Transformers
GGUF
English
llama
TheBloke commited on
Commit
cb16f76
1 Parent(s): 9dd1cdd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +38 -0
README.md CHANGED
@@ -114,8 +114,46 @@ Refer to the Provided Files table below to see what files use which methods, and
114
  | [samantha-1.11-70b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.11-70B-GGUF/blob/main/samantha-1.11-70b.Q4_K_M.gguf) | Q4_K_M | 4 | 41.38 GB| 43.88 GB | medium, balanced quality - recommended |
115
  | [samantha-1.11-70b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.11-70B-GGUF/blob/main/samantha-1.11-70b.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
116
  | [samantha-1.11-70b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.11-70B-GGUF/blob/main/samantha-1.11-70b.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - 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
  <!-- README_GGUF.md-provided-files end -->
120
 
121
  <!-- README_GGUF.md-how-to-run start -->
 
114
  | [samantha-1.11-70b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.11-70B-GGUF/blob/main/samantha-1.11-70b.Q4_K_M.gguf) | Q4_K_M | 4 | 41.38 GB| 43.88 GB | medium, balanced quality - recommended |
115
  | [samantha-1.11-70b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Samantha-1.11-70B-GGUF/blob/main/samantha-1.11-70b.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended |
116
  | [samantha-1.11-70b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Samantha-1.11-70B-GGUF/blob/main/samantha-1.11-70b.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended |
117
+ | samantha-1.11-70b.Q6_K.bin | q6_K | 6 | 56.82 GB | 59.32 GB | very large, extremely low quality loss |
118
+ | samantha-1.11-70b.Q8_0.bin | q8_0 | 8 | 73.29 GB | 75.79 GB | very large, extremely low quality loss - not recommended |
119
 
120
  **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.
121
+
122
+ ### Q6_K and Q8_0 files are split and require joining
123
+
124
+ **Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.
125
+
126
+ <details>
127
+ <summary>Click for instructions regarding Q6_K and Q8_0 files</summary>
128
+
129
+ ### q6_K
130
+ Please download:
131
+ * `samantha-1.11-70b.Q6_K.gguf-split-a`
132
+ * `samantha-1.11-70b.Q6_K.gguf-split-b`
133
+
134
+ ### q8_0
135
+ Please download:
136
+ * `samantha-1.11-70b.Q8_0.gguf-split-a`
137
+ * `samantha-1.11-70b.Q8_0.gguf-split-b`
138
+
139
+ To join the files, do the following:
140
+
141
+ Linux and macOS:
142
+ ```
143
+ cat samantha-1.11-70b.Q6_K.gguf-split-* > samantha-1.11-70b.Q6_K.gguf && rm samantha-1.11-70b.Q6_K.gguf-split-*
144
+ cat samantha-1.11-70b.Q8_0.gguf-split-* > samantha-1.11-70b.Q8_0.gguf && rm samantha-1.11-70b.Q8_0.gguf-split-*
145
+ ```
146
+ Windows command line:
147
+ ```
148
+ COPY /B samantha-1.11-70b.Q6_K.gguf-split-a + samantha-1.11-70b.Q6_K.gguf-split-b samantha-1.11-70b.Q6_K.gguf
149
+ del samantha-1.11-70b.Q6_K.gguf-split-a samantha-1.11-70b.Q6_K.gguf-split-b
150
+
151
+ COPY /B samantha-1.11-70b.Q8_0.gguf-split-a + samantha-1.11-70b.Q8_0.gguf-split-b samantha-1.11-70b.Q8_0.gguf
152
+ del samantha-1.11-70b.Q8_0.gguf-split-a samantha-1.11-70b.Q8_0.gguf-split-b
153
+ ```
154
+
155
+ </details>
156
+
157
  <!-- README_GGUF.md-provided-files end -->
158
 
159
  <!-- README_GGUF.md-how-to-run start -->