Downloads · 30 days
149
21% of all-time downloads
ClaudioItaly_-_Book-Gut12B-gguf
RichardErkhov/ClaudioItaly_-_Book-Gut12B-gguf
ClaudioItaly_-_Book-Gut12B-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
722
Public
Repo size
141 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf163 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 29, 2024
- Updated
- Sep 30, 2024
- SHA
- d9d2aa15
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Book-Gut12B - GGUF
- Model creator: https://huggingface.co/ClaudioItaly/
- Original model: https://huggingface.co/ClaudioItaly/Book-Gut12B/
| Name | Quant method | Size |
|---|---|---|
| Book-Gut12B.Q2_K.gguf | Q2_K | 4.46GB |
| Book-Gut12B.IQ3_XS.gguf | IQ3_XS | 4.94GB |
| Book-Gut12B.IQ3_S.gguf | IQ3_S | 5.18GB |
| Book-Gut12B.Q3_K_S.gguf | Q3_K_S | 5.15GB |
| Book-Gut12B.IQ3_M.gguf | IQ3_M | 5.33GB |
| Book-Gut12B.Q3_K.gguf | Q3_K | 5.67GB |
| Book-Gut12B.Q3_K_M.gguf | Q3_K_M | 5.67GB |
| Book-Gut12B.Q3_K_L.gguf | Q3_K_L | 6.11GB |
| Book-Gut12B.IQ4_XS.gguf | IQ4_XS | 6.33GB |
| Book-Gut12B.Q4_0.gguf | Q4_0 | 6.59GB |
| Book-Gut12B.IQ4_NL.gguf | IQ4_NL | 6.65GB |
| Book-Gut12B.Q4_K_S.gguf | Q4_K_S | 6.63GB |
| Book-Gut12B.Q4_K.gguf | Q4_K | 6.96GB |
| Book-Gut12B.Q4_K_M.gguf | Q4_K_M | 6.96GB |
| Book-Gut12B.Q4_1.gguf | Q4_1 | 7.26GB |
| Book-Gut12B.Q5_0.gguf | Q5_0 | 7.93GB |
| Book-Gut12B.Q5_K_S.gguf | Q5_K_S | 7.93GB |
| Book-Gut12B.Q5_K.gguf | Q5_K | 8.13GB |
| Book-Gut12B.Q5_K_M.gguf | Q5_K_M | 8.13GB |
| Book-Gut12B.Q5_1.gguf | Q5_1 | 8.61GB |
| Book-Gut12B.Q6_K.gguf | Q6_K | 9.37GB |
| Book-Gut12B.Q8_0.gguf | Q8_0 | 12.13GB |
Original model description:
base_model:
- nbeerbower/Stella-mistral-nemo-12B-v2
- nbeerbower/mistral-nemo-gutenberg-12B-v2 library_name: transformers tags:
- mergekit
- merge license: mit
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: nbeerbower/Stella-mistral-nemo-12B-v2
- model: nbeerbower/mistral-nemo-gutenberg-12B-v2
merge_method: slerp
tokenizer_merge_method: slerp
tokenizer_parameters:
t: 0.3 # Dà più peso al tokenizer
base_model: nbeerbower/mistral-nemo-gutenberg-12B-v2
dtype: bfloat16
parameters:
t: [0, 0.2, 0.4, 0.5, 0.4, 0.2, 0] # Curva che favorisce leggermente
temp: 1.3 # Temperatura per smoothare il merge
density: # Density merging per bilanciare le caratteristiche dei due modelli
- threshold: 0.1
t: 0.7
- threshold: 0.5
t: 0.5
- threshold: 0.9
t: 0.3
- Created
- Sep 29, 2024
- Updated
- Sep 30, 2024