Commit
•
6946fb0
1
Parent(s):
5da4e46
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
base_model:
|
| 5 |
+
- bunnycore/Gemma2-2B-Chaos
|
| 6 |
+
- bunnycore/Gemma2-2b-Evol-lora
|
| 7 |
+
- SaisExperiments/Gemma-2-2B-Stheno-Filtered
|
| 8 |
+
- bunnycore/Gemma2-2b-Evol-lora
|
| 9 |
+
- SaisExperiments/Gemma-2-2B-Opus-Instruct
|
| 10 |
+
- bunnycore/Gemma2-2b-Evol-lora
|
| 11 |
+
- MinnieMin/gemma-2-2b-it-ThinkLink
|
| 12 |
+
- bunnycore/Gemma2-2b-code-lora
|
| 13 |
+
- IlyaGusev/gemma-2-2b-it-abliterated
|
| 14 |
+
- bunnycore/Gemma2-2B-mixed
|
| 15 |
+
- bunnycore/Gemma2-2b-Evol-lora
|
| 16 |
+
- RyanYr/gemma-2-2b-it_CoT-it_SFT
|
| 17 |
+
- IlyaGusev/gemma-2-2b-it-abliterated
|
| 18 |
+
- bunnycore/Gemma2-2b-code-lora
|
| 19 |
+
library_name: transformers
|
| 20 |
+
tags:
|
| 21 |
+
- mergekit
|
| 22 |
+
- merge
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
[](https://hf.co/QuantFactory)
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
# QuantFactory/Gemma-2-2b-TitanFusion-GGUF
|
| 31 |
+
This is quantized version of [bunnycore/Gemma-2-2b-TitanFusion](https://huggingface.co/bunnycore/Gemma-2-2b-TitanFusion) created using llama.cpp
|
| 32 |
+
|
| 33 |
+
# Original Model Card
|
| 34 |
+
|
| 35 |
+
# merge
|
| 36 |
+
|
| 37 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 38 |
+
|
| 39 |
+
## Merge Details
|
| 40 |
+
### Merge Method
|
| 41 |
+
|
| 42 |
+
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [IlyaGusev/gemma-2-2b-it-abliterated](https://huggingface.co/IlyaGusev/gemma-2-2b-it-abliterated) as a base.
|
| 43 |
+
|
| 44 |
+
### Models Merged
|
| 45 |
+
|
| 46 |
+
The following models were included in the merge:
|
| 47 |
+
* [bunnycore/Gemma2-2B-Chaos](https://huggingface.co/bunnycore/Gemma2-2B-Chaos) + [bunnycore/Gemma2-2b-Evol-lora](https://huggingface.co/bunnycore/Gemma2-2b-Evol-lora)
|
| 48 |
+
* [SaisExperiments/Gemma-2-2B-Stheno-Filtered](https://huggingface.co/SaisExperiments/Gemma-2-2B-Stheno-Filtered) + [bunnycore/Gemma2-2b-Evol-lora](https://huggingface.co/bunnycore/Gemma2-2b-Evol-lora)
|
| 49 |
+
* [SaisExperiments/Gemma-2-2B-Opus-Instruct](https://huggingface.co/SaisExperiments/Gemma-2-2B-Opus-Instruct) + [bunnycore/Gemma2-2b-Evol-lora](https://huggingface.co/bunnycore/Gemma2-2b-Evol-lora)
|
| 50 |
+
* [MinnieMin/gemma-2-2b-it-ThinkLink](https://huggingface.co/MinnieMin/gemma-2-2b-it-ThinkLink) + [bunnycore/Gemma2-2b-code-lora](https://huggingface.co/bunnycore/Gemma2-2b-code-lora)
|
| 51 |
+
* [bunnycore/Gemma2-2B-mixed](https://huggingface.co/bunnycore/Gemma2-2B-mixed) + [bunnycore/Gemma2-2b-Evol-lora](https://huggingface.co/bunnycore/Gemma2-2b-Evol-lora)
|
| 52 |
+
* [RyanYr/gemma-2-2b-it_CoT-it_SFT](https://huggingface.co/RyanYr/gemma-2-2b-it_CoT-it_SFT)
|
| 53 |
+
* [IlyaGusev/gemma-2-2b-it-abliterated](https://huggingface.co/IlyaGusev/gemma-2-2b-it-abliterated) + [bunnycore/Gemma2-2b-code-lora](https://huggingface.co/bunnycore/Gemma2-2b-code-lora)
|
| 54 |
+
|
| 55 |
+
### Configuration
|
| 56 |
+
|
| 57 |
+
The following YAML configuration was used to produce this model:
|
| 58 |
+
|
| 59 |
+
```yaml
|
| 60 |
+
models:
|
| 61 |
+
- model: IlyaGusev/gemma-2-2b-it-abliterated+bunnycore/Gemma2-2b-code-lora
|
| 62 |
+
- model: bunnycore/Gemma2-2B-mixed+bunnycore/Gemma2-2b-Evol-lora
|
| 63 |
+
- model: bunnycore/Gemma2-2B-Chaos+bunnycore/Gemma2-2b-Evol-lora
|
| 64 |
+
- model: SaisExperiments/Gemma-2-2B-Opus-Instruct+bunnycore/Gemma2-2b-Evol-lora
|
| 65 |
+
- model: SaisExperiments/Gemma-2-2B-Stheno-Filtered+bunnycore/Gemma2-2b-Evol-lora
|
| 66 |
+
- model: RyanYr/gemma-2-2b-it_CoT-it_SFT
|
| 67 |
+
- model: MinnieMin/gemma-2-2b-it-ThinkLink+bunnycore/Gemma2-2b-code-lora
|
| 68 |
+
merge_method: model_stock
|
| 69 |
+
base_model: IlyaGusev/gemma-2-2b-it-abliterated
|
| 70 |
+
dtype: bfloat16
|
| 71 |
+
|
| 72 |
+
```
|
| 73 |
+
|