100 lines
6.3 KiB
Markdown
100 lines
6.3 KiB
Markdown
|
Quantization made by Richard Erkhov.
|
||
|
|
|
||
|
|
[Github](https://github.com/RichardErkhov)
|
||
|
|
|
||
|
|
[Discord](https://discord.gg/pvy7H8DZMG)
|
||
|
|
|
||
|
|
[Request more models](https://github.com/RichardErkhov/quant_request)
|
||
|
|
|
||
|
|
|
||
|
|
mergekit-model_stock-xtxndeh - GGUF
|
||
|
|
- Model creator: https://huggingface.co/Hjgugugjhuhjggg/
|
||
|
|
- Original model: https://huggingface.co/Hjgugugjhuhjggg/mergekit-model_stock-xtxndeh/
|
||
|
|
|
||
|
|
|
||
|
|
| Name | Quant method | Size |
|
||
|
|
| ---- | ---- | ---- |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q2_K.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q2_K.gguf) | Q2_K | 0.7GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.IQ3_XS.gguf) | IQ3_XS | 0.77GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.IQ3_S.gguf) | IQ3_S | 0.8GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q3_K_S.gguf) | Q3_K_S | 0.8GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.IQ3_M.gguf) | IQ3_M | 0.82GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q3_K.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q3_K.gguf) | Q3_K | 0.86GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q3_K_M.gguf) | Q3_K_M | 0.86GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q3_K_L.gguf) | Q3_K_L | 0.91GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.IQ4_XS.gguf) | IQ4_XS | 0.96GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q4_0.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q4_0.gguf) | Q4_0 | 0.99GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.IQ4_NL.gguf) | IQ4_NL | 1.0GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q4_K_S.gguf) | Q4_K_S | 1.0GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q4_K.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q4_K.gguf) | Q4_K | 1.04GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q4_K_M.gguf) | Q4_K_M | 1.04GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q4_1.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q4_1.gguf) | Q4_1 | 1.08GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q5_0.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q5_0.gguf) | Q5_0 | 1.17GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q5_K_S.gguf) | Q5_K_S | 1.17GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q5_K.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q5_K.gguf) | Q5_K | 1.2GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q5_K_M.gguf) | Q5_K_M | 1.2GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q5_1.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q5_1.gguf) | Q5_1 | 1.26GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q6_K.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q6_K.gguf) | Q6_K | 1.36GB |
|
||
|
|
| [mergekit-model_stock-xtxndeh.Q8_0.gguf](https://huggingface.co/RichardErkhov/Hjgugugjhuhjggg_-_mergekit-model_stock-xtxndeh-gguf/blob/main/mergekit-model_stock-xtxndeh.Q8_0.gguf) | Q8_0 | 1.76GB |
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
Original model description:
|
||
|
|
---
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen2.5-1.5B
|
||
|
|
- Qwen/Qwen2.5-Math-1.5B-Instruct
|
||
|
|
- Qwen/Qwen2.5-1.5B-Instruct
|
||
|
|
- Qwen/Qwen2.5-Math-1.5B
|
||
|
|
- Qwen/Qwen2.5-Coder-1.5B
|
||
|
|
- Qwen/Qwen2.5-Coder-1.5B-Instruct
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- mergekit
|
||
|
|
- merge
|
||
|
|
|
||
|
|
---
|
||
|
|
# merge
|
||
|
|
|
||
|
|
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) as a base.
|
||
|
|
|
||
|
|
### Models Merged
|
||
|
|
|
||
|
|
The following models were included in the merge:
|
||
|
|
* [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B)
|
||
|
|
* [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct)
|
||
|
|
* [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)
|
||
|
|
* [Qwen/Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B)
|
||
|
|
* [Qwen/Qwen2.5-Coder-1.5B](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B)
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
merge_method: model_stock
|
||
|
|
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
|
||
|
|
|
||
|
|
models:
|
||
|
|
- model: Qwen/Qwen2.5-1.5B
|
||
|
|
- model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
||
|
|
- model: Qwen/Qwen2.5-Coder-1.5B-Instruct
|
||
|
|
- model: Qwen/Qwen2.5-Math-1.5B
|
||
|
|
- model: Qwen/Qwen2.5-1.5B-Instruct
|
||
|
|
- model: Qwen/Qwen2.5-Coder-1.5B
|
||
|
|
|
||
|
|
parameters:
|
||
|
|
density: 0.5
|
||
|
|
weight: 1.0
|
||
|
|
int8_mask: true
|
||
|
|
|
||
|
|
```
|
||
|
|
|
||
|
|
|