Downloads · 30 days
220
8% of all-time downloads
kechengcode_-_Qwen2-5B-16Layers-gguf
RichardErkhov/kechengcode_-_Qwen2-5B-16Layers-gguf
kechengcode_-_Qwen2-5B-16Layers-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
2.9K
Public
Repo size
56.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf65.7 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 3, 2024
- Updated
- Oct 4, 2024
- SHA
- 47fdcbef
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Qwen2-5B-16Layers - GGUF
- Model creator: https://huggingface.co/kechengcode/
- Original model: https://huggingface.co/kechengcode/Qwen2-5B-16Layers/
| Name | Quant method | Size |
|---|---|---|
| Qwen2-5B-16Layers.Q2_K.gguf | Q2_K | 1.86GB |
| Qwen2-5B-16Layers.IQ3_XS.gguf | IQ3_XS | 2.06GB |
| Qwen2-5B-16Layers.IQ3_S.gguf | IQ3_S | 2.14GB |
| Qwen2-5B-16Layers.Q3_K_S.gguf | Q3_K_S | 2.13GB |
| Qwen2-5B-16Layers.IQ3_M.gguf | IQ3_M | 2.18GB |
| Qwen2-5B-16Layers.Q3_K.gguf | Q3_K | 2.3GB |
| Qwen2-5B-16Layers.Q3_K_M.gguf | Q3_K_M | 2.3GB |
| Qwen2-5B-16Layers.Q3_K_L.gguf | Q3_K_L | 2.45GB |
| Qwen2-5B-16Layers.IQ4_XS.gguf | IQ4_XS | 2.56GB |
| Qwen2-5B-16Layers.Q4_0.gguf | Q4_0 | 2.66GB |
| Qwen2-5B-16Layers.IQ4_NL.gguf | IQ4_NL | 2.68GB |
| Qwen2-5B-16Layers.Q4_K_S.gguf | Q4_K_S | 2.68GB |
| Qwen2-5B-16Layers.Q4_K.gguf | Q4_K | 2.8GB |
| Qwen2-5B-16Layers.Q4_K_M.gguf | Q4_K_M | 2.8GB |
| Qwen2-5B-16Layers.Q4_1.gguf | Q4_1 | 2.91GB |
| Qwen2-5B-16Layers.Q5_0.gguf | Q5_0 | 3.16GB |
| Qwen2-5B-16Layers.Q5_K_S.gguf | Q5_K_S | 3.16GB |
| Qwen2-5B-16Layers.Q5_K.gguf | Q5_K | 3.23GB |
| Qwen2-5B-16Layers.Q5_K_M.gguf | Q5_K_M | 3.23GB |
| Qwen2-5B-16Layers.Q5_1.gguf | Q5_1 | 3.41GB |
| Qwen2-5B-16Layers.Q6_K.gguf | Q6_K | 3.69GB |
| Qwen2-5B-16Layers.Q8_0.gguf | Q8_0 | 4.77GB |
Original model description:
base_model:
- Qwen/Qwen2-7B library_name: transformers tags:
- mergekit
- merge
merged
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:
dtype: float16
merge_method: passthrough
slices:
- sources:
- layer_range: [0, 10]
model: Qwen/Qwen2-7B
- sources:
- layer_range: [22, 28]
model: Qwen/Qwen2-7B
- Created
- Oct 3, 2024
- Updated
- Oct 4, 2024