TheBloke commited on
Commit
cd603f2
1 Parent(s): e070919

Update for Transformers GPTQ support

Browse files
README.md CHANGED
@@ -10,17 +10,20 @@ tags:
10
  ---
11
 
12
  <!-- header start -->
13
- <div style="width: 100%;">
14
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 
15
  </div>
16
  <div style="display: flex; justify-content: space-between; width: 100%;">
17
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
18
- <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
19
  </div>
20
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
21
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
22
  </div>
23
  </div>
 
 
24
  <!-- header end -->
25
 
26
  # Elinas' Chronos 33B GPTQ
@@ -171,6 +174,7 @@ The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLa
171
  ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
172
 
173
  <!-- footer start -->
 
174
  ## Discord
175
 
176
  For further support, and discussions on these models and AI in general, join us at:
@@ -190,12 +194,15 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
190
  * Patreon: https://patreon.com/TheBlokeAI
191
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
192
 
193
- **Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
 
 
194
 
195
- **Patreon special mentions**: Space Cruiser, Nikolai Manek, Sam, Chris McCloskey, Rishabh Srivastava, Kalila, Spiking Neurons AB, Khalefa Al-Ahmad, WelcomeToTheClub, Chadd, Lone Striker, Viktor Bowallius, Edmond Seymore, Ai Maven, Chris Smitley, Dave, Alexandros Triantafyllidis, Luke @flexchar, Elle, ya boyyy, Talal Aujan, Alex , Jonathan Leane, Deep Realms, Randy H, subjectnull, Preetika Verma, Joseph William Delisle, Michael Levine, chris gileta, K, Oscar Rangel, LangChain4j, Trenton Dambrowitz, Eugene Pentland, Johann-Peter Hartmann, Femi Adebogun, Illia Dulskyi, senxiiz, Daniel P. Andersen, Sean Connelly, Artur Olbinski, RoA, Mano Prime, Derek Yates, Raven Klaugh, David Flickinger, Willem Michiel, Pieter, Willian Hasse, vamX, Luke Pendergrass, webtim, Ghost , Rainer Wilmers, Nathan LeClaire, Will Dee, Cory Kujawski, John Detwiler, Fred von Graf, biorpg, Iucharbius , Imad Khwaja, Pierre Kircher, terasurfer , Asp the Wyvern, John Villwock, theTransient, zynix , Gabriel Tamborski, Fen Risland, Gabriel Puliatti, Matthew Berman, Pyrater, SuperWojo, Stephen Murray, Karl Bernard, Ajan Kanaga, Greatston Gnanesh, Junyu Yang.
196
 
197
  Thank you to all my generous patrons and donaters!
198
 
 
 
199
  <!-- footer end -->
200
 
201
  # Original model card: Elinas' Chronos 33B
@@ -221,7 +228,7 @@ Your instruction or question here.
221
  [4bit GPTQ Version provided by @TheBloke](https://huggingface.co/TheBloke/chronos-33b-GPTQ)
222
 
223
  <!--**Support My Development of New Models**
224
- <a href='https://ko-fi.com/Q5Q6MB734' target='_blank'><img height='36' style='border:0px;height:36px;'
225
  src='https://storage.ko-fi.com/cdn/kofi1.png?v=3' border='0' alt='Support Development' /></a>-->
226
 
227
  --
@@ -304,11 +311,11 @@ Hyperparameters for the model architecture
304
  </tr>
305
  <tr>
306
  <th>Number of parameters</th><th>dimension</th><th>n heads</th><th>n layers</th><th>Learn rate</th><th>Batch size</th><th>n tokens</th>
307
- </tr>
308
  </thead>
309
- <tbody>
310
  <tr>
311
- <th>7B</th> <th>4096</th> <th>32</th> <th>32</th> <th>3.0E-04</th><th>4M</th><th>1T
312
  </tr>
313
  <tr>
314
  <th>13B</th><th>5120</th><th>40</th><th>40</th><th>3.0E-04</th><th>4M</th><th>1T
@@ -318,13 +325,13 @@ Hyperparameters for the model architecture
318
  </tr>
319
  <tr>
320
  <th>65B</th><th>8192</th><th>64</th><th>80</th><th>1.5.E-04</th><th>4M</th><th>1.4T
321
- </tr>
322
  </tbody>
323
  </table>
324
 
