Transformers
GGUF
English
quantized
roleplay
imatrix
mistral
Merge
Eval Results
Lewdiculous commited on
Commit
7d9e390
1 Parent(s): 38b8619

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -10,7 +10,6 @@ tags:
10
  - imatrix
11
  - mistral
12
  - merge
13
- - nsfw
14
  inference: false
15
  datasets:
16
  - ResplendentAI/Alpaca_NSFW_Shuffled
@@ -126,7 +125,7 @@ This repository hosts GGUF-Imatrix quantizations for [ResplendentAI/Sinerva_7B](
126
  ```
127
  Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
128
  ```
129
- To be uploaded:
130
  ```python
131
  quantization_options = [
132
  "Q4_K_M", "IQ4_XS", "Q5_K_M", "Q5_K_S", "Q6_K",
@@ -134,6 +133,8 @@ To be uploaded:
134
  ]
135
  ```
136
 
 
 
137
  **This is experimental.**
138
 
139
  For imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay chats was used, you can find it [here](https://huggingface.co/Lewdiculous/Datura_7B-GGUF-Imatrix/blob/main/imatrix-with-rp-format-data.txt).
 
10
  - imatrix
11
  - mistral
12
  - merge
 
13
  inference: false
14
  datasets:
15
  - ResplendentAI/Alpaca_NSFW_Shuffled
 
125
  ```
126
  Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
127
  ```
128
+ Quants:
129
  ```python
130
  quantization_options = [
131
  "Q4_K_M", "IQ4_XS", "Q5_K_M", "Q5_K_S", "Q6_K",
 
133
  ]
134
  ```
135
 
136
+ If you want anything that's not here or another model, feel free to request.
137
+
138
  **This is experimental.**
139
 
140
  For imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay chats was used, you can find it [here](https://huggingface.co/Lewdiculous/Datura_7B-GGUF-Imatrix/blob/main/imatrix-with-rp-format-data.txt).