Downloads · 30 days
81
13% of all-time downloads
RichardErkhov/appvoid_-_arco-chat-merged-gguf
appvoid_-_arco-chat-merged-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
81
13% of all-time downloads
All-time downloads
633
Public
Repo size
5.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf7 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
arco-chat-merged - GGUF
| Name | Quant method | Size |
|---|---|---|
| arco-chat-merged.Q2_K.gguf | Q2_K | 0.2GB |
| arco-chat-merged.IQ3_XS.gguf | IQ3_XS | 0.22GB |
| arco-chat-merged.IQ3_S.gguf | IQ3_S | 0.22GB |
| arco-chat-merged.Q3_K_S.gguf | Q3_K_S | 0.22GB |
| arco-chat-merged.IQ3_M.gguf | IQ3_M | 0.23GB |
| arco-chat-merged.Q3_K.gguf | Q3_K | 0.24GB |
| arco-chat-merged.Q3_K_M.gguf | Q3_K_M | 0.24GB |
| arco-chat-merged.Q3_K_L.gguf | Q3_K_L | 0.26GB |
| arco-chat-merged.IQ4_XS.gguf | IQ4_XS | 0.27GB |
| arco-chat-merged.Q4_0.gguf | Q4_0 | 0.28GB |
| arco-chat-merged.IQ4_NL.gguf | IQ4_NL | 0.28GB |
| arco-chat-merged.Q4_K_S.gguf | Q4_K_S | 0.28GB |
| arco-chat-merged.Q4_K.gguf | Q4_K | 0.3GB |
| arco-chat-merged.Q4_K_M.gguf | Q4_K_M | 0.3GB |
| arco-chat-merged.Q4_1.gguf | Q4_1 | 0.31GB |
| arco-chat-merged.Q5_0.gguf | Q5_0 | 0.34GB |
| arco-chat-merged.Q5_K_S.gguf | Q5_K_S | 0.34GB |
| arco-chat-merged.Q5_K.gguf | Q5_K | 0.34GB |
| arco-chat-merged.Q5_K_M.gguf | Q5_K_M | 0.34GB |
| arco-chat-merged.Q5_1.gguf | Q5_1 | 0.36GB |
| arco-chat-merged.Q6_K.gguf | Q6_K | 0.39GB |
| arco-chat-merged.Q8_0.gguf | Q8_0 | 0.51GB |
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: appvoid/arco-chat-v0.1
- model: appvoid/arco
merge_method: slerp
base_model: appvoid/arco-chat-v0.1
dtype: float16
parameters:
t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers