Downloads · 30 days
125
3% of all-time downloads
kechengcode_-_Llama3-5B-19Layers-gguf
RichardErkhov/kechengcode_-_Llama3-5B-19Layers-gguf
kechengcode_-_Llama3-5B-19Layers-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
4.2K
Public
Repo size
60.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf70.5 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 23, 2024
- Updated
- Aug 23, 2024
- SHA
- 2f4f945a
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Llama3-5B-19Layers - GGUF
- Model creator: https://huggingface.co/kechengcode/
- Original model: https://huggingface.co/kechengcode/Llama3-5B-19Layers/
| Name | Quant method | Size |
|---|---|---|
| Llama3-5B-19Layers.Q2_K.gguf | Q2_K | 1.99GB |
| Llama3-5B-19Layers.IQ3_XS.gguf | IQ3_XS | 2.2GB |
| Llama3-5B-19Layers.IQ3_S.gguf | IQ3_S | 2.29GB |
| Llama3-5B-19Layers.Q3_K_S.gguf | Q3_K_S | 2.28GB |
| Llama3-5B-19Layers.IQ3_M.gguf | IQ3_M | 2.34GB |
| Llama3-5B-19Layers.Q3_K.gguf | Q3_K | 2.47GB |
| Llama3-5B-19Layers.Q3_K_M.gguf | Q3_K_M | 2.47GB |
| Llama3-5B-19Layers.Q3_K_L.gguf | Q3_K_L | 2.64GB |
| Llama3-5B-19Layers.IQ4_XS.gguf | IQ4_XS | 2.75GB |
| Llama3-5B-19Layers.Q4_0.gguf | Q4_0 | 2.86GB |
| Llama3-5B-19Layers.IQ4_NL.gguf | IQ4_NL | 2.88GB |
| Llama3-5B-19Layers.Q4_K_S.gguf | Q4_K_S | 2.87GB |
| Llama3-5B-19Layers.Q4_K.gguf | Q4_K | 2.99GB |
| Llama3-5B-19Layers.Q4_K_M.gguf | Q4_K_M | 2.99GB |
| Llama3-5B-19Layers.Q4_1.gguf | Q4_1 | 3.13GB |
| Llama3-5B-19Layers.Q5_0.gguf | Q5_0 | 3.4GB |
| Llama3-5B-19Layers.Q5_K_S.gguf | Q5_K_S | 3.4GB |
| Llama3-5B-19Layers.Q5_K.gguf | Q5_K | 3.47GB |
| Llama3-5B-19Layers.Q5_K_M.gguf | Q5_K_M | 3.47GB |
| Llama3-5B-19Layers.Q5_1.gguf | Q5_1 | 3.67GB |
| Llama3-5B-19Layers.Q6_K.gguf | Q6_K | 3.98GB |
| Llama3-5B-19Layers.Q8_0.gguf | Q8_0 | 5.15GB |
Original model description:
base_model: [] 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:
- /home/ke.cheng1/SliceGPT/models/Llama-3-8B
Configuration
The following YAML configuration was used to produce this model:
dtype: float16
merge_method: passthrough
slices:
- sources:
- layer_range: [0, 16]
model: /home/ke.cheng1/SliceGPT/models/Llama-3-8B
- sources:
- layer_range: [29, 32]
model: /home/ke.cheng1/SliceGPT/models/Llama-3-8B
- Created
- Aug 23, 2024
- Updated
- Aug 23, 2024