Downloads · 30 days
50
7% of all-time downloads
SJ-Donald_-_llama3-passthrough-chat-gguf
RichardErkhov/SJ-Donald_-_llama3-passthrough-chat-gguf
SJ-Donald_-_llama3-passthrough-chat-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
744
Public
Repo size
117 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf138 GB · 100%
At a glance
- Access
- Public
- Created
- Nov 9, 2024
- Updated
- Nov 10, 2024
- SHA
- ff284a81
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
llama3-passthrough-chat - GGUF
- Model creator: https://huggingface.co/SJ-Donald/
- Original model: https://huggingface.co/SJ-Donald/llama3-passthrough-chat/
| Name | Quant method | Size |
|---|---|---|
| llama3-passthrough-chat.Q2_K.gguf | Q2_K | 4.16GB |
| llama3-passthrough-chat.Q3_K_S.gguf | Q3_K_S | 4.81GB |
| llama3-passthrough-chat.Q3_K.gguf | Q3_K | 5.3GB |
| llama3-passthrough-chat.Q3_K_M.gguf | Q3_K_M | 5.3GB |
| llama3-passthrough-chat.Q3_K_L.gguf | Q3_K_L | 5.73GB |
| llama3-passthrough-chat.IQ4_XS.gguf | IQ4_XS | 5.93GB |
| llama3-passthrough-chat.Q4_0.gguf | Q4_0 | 6.17GB |
| llama3-passthrough-chat.IQ4_NL.gguf | IQ4_NL | 6.23GB |
| llama3-passthrough-chat.Q4_K_S.gguf | Q4_K_S | 6.21GB |
| llama3-passthrough-chat.Q4_K.gguf | Q4_K | 6.53GB |
| llama3-passthrough-chat.Q4_K_M.gguf | Q4_K_M | 6.53GB |
| llama3-passthrough-chat.Q4_1.gguf | Q4_1 | 6.81GB |
| llama3-passthrough-chat.Q5_0.gguf | Q5_0 | 7.45GB |
| llama3-passthrough-chat.Q5_K_S.gguf | Q5_K_S | 7.45GB |
| llama3-passthrough-chat.Q5_K.gguf | Q5_K | 7.64GB |
| llama3-passthrough-chat.Q5_K_M.gguf | Q5_K_M | 7.64GB |
| llama3-passthrough-chat.Q5_1.gguf | Q5_1 | 8.09GB |
| llama3-passthrough-chat.Q6_K.gguf | Q6_K | 8.81GB |
| llama3-passthrough-chat.Q8_0.gguf | Q8_0 | 11.41GB |
Original model description:
base_model:
- meta-llama/Meta-Llama-3-8B-Instruct library_name: transformers tags:
- mergekit
- merge license: llama3
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:
- model: meta-llama/Meta-Llama-3-8B-Instruct
layer_range: [0, 24]
- sources:
- model: meta-llama/Meta-Llama-3-8B-Instruct
layer_range: [8, 32]
merge_method: passthrough
dtype: float16
- Created
- Nov 9, 2024
- Updated
- Nov 10, 2024