|
Quantization made by Richard Erkhov. |
|
|
|
[Github](https://github.com/RichardErkhov) |
|
|
|
[Discord](https://discord.gg/pvy7H8DZMG) |
|
|
|
[Request more models](https://github.com/RichardErkhov/quant_request) |
|
|
|
|
|
DARE_TIES_13B - GGUF |
|
- Model creator: https://huggingface.co/yunconglong/ |
|
- Original model: https://huggingface.co/yunconglong/DARE_TIES_13B/ |
|
|
|
|
|
| Name | Quant method | Size | |
|
| ---- | ---- | ---- | |
|
| [DARE_TIES_13B.Q2_K.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q2_K.gguf) | Q2_K | 4.43GB | |
|
| [DARE_TIES_13B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.IQ3_XS.gguf) | IQ3_XS | 4.94GB | |
|
| [DARE_TIES_13B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.IQ3_S.gguf) | IQ3_S | 5.22GB | |
|
| [DARE_TIES_13B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q3_K_S.gguf) | Q3_K_S | 5.2GB | |
|
| [DARE_TIES_13B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.IQ3_M.gguf) | IQ3_M | 5.34GB | |
|
| [DARE_TIES_13B.Q3_K.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q3_K.gguf) | Q3_K | 5.78GB | |
|
| [DARE_TIES_13B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q3_K_M.gguf) | Q3_K_M | 5.78GB | |
|
| [DARE_TIES_13B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q3_K_L.gguf) | Q3_K_L | 6.27GB | |
|
| [DARE_TIES_13B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.IQ4_XS.gguf) | IQ4_XS | 6.5GB | |
|
| [DARE_TIES_13B.Q4_0.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q4_0.gguf) | Q4_0 | 6.78GB | |
|
| [DARE_TIES_13B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.IQ4_NL.gguf) | IQ4_NL | 6.85GB | |
|
| [DARE_TIES_13B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q4_K_S.gguf) | Q4_K_S | 6.84GB | |
|
| [DARE_TIES_13B.Q4_K.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q4_K.gguf) | Q4_K | 7.25GB | |
|
| [DARE_TIES_13B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q4_K_M.gguf) | Q4_K_M | 7.25GB | |
|
| [DARE_TIES_13B.Q4_1.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q4_1.gguf) | Q4_1 | 7.52GB | |
|
| [DARE_TIES_13B.Q5_0.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q5_0.gguf) | Q5_0 | 8.26GB | |
|
| [DARE_TIES_13B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q5_K_S.gguf) | Q5_K_S | 8.26GB | |
|
| [DARE_TIES_13B.Q5_K.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q5_K.gguf) | Q5_K | 8.51GB | |
|
| [DARE_TIES_13B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q5_K_M.gguf) | Q5_K_M | 8.51GB | |
|
| [DARE_TIES_13B.Q5_1.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q5_1.gguf) | Q5_1 | 9.01GB | |
|
| [DARE_TIES_13B.Q6_K.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q6_K.gguf) | Q6_K | 9.84GB | |
|
| [DARE_TIES_13B.Q8_0.gguf](https://huggingface.co/RichardErkhov/yunconglong_-_DARE_TIES_13B-gguf/blob/main/DARE_TIES_13B.Q8_0.gguf) | Q8_0 | 12.75GB | |
|
|
|
|
|
|
|
|
|
Original model description: |
|
--- |
|
license: |
|
- other |
|
|
|
tags: |
|
- dare ties |
|
|
|
--- |
|
# DARE_TIES_13B |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B](https://huggingface.co/yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* ./13B_DPO |
|
* ./13B_MATH_DPO |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B |
|
parameters: |
|
density: 1.0 |
|
weight: 1.0 |
|
- model: ./13B_MATH_DPO |
|
parameters: |
|
density: 0.5 |
|
weight: [0.33, 0.4, 0.33] |
|
- model: ./13B_DPO |
|
parameters: |
|
density: [0.33, 0.45, 0.66] |
|
weight: 0.66 |
|
merge_method: dare_ties |
|
base_model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B |
|
parameters: |
|
normalize: true |
|
int8_mask: true |
|
dtype: bfloat16 |
|
tokenizer_source : union |
|
|
|
``` |
|
|
|
|
|
|