Transformers
GGUF
llama
TheBloke commited on
Commit
c04c28a
1 Parent(s): d22beb2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +38 -0
README.md CHANGED
@@ -112,8 +112,46 @@ Refer to the Provided Files table below to see what files use which methods, and
112
  | [airoboros-l2-70b-2.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/Airoboros-L2-70B-2.1-GGUF/blob/main/airoboros-l2-70b-2.1.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended |
113
  | [airoboros-l2-70b-2.1.Q5_K_S.gguf](https://huggingface.co/TheBloke/Airoboros-L2-70B-2.1-GGUF/blob/main/airoboros-l2-70b-2.1.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
114
  | [airoboros-l2-70b-2.1.Q5_K_M.gguf](https://huggingface.co/TheBloke/Airoboros-L2-70B-2.1-GGUF/blob/main/airoboros-l2-70b-2.1.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended |
 
 
115
 
116
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
117
  <!-- README_GGUF.md-provided-files end -->
118
 
119
  <!-- README_GGUF.md-how-to-run start -->
 
112
  | [airoboros-l2-70b-2.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/Airoboros-L2-70B-2.1-GGUF/blob/main/airoboros-l2-70b-2.1.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended |
113
  | [airoboros-l2-70b-2.1.Q5_K_S.gguf](https://huggingface.co/TheBloke/Airoboros-L2-70B-2.1-GGUF/blob/main/airoboros-l2-70b-2.1.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
114
  | [airoboros-l2-70b-2.1.Q5_K_M.gguf](https://huggingface.co/TheBloke/Airoboros-L2-70B-2.1-GGUF/blob/main/airoboros-l2-70b-2.1.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended |
115
+ | airoboros-l2-70b-2.1.Q6_K.gguf | q6_K | 6 | 56.82 GB | 59.32 GB | very large, extremely low quality loss |
116
+ | airoboros-l2-70b-2.1.Q8_0.gguf | q8_0 | 8 | 73.29 GB | 75.79 GB | very large, extremely low quality loss - not recommended |
117
 
118
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
119
+
120
+ ### Q6_K and Q8_0 files are split and require joining
121
+
122
+ **Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
123
+
124
+ <details>
125
+ <summary>Click for instructions regarding Q6_K and Q8_0 files</summary>
126
+
127
+ ### q6_K
128
+ Please download:
129
+ * `airoboros-l2-70b-2.1.Q6_K.gguf-split-a`
130
+ * `airoboros-l2-70b-2.1.Q6_K.gguf-split-b`
131
+
132
+ ### q8_0
133
+ Please download:
134
+ * `airoboros-l2-70b-2.1.Q8_0.gguf-split-a`
135
+ * `airoboros-l2-70b-2.1.Q8_0.gguf-split-b`
136
+
137
+ To join the files, do the following:
138
+
139
+ Linux and macOS:
140
+ ```
141
+ cat airoboros-l2-70b-2.1.Q6_K.gguf-split-* > airoboros-l2-70b-2.1.Q6_K.gguf && rm airoboros-l2-70b-2.1.Q6_K.gguf-split-*
142
+ cat airoboros-l2-70b-2.1.Q8_0.gguf-split-* > airoboros-l2-70b-2.1.Q8_0.gguf && rm airoboros-l2-70b-2.1.Q8_0.gguf-split-*
143
+ ```
144
+ Windows command line:
145
+ ```
146
+ COPY /B airoboros-l2-70b-2.1.Q6_K.gguf-split-a + airoboros-l2-70b-2.1.Q6_K.gguf-split-b airoboros-l2-70b-2.1.Q6_K.gguf
147
+ del airoboros-l2-70b-2.1.Q6_K.gguf-split-a airoboros-l2-70b-2.1.Q6_K.gguf-split-b
148
+
149
+ COPY /B airoboros-l2-70b-2.1.Q8_0.gguf-split-a + airoboros-l2-70b-2.1.Q8_0.gguf-split-b airoboros-l2-70b-2.1.Q8_0.gguf
150
+ del airoboros-l2-70b-2.1.Q8_0.gguf-split-a airoboros-l2-70b-2.1.Q8_0.gguf-split-b
151
+ ```
152
+
153
+ </details>
154
+
155
  <!-- README_GGUF.md-provided-files end -->
156
 
157
  <!-- README_GGUF.md-how-to-run start -->