Downloads · 30 days
43
10% of all-time downloads
RichardErkhov/Nohobby_-_Karasik-22B-v0.2-gguf
Nohobby_-_Karasik-22B-v0.2-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.
Downloads · 30 days
43
10% of all-time downloads
All-time downloads
427
Public
Repo size
252 GB
Likes
0
Public
Click a slice to open those files.
.gguf291 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Karasik-22B-v0.2 - GGUF
| Name | Quant method | Size |
|---|---|---|
| Karasik-22B-v0.2.Q2_K.gguf | Q2_K | 7.7GB |
| Karasik-22B-v0.2.IQ3_XS.gguf | IQ3_XS | 8.55GB |
| Karasik-22B-v0.2.IQ3_S.gguf | IQ3_S | 9.02GB |
| Karasik-22B-v0.2.Q3_K_S.gguf | Q3_K_S | 8.98GB |
| Karasik-22B-v0.2.IQ3_M.gguf | IQ3_M | 9.37GB |
| Karasik-22B-v0.2.Q3_K.gguf | Q3_K | 10.02GB |
| Karasik-22B-v0.2.Q3_K_M.gguf | Q3_K_M | 10.02GB |
| Karasik-22B-v0.2.Q3_K_L.gguf | Q3_K_L | 10.92GB |
| Karasik-22B-v0.2.IQ4_XS.gguf | IQ4_XS | 11.22GB |
| Karasik-22B-v0.2.Q4_0.gguf | Q4_0 | 11.71GB |
| Karasik-22B-v0.2.IQ4_NL.gguf | IQ4_NL | 11.83GB |
| Karasik-22B-v0.2.Q4_K_S.gguf | Q4_K_S | 11.79GB |
| Karasik-22B-v0.2.Q4_K.gguf | Q4_K | 12.43GB |
| Karasik-22B-v0.2.Q4_K_M.gguf | Q4_K_M | 12.43GB |
| Karasik-22B-v0.2.Q4_1.gguf | Q4_1 | 12.99GB |
| Karasik-22B-v0.2.Q5_0.gguf | Q5_0 | 14.27GB |
| Karasik-22B-v0.2.Q5_K_S.gguf | Q5_K_S | 14.27GB |
| Karasik-22B-v0.2.Q5_K.gguf | Q5_K | 14.64GB |
| Karasik-22B-v0.2.Q5_K_M.gguf | Q5_K_M | 14.64GB |
| Karasik-22B-v0.2.Q5_1.gguf | Q5_1 | 15.56GB |
| Karasik-22B-v0.2.Q6_K.gguf | Q6_K | 17.0GB |
| Karasik-22B-v0.2.Q8_0.gguf | Q8_0 | 22.02GB |
base_model:
Somewhat experimental merge of some Mistral Small models.
This model was merged using the della_linear merge method using ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
parameters:
epsilon: 0.04
lambda: 1.05
int8_mask: true
rescale: true
normalize: false
dtype: bfloat16
tokenizer_source: base
merge_method: della_linear
models:
- model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
parameters:
weight: [0.2, 0.3, 0.2, 0.3, 0.2]
density: [0.45, 0.55, 0.45, 0.55, 0.45]
- model: gghfez/SeminalRP-22b
parameters:
weight: [0.01768, -0.01675, 0.01285, -0.01696, 0.01421]
density: [0.6, 0.4, 0.5, 0.4, 0.6]
- model: TheDrummer/Cydonia-22B-v1.1
parameters:
weight: [0.208, 0.139, 0.139, 0.139, 0.208]
density: [0.7]
- model: nbeerbower/Mistral-Small-Drummer-22B
parameters:
weight: [0.33]
density: [0.45, 0.55, 0.45, 0.55, 0.45]