TheBloke commited on
Commit
c234d7c
1 Parent(s): d8dd072

Update for Transformers GPTQ support

Browse files
README.md CHANGED
@@ -9,17 +9,20 @@ quantized_by: TheBloke
9
  ---
10
 
11
  <!-- header start -->
12
- <div style="width: 100%;">
13
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 
14
  </div>
15
  <div style="display: flex; justify-content: space-between; width: 100%;">
16
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
17
- <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
18
  </div>
19
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
20
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
21
  </div>
22
  </div>
 
 
23
  <!-- header end -->
24
 
25
  # WizardLM 70B V1.0 - GPTQ
@@ -67,11 +70,11 @@ All GPTQ files are made with AutoGPTQ.
67
 
68
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
69
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
70
- | [main](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 35.33 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
71
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 40.66 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
72
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 37.99 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
73
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 36.65 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
74
- | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.78 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
75
  | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 28.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
76
 
77
  ## How to download from branches
@@ -185,6 +188,7 @@ The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLa
185
  ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
186
 
187
  <!-- footer start -->
 
188
  ## Discord
189
 
190
  For further support, and discussions on these models and AI in general, join us at:
@@ -204,13 +208,15 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
204
  * Patreon: https://patreon.com/TheBlokeAI
205
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
206
 
207
- **Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
208
 
209
- **Patreon special mentions**: Willem Michiel, Ajan Kanaga, Cory Kujawski, Alps Aficionado, Nikolai Manek, Jonathan Leane, Stanislav Ovsiannikov, Michael Levine, Luke Pendergrass, Sid, K, Gabriel Tamborski, Clay Pascal, Kalila, William Sang, Will Dee, Pieter, Nathan LeClaire, ya boyyy, David Flickinger, vamX, Derek Yates, Fen Risland, Jeffrey Morgan, webtim, Daniel P. Andersen, Chadd, Edmond Seymore, Pyrater, Olusegun Samson, Lone Striker, biorpg, alfie_i, Mano Prime, Chris Smitley, Dave, zynix, Trenton Dambrowitz, Johann-Peter Hartmann, Magnesian, Spencer Kim, John Detwiler, Iucharbius, Gabriel Puliatti, LangChain4j, Luke @flexchar, Vadim, Rishabh Srivastava, Preetika Verma, Ai Maven, Femi Adebogun, WelcomeToTheClub, Leonard Tan, Imad Khwaja, Steven Wood, Stefan Sabev, Sebastain Graf, usrbinkat, Dan Guido, Sam, Eugene Pentland, Mandus, transmissions 11, Slarti, Karl Bernard, Spiking Neurons AB, Artur Olbinski, Joseph William Delisle, ReadyPlayerEmma, Olakabola, Asp the Wyvern, Space Cruiser, Matthew Berman, Randy H, subjectnull, danny, John Villwock, Illia Dulskyi, Rainer Wilmers, theTransient, Pierre Kircher, Alexandros Triantafyllidis, Viktor Bowallius, terasurfer, Deep Realms, SuperWojo, senxiiz, Oscar Rangel, Alex, Stephen Murray, Talal Aujan, Raven Klaugh, Sean Connelly, Raymond Fosdick, Fred von Graf, chris gileta, Junyu Yang, Elle
210
 
211
 
212
  Thank you to all my generous patrons and donaters!
213
 
 
 
214
  <!-- footer end -->
215
 
216
  # Original model card: WizardLM's WizardLM 70B V1.0
@@ -230,9 +236,9 @@ Thank you to all my generous patrons and donaters!
230
 
231
 
232
  <font size=4>
233
-
234
  | <sup>Model</sup> | <sup>Checkpoint</sup> | <sup>Paper</sup> |<sup>MT-Bench</sup> | <sup>AlpacaEval</sup> | <sup>GSM8k</sup> | <sup>HumanEval</sup> | <sup>License</sup>|
235
- | ----- |------| ---- |------|-------| ----- | ----- | ----- |
236
  | <sup>**WizardLM-70B-V1.0**</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-70B-V1.0" target="_blank">HF Link</a> </sup>|<sup>📃**Coming Soon**</sup>| <sup>**7.78**</sup> | <sup>**92.91%**</sup> |<sup>**77.6%**</sup> | <sup> **50.6 pass@1**</sup>|<sup> <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License </a></sup> |
237
  | <sup>WizardLM-13B-V1.2</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.2" target="_blank">HF Link</a> </sup>| | <sup>7.06</sup> | <sup>89.17%</sup> |<sup>55.3%</sup> | <sup>36.6 pass@1</sup>|<sup> <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License </a></sup> |
238
  | <sup>WizardLM-13B-V1.1</sup> |<sup> 🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.1" target="_blank">HF Link</a> </sup> | | <sup>6.76</sup> |<sup>86.32%</sup> | | <sup>25.0 pass@1</sup>| <sup>Non-commercial</sup>|
@@ -258,5 +264,5 @@ Thank you to all my generous patrons and donaters!
258
  <b>WizardLM</b> adopts the prompt format from <b>Vicuna</b> and supports **multi-turn** conversation. The prompt should be as following:
259
 
