Downloads · 30 days
86
12% of all-time downloads
djuna_-_Qwen2-2B-RHSD-gguf
RichardErkhov/djuna_-_Qwen2-2B-RHSD-gguf
djuna_-_Qwen2-2B-RHSD-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.
All-time downloads
719
Public
Repo size
28.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf33 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 3, 2024
- Updated
- Oct 4, 2024
- SHA
- 54c1c193
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Qwen2-2B-RHSD - GGUF
- Model creator: https://huggingface.co/djuna/
- Original model: https://huggingface.co/djuna/Qwen2-2B-RHSD/
| Name | Quant method | Size |
|---|---|---|
| Qwen2-2B-RHSD.Q2_K.gguf | Q2_K | 0.92GB |
| Qwen2-2B-RHSD.IQ3_XS.gguf | IQ3_XS | 1.02GB |
| Qwen2-2B-RHSD.IQ3_S.gguf | IQ3_S | 1.07GB |
| Qwen2-2B-RHSD.Q3_K_S.gguf | Q3_K_S | 1.06GB |
| Qwen2-2B-RHSD.IQ3_M.gguf | IQ3_M | 1.09GB |
| Qwen2-2B-RHSD.Q3_K.gguf | Q3_K | 1.15GB |
| Qwen2-2B-RHSD.Q3_K_M.gguf | Q3_K_M | 1.15GB |
| Qwen2-2B-RHSD.Q3_K_L.gguf | Q3_K_L | 1.23GB |
| Qwen2-2B-RHSD.IQ4_XS.gguf | IQ4_XS | 1.28GB |
| Qwen2-2B-RHSD.Q4_0.gguf | Q4_0 | 1.34GB |
| Qwen2-2B-RHSD.IQ4_NL.gguf | IQ4_NL | 1.35GB |
| Qwen2-2B-RHSD.Q4_K_S.gguf | Q4_K_S | 1.34GB |
| Qwen2-2B-RHSD.Q4_K.gguf | Q4_K | 1.41GB |
| Qwen2-2B-RHSD.Q4_K_M.gguf | Q4_K_M | 1.41GB |
| Qwen2-2B-RHSD.Q4_1.gguf | Q4_1 | 1.46GB |
| Qwen2-2B-RHSD.Q5_0.gguf | Q5_0 | 1.59GB |
| Qwen2-2B-RHSD.Q5_K_S.gguf | Q5_K_S | 1.59GB |
| Qwen2-2B-RHSD.Q5_K.gguf | Q5_K | 1.63GB |
| Qwen2-2B-RHSD.Q5_K_M.gguf | Q5_K_M | 1.63GB |
| Qwen2-2B-RHSD.Q5_1.gguf | Q5_1 | 1.72GB |
| Qwen2-2B-RHSD.Q6_K.gguf | Q6_K | 1.86GB |
| Qwen2-2B-RHSD.Q8_0.gguf | Q8_0 | 2.41GB |
Original model description:
base_model:
- mergekit-community/Qwen2-1.5B-RHSD library_name: transformers tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- layer_range: [0, 14]
model: mergekit-community/Qwen2-1.5B-RHSD
- sources:
- layer_range: [7, 21]
model: mergekit-community/Qwen2-1.5B-RHSD
- sources:
- layer_range: [14, 28]
model: mergekit-community/Qwen2-1.5B-RHSD
merge_method: passthrough
dtype: bfloat16
- Created
- Oct 3, 2024
- Updated
- Oct 4, 2024