TheBloke commited on
Commit
0e785ba
1 Parent(s): 01bfd1c

Update for Transformers GPTQ support

Browse files
README.md CHANGED
@@ -14,17 +14,20 @@ tags:
14
  ---
15
 
16
  <!-- header start -->
17
- <div style="width: 100%;">
18
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 
19
  </div>
20
  <div style="display: flex; justify-content: space-between; width: 100%;">
21
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
22
- <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
23
  </div>
24
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
25
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
26
  </div>
27
  </div>
 
 
28
  <!-- header end -->
29
 
30
  # Meta's Llama 2 13B-chat GPTQ
@@ -117,7 +120,7 @@ from transformers import AutoTokenizer, pipeline, logging
117
  from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
118
 
119
  model_name_or_path = "TheBloke/Llama-2-13B-chat-GPTQ"
120
- model_basename = "gptq_model-4bit-128g"
121
 
122
  use_triton = False
123
 
@@ -183,6 +186,7 @@ The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLa
183
  ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
184
 
185
  <!-- footer start -->
 
186
  ## Discord
187
 
188
  For further support, and discussions on these models and AI in general, join us at:
@@ -202,12 +206,15 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
202
  * Patreon: https://patreon.com/TheBlokeAI
203
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
204
 
205
- **Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
 
 
206
 
207
- **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.
208
 
209
  Thank you to all my generous patrons and donaters!
210
 
 
 
211
  <!-- footer end -->
212
 
213
  # Original model card: Meta's Llama 2 13B-chat
 
14
  ---
15
 
16
  <!-- header start -->
17
+ <!-- 200823 -->
18
+ <div style="width: auto; margin-left: auto; margin-right: auto">
19
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
20
  </div>
21
  <div style="display: flex; justify-content: space-between; width: 100%;">
22
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
23
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
24
  </div>
25
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
26
+ <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>
27
  </div>
28
  </div>
29
+ <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>
30
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
31
  <!-- header end -->
32
 
33
  # Meta's Llama 2 13B-chat GPTQ
 
120
  from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
121
 
122
  model_name_or_path = "TheBloke/Llama-2-13B-chat-GPTQ"
123
+ model_basename = "model"
124
 
125
  use_triton = False
126
 
 
186
  ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
187
 
188
  <!-- footer start -->
189
+ <!-- 200823 -->
190
  ## Discord
191
 
192
  For further support, and discussions on these models and AI in general, join us at:
 
206
  * Patreon: https://patreon.com/TheBlokeAI
207
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
208
 
209
+ **Special thanks to**: Aemon Algiz.
210
+
211
+ **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
212
 
 
213
 
214
  Thank you to all my generous patrons and donaters!
215
 
216
+ And thank you again to a16z for their generous grant.
217
+
218
  <!-- footer end -->
219
 
220
  # Original model card: Meta's Llama 2 13B-chat
config.json CHANGED
@@ -1,25 +1,36 @@
1
  {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "bos_token_id": 1,
6
- "eos_token_id": 2,
7
- "hidden_act": "silu",
8
- "hidden_size": 5120,
9
- "initializer_range": 0.02,
10
- "intermediate_size": 13824,
11
- "max_length": 4096,
12
- "max_position_embeddings": 4096,
13
- "model_type": "llama",
14
- "num_attention_heads": 40,
15
- "num_hidden_layers": 40,
16
- "num_key_value_heads": 40,
17
- "pad_token_id": 0,
18
- "rms_norm_eps": 1e-05,
19
- "rope_scaling": null,
20
- "tie_word_embeddings": false,
21
- "torch_dtype": "float16",
22
- "transformers_version": "4.30.2",
23
- "use_cache": true,
24
- "vocab_size": 32000
 
 
 
 
 
 
 
 
 
 
 
25
  }
 
1
  {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 5120,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 13824,
11
+ "max_length": 4096,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 40,
16
+ "num_key_value_heads": 40,
17
+ "pad_token_id": 0,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.30.2",
23
+ "use_cache": true,
24
+ "vocab_size": 32000,
25
+ "quantization_config": {
26
+ "bits": 4,
27
+ "group_size": 128,
28
+ "damp_percent": 0.01,
29
+ "desc_act": false,
30
+ "sym": true,
31
+ "true_sequential": true,
32
+ "model_name_or_path": null,
33
+ "model_file_base_name": "model",
34
+ "quant_method": "gptq"
35
+ }
36
  }
gptq_model-4bit-128g.safetensors → model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48c398d528e3a9efe281883e3e69241539c1e2e328106ec570f65f0b95dcfa3a
3
- size 7259449424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:586f4d59cbaa1fc83e34898cd7a650b4d87ab69ef1560a9153628367c96e2dbc
3
+ size 7259449480
quantize_config.json CHANGED
@@ -6,5 +6,5 @@
6
  "sym": true,
7
  "true_sequential": true,
8
  "model_name_or_path": null,
9
- "model_file_base_name": null
10
  }
 
6
  "sym": true,
7
  "true_sequential": true,
8
  "model_name_or_path": null,
9
+ "model_file_base_name": "model"
10
  }