B-chat.Q3_K_S.gguf | Q3_K_S | 5.27GB |
| Qra-13B-chat.IQ3_M.gguf | IQ3_M | 5.57GB |
| Qra-13B-chat.Q3_K.gguf | Q3_K | 5.9GB |
| Qra-13B-chat.Q3_K_M.gguf | Q3_K_M | 5.9GB |
| Qra-13B-chat.Q3_K_L.gguf | Q3_K_L | 6.45GB |
| Qra-13B-chat.IQ4_XS.gguf | IQ4_XS | 6.54GB |
| Qra-13B-chat.Q4_0.gguf | Q4_0 | 6.86GB |
| Qra-13B-chat.IQ4_NL.gguf | IQ4_NL | 6.9GB |
| Qra-13B-chat.Q4_K_S.gguf | Q4_K_S | 6.91GB |
| Qra-13B-chat.Q4_K.gguf | Q4_K | 7.33GB |
| Qra-13B-chat.Q4_K_M.gguf | Q4_K_M | 7.33GB |
| Qra-13B-chat.Q4_1.gguf | Q4_1 | 7.61GB |
| Qra-13B-chat.Q5_0.gguf | Q5_0 | 8.36GB |
| Qra-13B-chat.Q5_K_S.gguf | Q5_K_S | 8.36GB |
| Qra-13B-chat.Q5_K.gguf | Q5_K | 8.6GB |
| Qra-13B-chat.Q5_K_M.gguf | Q5_K_M | 8.6GB |
| Qra-13B-chat.Q5_1.gguf | Q5_1 | 9.1GB |
| Qra-13B-chat.Q6_K.gguf | Q6_K | 9.95GB |
| Qra-13B-chat.Q8_0.gguf | Q8_0 | 12.88GB |
Original model description:
base_model: TeeZee/Qra-13b-instruct language:
- en
- pl license: llama2 tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft datasets:
- TeeZee/chat-alpaca-pl-no-refusals
TeeZee/Qra-13B-chat
- Developed by: TeeZee
- License: llama2
- Finetuned from model : TeeZee/Qra-13b-instruct
- Finetuned on a PL chat dataset
- Alpaca chat format, tested, works fine, can follow chat coherently
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel: <a href="https://www.buymeacoffee.com/TeeZee" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
- Created
- Sep 18, 2024
- Updated
- Sep 18, 2024