Downloads · 30 days
18
2% of all-time downloads
Undi95_-_UndiMix-v3-13B-gguf
RichardErkhov/Undi95_-_UndiMix-v3-13B-gguf
Undi95_-_UndiMix-v3-13B-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
1.1K
Public
Repo size
110 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf125 GB · 100%
At a glance
- Access
- Public
- Created
- Nov 1, 2024
- Updated
- Nov 1, 2024
- SHA
- 55084379
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
UndiMix-v3-13B - GGUF
- Model creator: https://huggingface.co/Undi95/
- Original model: https://huggingface.co/Undi95/UndiMix-v3-13B/
| Name | Quant method | Size |
|---|---|---|
| UndiMix-v3-13B.Q2_K.gguf | Q2_K | 4.52GB |
| UndiMix-v3-13B.Q3_K_S.gguf | Q3_K_S | 5.27GB |
| UndiMix-v3-13B.Q3_K.gguf | Q3_K | 5.9GB |
| UndiMix-v3-13B.Q3_K_M.gguf | Q3_K_M | 5.9GB |
| UndiMix-v3-13B.Q3_K_L.gguf | Q3_K_L | 3.86GB |
| UndiMix-v3-13B.IQ4_XS.gguf | IQ4_XS | 5.35GB |
| UndiMix-v3-13B.Q4_0.gguf | Q4_0 | 6.86GB |
| UndiMix-v3-13B.IQ4_NL.gguf | IQ4_NL | 2.72GB |
| UndiMix-v3-13B.Q4_K_S.gguf | Q4_K_S | 3.77GB |
| UndiMix-v3-13B.Q4_K.gguf | Q4_K | 7.33GB |
| UndiMix-v3-13B.Q4_K_M.gguf | Q4_K_M | 3.1GB |
| UndiMix-v3-13B.Q4_1.gguf | Q4_1 | 0.93GB |
| UndiMix-v3-13B.Q5_0.gguf | Q5_0 | 7.03GB |
| UndiMix-v3-13B.Q5_K_S.gguf | Q5_K_S | 4.95GB |
| UndiMix-v3-13B.Q5_K.gguf | Q5_K | 8.6GB |
| UndiMix-v3-13B.Q5_K_M.gguf | Q5_K_M | 8.6GB |
| UndiMix-v3-13B.Q5_1.gguf | Q5_1 | 9.1GB |
| UndiMix-v3-13B.Q6_K.gguf | Q6_K | 9.95GB |
| UndiMix-v3-13B.Q8_0.gguf | Q8_0 | 12.88GB |
Original model description:
license: cc-by-nc-4.0
<!-- description start -->Description
This repo contains fp16 files of personal mix : "UndiMix-v3".
It can be hot, serious, playful, and can use emoji thanks to llama-2-13b-chat-limarp-v2-merged.
What change from V2 is the that I didn't use Llama-2-13B-fp16 for the base anymore, and got straight into the merging with SLERP taking ReMM-S-Kimiko-v2-13B as a base.
<!-- description end --> <!-- description start -->Models used
- Undi95/ReMM-S-Kimiko-v2-13B (0.272) (base)
- The-Face-Of-Goonery/Huginn-13b-v1.2 (0.264)
- Doctor-Shotgun/llama-2-13b-chat-limarp-v2-merged (0.264)
- jondurbin/airoboros-l2-13b-2.1 (0.10)
- IkariDev/Athena-v1 (0.10)
Prompt template: Alpaca
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
Special thanks to Sushi kek
- Created
- Nov 1, 2024
- Updated
- Nov 1, 2024