325
  *Table 1 - Summary of LLama Model Hyperparameters*
326
 
327
- We present our results on eight standard common sense reasoning benchmarks in the table below.
328
  <table>
329
  <thead>
330
  <tr>
@@ -332,23 +339,23 @@ We present our results on eight standard common sense reasoning benchmarks in th
332
  </tr>
333
  <tr>
334
  <th>Number of parameters</th> <th>BoolQ</th><th>PIQA</th><th>SIQA</th><th>HellaSwag</th><th>WinoGrande</th><th>ARC-e</th><th>ARC-c</th><th>OBQA</th><th>COPA</th>
335
- </tr>
336
  </thead>
337
- <tbody>
338
- <tr>
339
  <th>7B</th><th>76.5</th><th>79.8</th><th>48.9</th><th>76.1</th><th>70.1</th><th>76.7</th><th>47.6</th><th>57.2</th><th>93
340
- </th>
341
  <tr><th>13B</th><th>78.1</th><th>80.1</th><th>50.4</th><th>79.2</th><th>73</th><th>78.1</th><th>52.7</th><th>56.4</th><th>94
342
  </th>
343
  <tr><th>33B</th><th>83.1</th><th>82.3</th><th>50.4</th><th>82.8</th><th>76</th><th>81.4</th><th>57.8</th><th>58.6</th><th>92
344
  </th>
345
- <tr><th>65B</th><th>85.3</th><th>82.8</th><th>52.3</th><th>84.2</th><th>77</th><th>81.5</th><th>56</th><th>60.2</th><th>94</th></tr>
346
  </tbody>
347
  </table>
348
  *Table 2 - Summary of LLama Model Performance on Reasoning tasks*
349
 
350
 
351
- We present our results on bias in the table below. Note that lower value is better indicating lower bias.
352
 
353
 
354
  | No | Category | FAIR LLM |
 
10
  ---
11
 
12
  <!-- header start -->
13
+ <!-- 200823 -->
14
+ <div style="width: auto; margin-left: auto; margin-right: auto">
15
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
16
  </div>
17
  <div style="display: flex; justify-content: space-between; width: 100%;">
18
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
19
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
20
  </div>
21
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
22
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
23
  </div>
24
  </div>
25
+ <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
26
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
27
  <!-- header end -->
28
 
29
  # Elinas' Chronos 33B GPTQ
 
174
  ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
175
 
176
  <!-- footer start -->
177
+ <!-- 200823 -->
178
  ## Discord
179
 
180
  For further support, and discussions on these models and AI in general, join us at:
 
194
  * Patreon: https://patreon.com/TheBlokeAI
195
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
196
 
197
+ **Special thanks to**: Aemon Algiz.
198
+
199
+ **Patreon special mentions**: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
200
 
 
201
 
202
  Thank you to all my generous patrons and donaters!
203
 
204
+ And thank you again to a16z for their generous grant.
205
+
206
  <!-- footer end -->
207
 
208
  # Original model card: Elinas' Chronos 33B
 
228
  [4bit GPTQ Version provided by @TheBloke](https://huggingface.co/TheBloke/chronos-33b-GPTQ)
229
 
230
  <!--**Support My Development of New Models**
231
+ <a href='https://ko-fi.com/Q5Q6MB734' target='_blank'><img height='36' style='border:0px;height:36px;'
232
  src='https://storage.ko-fi.com/cdn/kofi1.png?v=3' border='0' alt='Support Development' /></a>-->
233
 
234
  --
 
311
  </tr>
312
  <tr>
313
  <th>Number of parameters</th><th>dimension</th><th>n heads</th><th>n layers</th><th>Learn rate</th><th>Batch size</th><th>n tokens</th>
314
+ </tr>
315
  </thead>
316
+ <tbody>
317
  <tr>
318
+ <th>7B</th> <th>4096</th> <th>32</th> <th>32</th> <th>3.0E-04</th><th>4M</th><th>1T
319
  </tr>
320
  <tr>
321
  <th>13B</th><th>5120</th><th>40</th><th>40</th><th>3.0E-04</th><th>4M</th><th>1T
 
325
  </tr>
326
  <tr>
327
  <th>65B</th><th>8192</th><th>64</th><th>80</th><th>1.5.E-04</th><th>4M</th><th>1.4T
328
+ </tr>
329
  </tbody>
330
  </table>
331
 
