Downloads · 30 days
55
6% of all-time downloads
RichardErkhov/grimjim_-_Magot-v3-Gemma2-8k-9B-gguf
grimjim_-_Magot-v3-Gemma2-8k-9B-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
55
6% of all-time downloads
All-time downloads
861
Public
Repo size
108 GB
Likes
0
Public
Click a slice to open those files.
.gguf126 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Magot-v3-Gemma2-8k-9B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Magot-v3-Gemma2-8k-9B.Q2_K.gguf | Q2_K | 3.54GB |
| Magot-v3-Gemma2-8k-9B.IQ3_XS.gguf | IQ3_XS | 3.86GB |
| Magot-v3-Gemma2-8k-9B.IQ3_S.gguf | IQ3_S | 4.04GB |
| Magot-v3-Gemma2-8k-9B.Q3_K_S.gguf | Q3_K_S | 4.04GB |
| Magot-v3-Gemma2-8k-9B.IQ3_M.gguf | IQ3_M | 4.19GB |
| Magot-v3-Gemma2-8k-9B.Q3_K.gguf | Q3_K | 4.43GB |
| Magot-v3-Gemma2-8k-9B.Q3_K_M.gguf | Q3_K_M | 4.43GB |
| Magot-v3-Gemma2-8k-9B.Q3_K_L.gguf | Q3_K_L | 4.78GB |
| Magot-v3-Gemma2-8k-9B.IQ4_XS.gguf | IQ4_XS | 4.86GB |
| Magot-v3-Gemma2-8k-9B.Q4_0.gguf | Q4_0 | 5.07GB |
| Magot-v3-Gemma2-8k-9B.IQ4_NL.gguf | IQ4_NL | 5.1GB |
| Magot-v3-Gemma2-8k-9B.Q4_K_S.gguf | Q4_K_S | 5.1GB |
| Magot-v3-Gemma2-8k-9B.Q4_K.gguf | Q4_K | 5.37GB |
| Magot-v3-Gemma2-8k-9B.Q4_K_M.gguf | Q4_K_M | 5.37GB |
| Magot-v3-Gemma2-8k-9B.Q4_1.gguf | Q4_1 | 5.55GB |
| Magot-v3-Gemma2-8k-9B.Q5_0.gguf | Q5_0 | 6.04GB |
| Magot-v3-Gemma2-8k-9B.Q5_K_S.gguf | Q5_K_S | 6.04GB |
| Magot-v3-Gemma2-8k-9B.Q5_K.gguf | Q5_K | 6.19GB |
| Magot-v3-Gemma2-8k-9B.Q5_K_M.gguf | Q5_K_M | 6.19GB |
| Magot-v3-Gemma2-8k-9B.Q5_1.gguf | Q5_1 | 6.52GB |
| Magot-v3-Gemma2-8k-9B.Q6_K.gguf | Q6_K | 7.07GB |
| Magot-v3-Gemma2-8k-9B.Q8_0.gguf | Q8_0 | 9.15GB |
base_model:
This repo contains a merge of pre-trained language models created using mergekit.
This series of models is an attempt to combine the strengths of Instruct models with the creativity of Magnum models while balancing text generation on the shorter side compared to undiluted Magnum.
Tested at temp=1, minP=0.01.
This attempt seems more solid than earlier versions in the series. Coherence is moderately high. Unfortunately, some recency bias remains.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: grimjim/Kitsunebi-v1-Gemma2-8k-9B
- model: anthracite-org/magnum-v3-9b-chatml
merge_method: slerp
base_model: grimjim/Kitsunebi-v1-Gemma2-8k-9B
parameters:
t:
- value: 0.2
dtype: bfloat16