Downloads · 30 days
30
1% of all-time downloads
Undi95_-_C-Based-2x7B-gguf
RichardErkhov/Undi95_-_C-Based-2x7B-gguf
Undi95_-_C-Based-2x7B-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
2.7K
Public
Repo size
146 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf169 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 21, 2024
- Updated
- Sep 21, 2024
- SHA
- 9849ff92
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
C-Based-2x7B - GGUF
- Model creator: https://huggingface.co/Undi95/
- Original model: https://huggingface.co/Undi95/C-Based-2x7B/
| Name | Quant method | Size |
|---|---|---|
| C-Based-2x7B.Q2_K.gguf | Q2_K | 4.43GB |
| C-Based-2x7B.IQ3_XS.gguf | IQ3_XS | 4.95GB |
| C-Based-2x7B.IQ3_S.gguf | IQ3_S | 5.22GB |
| C-Based-2x7B.Q3_K_S.gguf | Q3_K_S | 5.2GB |
| C-Based-2x7B.IQ3_M.gguf | IQ3_M | 5.35GB |
| C-Based-2x7B.Q3_K.gguf | Q3_K | 5.78GB |
| C-Based-2x7B.Q3_K_M.gguf | Q3_K_M | 5.78GB |
| C-Based-2x7B.Q3_K_L.gguf | Q3_K_L | 6.27GB |
| C-Based-2x7B.IQ4_XS.gguf | IQ4_XS | 6.5GB |
| C-Based-2x7B.Q4_0.gguf | Q4_0 | 6.78GB |
| C-Based-2x7B.IQ4_NL.gguf | IQ4_NL | 6.85GB |
| C-Based-2x7B.Q4_K_S.gguf | Q4_K_S | 6.84GB |
| C-Based-2x7B.Q4_K.gguf | Q4_K | 7.25GB |
| C-Based-2x7B.Q4_K_M.gguf | Q4_K_M | 7.25GB |
| C-Based-2x7B.Q4_1.gguf | Q4_1 | 7.52GB |
| C-Based-2x7B.Q5_0.gguf | Q5_0 | 8.26GB |
| C-Based-2x7B.Q5_K_S.gguf | Q5_K_S | 8.26GB |
| C-Based-2x7B.Q5_K.gguf | Q5_K | 8.51GB |
| C-Based-2x7B.Q5_K_M.gguf | Q5_K_M | 8.51GB |
| C-Based-2x7B.Q5_1.gguf | Q5_1 | 9.01GB |
| C-Based-2x7B.Q6_K.gguf | Q6_K | 9.84GB |
| C-Based-2x7B.Q8_0.gguf | Q8_0 | 12.75GB |
Original model description:
license: cc-by-nc-4.0 tags:
- not-for-all-audiences
- nsfw
<!-- description start -->
Description
This repo contains fp16 files of C-Based-2x7B.
Created by taking the best benchmark scoring model with the smallest size on HF leaderboard as of today (29/03/2024) which is zhengr/MixTAO-7Bx2-MoE-v8.1 and merging to it some MoE done by myself using the human feedback data from Chaiverse specifically to have high level of RP, intelligence and usage.
Since this is a frankenmoe, I really don't know what the result will be leaderboard side, but what interest me is the human interaction realism anyway (for RP/ERP).
<!-- description end --> <!-- prompt-template start -->Prompt template: Alpaca
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{system prompt}
### Input:
{prompt}
### Response:
{output}
If you want to support me, you can here.
- Created
- Sep 21, 2024
- Updated
- Sep 21, 2024