Downloads · 30 days
312
6% of all-time downloads
RichardErkhov/grimjim_-_Gemma2-Nephilim-v3-9B-gguf
grimjim_-_Gemma2-Nephilim-v3-9B-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
312
6% of all-time downloads
All-time downloads
5K
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.
Gemma2-Nephilim-v3-9B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Gemma2-Nephilim-v3-9B.Q2_K.gguf | Q2_K | 3.54GB |
| Gemma2-Nephilim-v3-9B.IQ3_XS.gguf | IQ3_XS | 3.86GB |
| Gemma2-Nephilim-v3-9B.IQ3_S.gguf | IQ3_S | 4.04GB |
| Gemma2-Nephilim-v3-9B.Q3_K_S.gguf | Q3_K_S | 4.04GB |
| Gemma2-Nephilim-v3-9B.IQ3_M.gguf | IQ3_M | 4.19GB |
| Gemma2-Nephilim-v3-9B.Q3_K.gguf | Q3_K | 4.43GB |
| Gemma2-Nephilim-v3-9B.Q3_K_M.gguf | Q3_K_M | 4.43GB |
| Gemma2-Nephilim-v3-9B.Q3_K_L.gguf | Q3_K_L | 4.78GB |
| Gemma2-Nephilim-v3-9B.IQ4_XS.gguf | IQ4_XS | 4.86GB |
| Gemma2-Nephilim-v3-9B.Q4_0.gguf | Q4_0 | 5.07GB |
| Gemma2-Nephilim-v3-9B.IQ4_NL.gguf | IQ4_NL | 5.1GB |
| Gemma2-Nephilim-v3-9B.Q4_K_S.gguf | Q4_K_S | 5.1GB |
| Gemma2-Nephilim-v3-9B.Q4_K.gguf | Q4_K | 5.37GB |
| Gemma2-Nephilim-v3-9B.Q4_K_M.gguf | Q4_K_M | 5.37GB |
| Gemma2-Nephilim-v3-9B.Q4_1.gguf | Q4_1 | 5.55GB |
| Gemma2-Nephilim-v3-9B.Q5_0.gguf | Q5_0 | 6.04GB |
| Gemma2-Nephilim-v3-9B.Q5_K_S.gguf | Q5_K_S | 6.04GB |
| Gemma2-Nephilim-v3-9B.Q5_K.gguf | Q5_K | 6.19GB |
| Gemma2-Nephilim-v3-9B.Q5_K_M.gguf | Q5_K_M | 6.19GB |
| Gemma2-Nephilim-v3-9B.Q5_1.gguf | Q5_1 | 6.52GB |
| Gemma2-Nephilim-v3-9B.Q6_K.gguf | Q6_K | 7.07GB |
| Gemma2-Nephilim-v3-9B.Q8_0.gguf | Q8_0 | 9.15GB |
base_model:
This repo contains a merge of pre-trained language models created using mergekit.
Though none of the components of this merge were trained for roleplay nor intended for it, the model can be used effectively in that role.
Tested with temperature 1 and minP 0.01. This model leans toward being creative, so adjust temperature upward or downward as desired. The Instruct template used during testing can be found below:
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:
slices:
- sources:
- model: princeton-nlp/gemma-2-9b-it-SimPO
layer_range:
- 0
- 42
- model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
layer_range:
- 0
- 42
merge_method: slerp
base_model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
parameters:
t:
- filter: self_attn
value:
- 0
- 0.5
- 0.3
- 0.7
- 1
- filter: mlp
value:
- 1
- 0.5
- 0.7
- 0.3
- 0
- value: 0.5
dtype: bfloat16