332
  *Table 1 - Summary of LLama Model Hyperparameters*
333
 
334
+ We present our results on eight standard common sense reasoning benchmarks in the table below.
335
  <table>
336
  <thead>
337
  <tr>
 
339
  </tr>
340
  <tr>
341
  <th>Number of parameters</th> <th>BoolQ</th><th>PIQA</th><th>SIQA</th><th>HellaSwag</th><th>WinoGrande</th><th>ARC-e</th><th>ARC-c</th><th>OBQA</th><th>COPA</th>
342
+ </tr>
343
  </thead>
344
+ <tbody>
345
+ <tr>
346
  <th>7B</th><th>76.5</th><th>79.8</th><th>48.9</th><th>76.1</th><th>70.1</th><th>76.7</th><th>47.6</th><th>57.2</th><th>93
347
+ </th>
348
  <tr><th>13B</th><th>78.1</th><th>80.1</th><th>50.4</th><th>79.2</th><th>73</th><th>78.1</th><th>52.7</th><th>56.4</th><th>94
349
  </th>
350
  <tr><th>33B</th><th>83.1</th><th>82.3</th><th>50.4</th><th>82.8</th><th>76</th><th>81.4</th><th>57.8</th><th>58.6</th><th>92
351
  </th>
352
+ <tr><th>65B</th><th>85.3</th><th>82.8</th><th>52.3</th><th>84.2</th><th>77</th><th>81.5</th><th>56</th><th>60.2</th><th>94</th></tr>
353
  </tbody>
354
  </table>
355
  *Table 2 - Summary of LLama Model Performance on Reasoning tasks*
356
 
357
 
358
+ We present our results on bias in the table below. Note that lower value is better indicating lower bias.
359
 
360
 
361
  | No | Category | FAIR LLM |
config.json CHANGED
@@ -1,23 +1,33 @@
1
  {
2
- "_name_or_path": "elinas/llama-30b-hf-transformers-4.29",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "bos_token_id": 1,
7
- "eos_token_id": 2,
8
- "hidden_act": "silu",
9
- "hidden_size": 6656,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 17920,
12
- "max_position_embeddings": 2048,
13
- "model_type": "llama",
14
- "num_attention_heads": 52,
15
- "num_hidden_layers": 60,
16
- "pad_token_id": 0,
17
- "rms_norm_eps": 1e-06,
18
- "tie_word_embeddings": false,
19
- "torch_dtype": "float16",
20
- "transformers_version": "4.28.1",
21
- "use_cache": true,
22
- "vocab_size": 32000
 
 
 
 
 
 
 
 
 
 
23
  }
 
1
  {
2
+ "_name_or_path": "elinas/llama-30b-hf-transformers-4.29",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 6656,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 17920,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 52,
15
+ "num_hidden_layers": 60,
16
+ "pad_token_id": 0,
17
+ "rms_norm_eps": 1e-06,
18
+ "tie_word_embeddings": false,
19
+ "torch_dtype": "float16",
20
+ "transformers_version": "4.28.1",
21
+ "use_cache": true,
22
+ "vocab_size": 32000,
23
+ "quantization_config": {
24
+ "bits": 4,
25
+ "group_size": -1,
26
+ "damp_percent": 0.01,
27
+ "desc_act": true,
28
+ "sym": true,
29
+ "true_sequential": true,
30
+ "model_file_base_name": "model",
31
+ "quant_method": "gptq"
32
+ }
33
  }
chronos-33b-GPTQ-4bit--1g.act.order.safetensors → model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:025262e9334c4afdb8ca7b1e4b1b173061374958cc26b1561e950a1887b0d6f2
3
- size 16940128408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:762600649e5e909640a6cbbb4e8ce1796977b3ae9dc8788cbeddbd3b93178c47
3
+ size 16940128464
quantize_config.json CHANGED
@@ -1,8 +1,9 @@
1
  {
2
- "bits": 4,
3
- "group_size": -1,
4
- "damp_percent": 0.01,
5
- "desc_act": true,
6
- "sym": true,
7
- "true_sequential": true
 
8
  }
 
1
  {
2
+ "bits": 4,
3
+ "group_size": -1,
4
+ "damp_percent": 0.01,
5
+ "desc_act": true,
6
+ "sym": true,
7
+ "true_sequential": true,
8
+ "model_file_base_name": "model"
9
  }