Downloads · 30 days
9
2% of all-time downloads
ericpolewski_-_Marxish-gguf
RichardErkhov/ericpolewski_-_Marxish-gguf
ericpolewski_-_Marxish-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
405
Public
Repo size
92.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf108 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 27, 2024
- Updated
- Aug 27, 2024
- SHA
- 90bdc094
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Marxish - GGUF
- Model creator: https://huggingface.co/ericpolewski/
- Original model: https://huggingface.co/ericpolewski/Marxish/
| Name | Quant method | Size |
|---|---|---|
| Marxish.Q2_K.gguf | Q2_K | 3.79GB |
| Marxish.IQ3_XS.gguf | IQ3_XS | 3.79GB |
| Marxish.IQ3_S.gguf | IQ3_S | 3.79GB |
| Marxish.Q3_K_S.gguf | Q3_K_S | 3.79GB |
| Marxish.IQ3_M.gguf | IQ3_M | 3.95GB |
| Marxish.Q3_K.gguf | Q3_K | 4.11GB |
| Marxish.Q3_K_M.gguf | Q3_K_M | 4.11GB |
| Marxish.Q3_K_L.gguf | Q3_K_L | 4.26GB |
| Marxish.IQ4_XS.gguf | IQ4_XS | 3.83GB |
| Marxish.Q4_0.gguf | Q4_0 | 3.79GB |
| Marxish.IQ4_NL.gguf | IQ4_NL | 3.83GB |
| Marxish.Q4_K_S.gguf | Q4_K_S | 4.63GB |
| Marxish.Q4_K.gguf | Q4_K | 4.98GB |
| Marxish.Q4_K_M.gguf | Q4_K_M | 4.98GB |
| Marxish.Q4_1.gguf | Q4_1 | 4.2GB |
| Marxish.Q5_0.gguf | Q5_0 | 4.61GB |
| Marxish.Q5_K_S.gguf | Q5_K_S | 5.02GB |
| Marxish.Q5_K.gguf | Q5_K | 5.33GB |
| Marxish.Q5_K_M.gguf | Q5_K_M | 5.33GB |
| Marxish.Q5_1.gguf | Q5_1 | 5.02GB |
| Marxish.Q6_K.gguf | Q6_K | 6.6GB |
| Marxish.Q8_0.gguf | Q8_0 | 7.07GB |
Original model description:
license: mit
This is a frankensteined Marx3b-v2 model (https://huggingface.co/acrastt/Marx-3B-V2)
It is approximately 7.1b. Just testing things out.
bfloat16
Used the same model 4 times. I fine-tuned it at r 256 but used the wrong alpaca format so I'll need to re-upload that merged model.
- Created
- Aug 27, 2024
- Updated
- Aug 27, 2024