Monero commited on
Commit
4609ffc
1 Parent(s): 1ca7857

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +61 -4
README.md CHANGED
@@ -15,8 +15,10 @@ inference: false
15
 
16
  Converted from the XORs weights from PygmalionAI's release https://huggingface.co/PygmalionAI/metharme-7b
17
 
18
- Quantized for KoboldAI use using https://github.com/0cc4m/GPTQ-for-LLaMa
19
-
 
 
20
 
21
  Metharme 7B is an instruct model based on Meta's LLaMA-7B.
22
 
@@ -85,11 +87,66 @@ As such, it was **not** fine-tuned to be safe and harmless: the base model _and_
85
 
86
  <p><strong><font size="5">Benchmarks</font></strong></p>
87
 
88
- <p><strong><font size="4">This Model:</font> <br><font size="4">4 Bit</font></strong></p>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
 
 
 
 
 
 
 
 
 
 
 
90
  <strong>Wikitext2</strong>: 6.997134685516357
91
 
92
  <strong>Ptb-New</strong>: 58.87525177001953
93
 
94
  <strong>C4-New</strong>: 8.824191093444824
95
- <hr>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
 
16
  Converted from the XORs weights from PygmalionAI's release https://huggingface.co/PygmalionAI/metharme-7b
17
 
18
+ Quantized for KoboldAI use using https://github.com/0cc4m/GPTQ-for-LLaMa
19
+
20
+ I created several quantized variations of this model and believe this variation to be "best."
21
+ <b>Benchmark scores at the bottom of readme.</b>
22
 
23
  Metharme 7B is an instruct model based on Meta's LLaMA-7B.
24
 
 
87
 
88
  <p><strong><font size="5">Benchmarks</font></strong></p>
89
 
90
+ <p><strong><font size="4">This Model:</font> <br><font size="4">4 Bit --Act-order</font></strong></p>
91
+ <strong>Wikitext2</strong>: 6.281311511993408
92
+
93
+ <strong>Ptb-New</strong>: 46.79158401489258
94
+
95
+ <strong>C4-New</strong>: 7.906069755554199
96
+ <hr>
97
+ <p><strong><font size="4">4 Bit --True-Sequential --Groupsize 32</font></strong></p>
98
+ <strong>Wikitext2</strong>: 6.424218654632568
99
+
100
+ <strong>Ptb-New</strong>: 48.48588943481445
101
+
102
+ <strong>C4-New</strong>: 8.089512825012207
103
+ <hr>
104
+ <p><strong><font size="4">4 Bit --Groupsize 32</font></strong></p>
105
+ <strong>Wikitext2</strong>: 6.902080535888672
106
+
107
+ <strong>Ptb-New</strong>: 50.237754821777344
108
+
109
+ <strong>C4-New</strong>: 8.081602096557617
110
+ <hr>
111
+ <p><strong><font size="4">4 Bit --Groupsize 128</font></strong></p>
112
+ <strong>Wikitext2</strong>: 10.206376075744629
113
+
114
+ <strong>Ptb-New</strong>: 49.00401306152344
115
 
116
+ <strong>C4-New</strong>: 8.198845863342285
117
+ <hr>
118
+ <p><strong><font size="4">4 Bit --True-Sequential --Groupsize 128</font></strong></p>
119
+ <strong>Wikitext2</strong>: 9.475017547607422
120
+
121
+ <strong>Ptb-New</strong>: 52.358829498291016
122
+
123
+ <strong>C4-New</strong>: 8.340700149536133
124
+ <hr>
125
+ <p><strong><font size="4">4 Bit</font></strong></p>
126
  <strong>Wikitext2</strong>: 6.997134685516357
127
 
128
  <strong>Ptb-New</strong>: 58.87525177001953
129
 
130
  <strong>C4-New</strong>: 8.824191093444824
131
+ <hr>
132
+ <p><strong><font size="4">4 Bit --True Sequential</font></strong></p>
133
+ <strong>Wikitext2</strong>: 7.735969543457031
134
+
135
+ <strong>Ptb-New</strong>: 62.92238235473633
136
+
137
+ <strong>C4-New</strong>: 8.913650512695312
138
+ <hr>
139
+ <p><strong><font size="4">4 Bit --act-order --groupsize 32</font></strong></p>
140
+ <strong>Wikitext2</strong>: 275425.5
141
+
142
+ <strong>Ptb-New</strong>: 267733.25
143
+
144
+ <strong>C4-New</strong>: 254506.71875
145
+ <hr>
146
+ <p><strong><font size="4">4 Bit --act-order --groupsize 32</font></strong></p>
147
+ <strong>Wikitext2</strong>: 251321.265625
148
+
149
+ <strong>Ptb-New</strong>: 250117.859375
150
+
151
+ <strong>C4-New</strong>: 232929.234375
152
+ <hr>