Downloads · 30 days
268
15% of all-time downloads
RichardErkhov/mergekit-community_-_mergekit-ties-hqqzvmi-gguf
mergekit-community_-_mergekit-ties-hqqzvmi-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
268
15% of all-time downloads
All-time downloads
1.8K
Public
Repo size
8.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf10.5 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
mergekit-ties-hqqzvmi - GGUF
| Name | Quant method | Size |
|---|---|---|
| mergekit-ties-hqqzvmi.Q2_K.gguf | Q2_K | 0.39GB |
| mergekit-ties-hqqzvmi.IQ3_XS.gguf | IQ3_XS | 0.39GB |
| mergekit-ties-hqqzvmi.IQ3_S.gguf | IQ3_S | 0.39GB |
| mergekit-ties-hqqzvmi.Q3_K_S.gguf | Q3_K_S | 0.39GB |
| mergekit-ties-hqqzvmi.IQ3_M.gguf | IQ3_M | 0.39GB |
| mergekit-ties-hqqzvmi.Q3_K.gguf | Q3_K | 0.4GB |
| mergekit-ties-hqqzvmi.Q3_K_M.gguf | Q3_K_M | 0.4GB |
| mergekit-ties-hqqzvmi.Q3_K_L.gguf | Q3_K_L | 0.42GB |
| mergekit-ties-hqqzvmi.IQ4_XS.gguf | IQ4_XS | 0.4GB |
| mergekit-ties-hqqzvmi.Q4_0.gguf | Q4_0 | 0.4GB |
| mergekit-ties-hqqzvmi.IQ4_NL.gguf | IQ4_NL | 0.4GB |
| mergekit-ties-hqqzvmi.Q4_K_S.gguf | Q4_K_S | 0.45GB |
| mergekit-ties-hqqzvmi.Q4_K.gguf | Q4_K | 0.46GB |
| mergekit-ties-hqqzvmi.Q4_K_M.gguf | Q4_K_M | 0.46GB |
| mergekit-ties-hqqzvmi.Q4_1.gguf | Q4_1 | 0.43GB |
| mergekit-ties-hqqzvmi.Q5_0.gguf | Q5_0 | 0.46GB |
| mergekit-ties-hqqzvmi.Q5_K_S.gguf | Q5_K_S | 0.48GB |
| mergekit-ties-hqqzvmi.Q5_K.gguf | Q5_K | 0.49GB |
| mergekit-ties-hqqzvmi.Q5_K_M.gguf | Q5_K_M | 0.49GB |
| mergekit-ties-hqqzvmi.Q5_1.gguf | Q5_1 | 0.49GB |
| mergekit-ties-hqqzvmi.Q6_K.gguf | Q6_K | 0.61GB |
| mergekit-ties-hqqzvmi.Q8_0.gguf | Q8_0 | 0.63GB |
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using Qwen/Qwen2.5-Coder-0.5B-Instruct as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Qwen/Qwen2.5-0.5B-Instruct
parameters:
density: 0.5
weight: -0.5
- model: Qwen/Qwen2.5-Coder-0.5B-Instruct
parameters:
density: 0.5
weight: 1.5
merge_method: ties
base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
parameters:
normalize: false
int8_mask: true
dtype: float16