Downloads · 30 days
32
3% of all-time downloads
RichardErkhov/lemon07r_-_Gemma-2-Ataraxy-v3i-9B-gguf
lemon07r_-_Gemma-2-Ataraxy-v3i-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
32
3% of all-time downloads
All-time downloads
976
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.
Gemma-2-Ataraxy-v3i-9B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Gemma-2-Ataraxy-v3i-9B.Q2_K.gguf | Q2_K | 3.54GB |
| Gemma-2-Ataraxy-v3i-9B.IQ3_XS.gguf | IQ3_XS | 3.86GB |
| Gemma-2-Ataraxy-v3i-9B.IQ3_S.gguf | IQ3_S | 4.04GB |
| Gemma-2-Ataraxy-v3i-9B.Q3_K_S.gguf | Q3_K_S | 4.04GB |
| Gemma-2-Ataraxy-v3i-9B.IQ3_M.gguf | IQ3_M | 4.19GB |
| Gemma-2-Ataraxy-v3i-9B.Q3_K.gguf | Q3_K | 4.43GB |
| Gemma-2-Ataraxy-v3i-9B.Q3_K_M.gguf | Q3_K_M | 4.43GB |
| Gemma-2-Ataraxy-v3i-9B.Q3_K_L.gguf | Q3_K_L | 4.78GB |
| Gemma-2-Ataraxy-v3i-9B.IQ4_XS.gguf | IQ4_XS | 4.86GB |
| Gemma-2-Ataraxy-v3i-9B.Q4_0.gguf | Q4_0 | 5.07GB |
| Gemma-2-Ataraxy-v3i-9B.IQ4_NL.gguf | IQ4_NL | 5.1GB |
| Gemma-2-Ataraxy-v3i-9B.Q4_K_S.gguf | Q4_K_S | 5.1GB |
| Gemma-2-Ataraxy-v3i-9B.Q4_K.gguf | Q4_K | 5.37GB |
| Gemma-2-Ataraxy-v3i-9B.Q4_K_M.gguf | Q4_K_M | 5.37GB |
| Gemma-2-Ataraxy-v3i-9B.Q4_1.gguf | Q4_1 | 5.55GB |
| Gemma-2-Ataraxy-v3i-9B.Q5_0.gguf | Q5_0 | 6.04GB |
| Gemma-2-Ataraxy-v3i-9B.Q5_K_S.gguf | Q5_K_S | 6.04GB |
| Gemma-2-Ataraxy-v3i-9B.Q5_K.gguf | Q5_K | 6.19GB |
| Gemma-2-Ataraxy-v3i-9B.Q5_K_M.gguf | Q5_K_M | 6.19GB |
| Gemma-2-Ataraxy-v3i-9B.Q5_1.gguf | Q5_1 | 6.52GB |
| Gemma-2-Ataraxy-v3i-9B.Q6_K.gguf | Q6_K | 7.07GB |
| Gemma-2-Ataraxy-v3i-9B.Q8_0.gguf | Q8_0 | 9.15GB |
library_name: transformers tags:
Another experimental model. This one is in the vein of advanced 2.1, but we replace the simpo model used in the original recipe, with a different simpo model, that was more finetuned with writing in mind, ifable. We also use another writing model, which was trained on gutenberg. We use this one at a higher density because SPPO, on paper is the superior training method, to simpo, and quite frankly, ifable is finicky to work with, and can end up being a little too strong.. or heavy in merges. It's a very strong writer but it introduced quite a bit slop in v2.
This is a merge of pre-trained language models created using mergekit.
https://huggingface.co/lemon07r/Gemma-2-Ataraxy-v3i-9B-Q8_0-GGUF
This model was merged using the della merge method using unsloth/gemma-2-9b-it as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: unsloth/gemma-2-9b-it
dtype: bfloat16
merge_method: della
parameters:
epsilon: 0.1
int8_mask: 1.0
lambda: 1.0
normalize: 1.0
slices:
- sources:
- layer_range: [0, 42]
model: unsloth/gemma-2-9b-it
- layer_range: [0, 42]
model: wzhouad/gemma-2-9b-it-WPO-HB
parameters:
density: 0.55
weight: 0.6
- layer_range: [0, 42]
model: nbeerbower/Gemma2-Gutenberg-Doppel-9B
parameters:
density: 0.35
weight: 0.6
- layer_range: [0, 42]
model: ifable/gemma-2-Ifable-9B
parameters:
density: 0.25
weight: 0.4
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 21.29 |
| IFEval (0-Shot) | 42.03 |
| BBH (3-Shot) | 38.24 |
| MATH Lvl 5 (4-Shot) | 0.15 |
| GPQA (0-shot) | 10.40 |
| MuSR (0-shot) | 1.76 |
| MMLU-PRO (5-shot) | 35.18 |