TheBloke commited on
Commit
4ea5b5a
1 Parent(s): aae25c3

Update for Transformers GPTQ support

Browse files
README.md CHANGED
@@ -4,17 +4,20 @@ license: other
4
  ---
5
 
6
  <!-- header start -->
7
- <div style="width: 100%;">
8
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 
9
  </div>
10
  <div style="display: flex; justify-content: space-between; width: 100%;">
11
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
12
- <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
13
  </div>
14
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
15
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
16
  </div>
17
  </div>
 
 
18
  <!-- header end -->
19
 
20
  # Lilloukas' GPlatty 30B GPTQ
@@ -148,6 +151,7 @@ It was created without group_size to lower VRAM requirements, and with --act-ord
148
  * Parameters: Groupsize = -1. Act Order / desc_act = True.
149
 
150
  <!-- footer start -->
 
151
  ## Discord
152
 
153
  For further support, and discussions on these models and AI in general, join us at:
@@ -167,12 +171,15 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
167
  * Patreon: https://patreon.com/TheBlokeAI
168
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
169
 
170
- **Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
 
 
171
 
172
- **Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
173
 
174
  Thank you to all my generous patrons and donaters!
175
 
 
 
176
  <!-- footer end -->
177
 
178
  # Original model card: Kaio Ken's SuperHOT 8K
@@ -220,7 +227,7 @@ GPlatty-30B is a merge of [lilloukas/Platypus-30B](https://huggingface.co/lillou
220
  | ARC (25-shot) | 66.0 |
221
  | HellaSwag (10-shot) | 84.8 |
222
  | TruthfulQA (0-shot) | 53.8 |
223
- | Avg. | 67.0 |
224
 
225
  We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above.
226
 
 
4
  ---
5
 
6
  <!-- header start -->
7
+ <!-- 200823 -->
8
+ <div style="width: auto; margin-left: auto; margin-right: auto">
9
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
10
  </div>
11
  <div style="display: flex; justify-content: space-between; width: 100%;">
12
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
13
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
14
  </div>
15
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
16
+ <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>
17
  </div>
18
  </div>
19
+ <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>
20
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
21
  <!-- header end -->
22
 
23
  # Lilloukas' GPlatty 30B GPTQ
 
151
  * Parameters: Groupsize = -1. Act Order / desc_act = True.
152
 
153
  <!-- footer start -->
154
+ <!-- 200823 -->
155
  ## Discord
156
 
157
  For further support, and discussions on these models and AI in general, join us at:
 
171
  * Patreon: https://patreon.com/TheBlokeAI
172
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
173
 
174
+ **Special thanks to**: Aemon Algiz.
175
+
176
+ **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
177
 
 
178
 
179
  Thank you to all my generous patrons and donaters!
180
 
181
+ And thank you again to a16z for their generous grant.
182
+
183
  <!-- footer end -->
184
 
185
  # Original model card: Kaio Ken's SuperHOT 8K
 
227
  | ARC (25-shot) | 66.0 |
228
  | HellaSwag (10-shot) | 84.8 |
229
  | TruthfulQA (0-shot) | 53.8 |
230
+ | Avg. | 67.0 |
231
 
232
  We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above.
233
 
config.json CHANGED
@@ -1,28 +1,38 @@
1
  {
2
- "_name_or_path": "/workspace/superhot_process/gplatty-30b/source",
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": 8192,
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": "4.30.0.dev0",
21
- "use_cache": true,
22
- "vocab_size": 32000,
23
- "auto_map": {
24
- "AutoModel": "modelling_llama.LlamaModel",
25
- "AutoModelForCausalLM": "modelling_llama.LlamaForCausalLM",
26
- "AutoModelForSequenceClassification": "modelling_llama.LlamaForSequenceClassification"
27
- }
 
 
 
 
 
 
 
 
 
 
28
  }
 
1
  {
2
+ "_name_or_path": "/workspace/superhot_process/gplatty-30b/source",
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": 8192,
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": "4.30.0.dev0",
21
+ "use_cache": true,
22
+ "vocab_size": 32000,
23
+ "auto_map": {
24
+ "AutoModel": "modelling_llama.LlamaModel",
25
+ "AutoModelForCausalLM": "modelling_llama.LlamaForCausalLM",
26
+ "AutoModelForSequenceClassification": "modelling_llama.LlamaForSequenceClassification"
27
+ },
28
+ "quantization_config": {
29
+ "bits": 4,
30
+ "group_size": -1,
31
+ "damp_percent": 0.01,
32
+ "desc_act": true,
33
+ "sym": true,
34
+ "true_sequential": true,
35
+ "model_file_base_name": "model",
36
+ "quant_method": "gptq"
37
+ }
38
  }
gplatty-30b-superhot-8k-GPTQ-4bit--1g.act.order.safetensors → model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36ac463e591cccd6547053b555fcc1030e12d2a3833ce6c2b892e0bc9f3f2f89
3
- size 16940128408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99020bc5eeec25bd7657cdea85ea0eb3d48eb40003d1ede3a009e4bb962b6c82
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
  }