260
  ```
261
- A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: hello, who are you? ASSISTANT:
262
  ```
 
9
  ---
10
 
11
  <!-- header start -->
12
+ <!-- 200823 -->
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
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 style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
19
  </div>
20
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
21
+ <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>
22
  </div>
23
  </div>
24
+ <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>
25
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
26
  <!-- header end -->
27
 
28
  # WizardLM 70B V1.0 - GPTQ
 
70
 
71
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
72
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
73
+ | [main](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 35.33 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
74
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 40.66 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
75
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 37.99 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
76
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 36.65 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
77
+ | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.78 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
78
  | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/WizardLM-70B-V1.0-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 28.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
79
 
80
  ## How to download from branches
 
188
  ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
189
 
190
  <!-- footer start -->
191
+ <!-- 200823 -->
192
  ## Discord
193
 
194
  For further support, and discussions on these models and AI in general, join us at:
 
208
  * Patreon: https://patreon.com/TheBlokeAI
209
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
210
 
211
+ **Special thanks to**: Aemon Algiz.
212
 
213
+ **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
214
 
215
 
216
  Thank you to all my generous patrons and donaters!
217
 
218
+ And thank you again to a16z for their generous grant.
219
+
220
  <!-- footer end -->
221
 
222
  # Original model card: WizardLM's WizardLM 70B V1.0
 
236
 
237
 
238
  <font size=4>
239
+
240
  | <sup>Model</sup> | <sup>Checkpoint</sup> | <sup>Paper</sup> |<sup>MT-Bench</sup> | <sup>AlpacaEval</sup> | <sup>GSM8k</sup> | <sup>HumanEval</sup> | <sup>License</sup>|
241
+ | ----- |------| ---- |------|-------| ----- | ----- | ----- |
242
  | <sup>**WizardLM-70B-V1.0**</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-70B-V1.0" target="_blank">HF Link</a> </sup>|<sup>📃**Coming Soon**</sup>| <sup>**7.78**</sup> | <sup>**92.91%**</sup> |<sup>**77.6%**</sup> | <sup> **50.6 pass@1**</sup>|<sup> <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License </a></sup> |
243
  | <sup>WizardLM-13B-V1.2</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.2" target="_blank">HF Link</a> </sup>| | <sup>7.06</sup> | <sup>89.17%</sup> |<sup>55.3%</sup> | <sup>36.6 pass@1</sup>|<sup> <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License </a></sup> |
244
  | <sup>WizardLM-13B-V1.1</sup> |<sup> 🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.1" target="_blank">HF Link</a> </sup> | | <sup>6.76</sup> |<sup>86.32%</sup> | | <sup>25.0 pass@1</sup>| <sup>Non-commercial</sup>|
 
264
  <b>WizardLM</b> adopts the prompt format from <b>Vicuna</b> and supports **multi-turn** conversation. The prompt should be as following:
265
 
266
  ```
267
+ A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: hello, who are you? ASSISTANT:
268
  ```
config.json CHANGED
@@ -1,26 +1,37 @@
1
  {
2
- "_name_or_path": "/home/aiscuser/Llama-2-70b-chat-hf",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "bos_token_id": 1,
7
- "eos_token_id": 2,
8
- "hidden_act": "silu",
9
- "hidden_size": 8192,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 28672,
12
- "max_position_embeddings": 4096,
13
- "model_type": "llama",
14
- "num_attention_heads": 64,
15
- "num_hidden_layers": 80,
16
- "num_key_value_heads": 8,
17
- "pad_token_id": 0,
18
- "pretraining_tp": 1,
19
- "rms_norm_eps": 1e-05,
20
- "rope_scaling": null,
21
- "tie_word_embeddings": false,
22
- "torch_dtype": "float16",
23
- "transformers_version": "4.31.0",
24
- "use_cache": true,
25
- "vocab_size": 32001
 
 
 
 
 
 
 
 
 
 
 
26
  }
 
1
  {
2
+ "_name_or_path": "/home/aiscuser/Llama-2-70b-chat-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 8192,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 28672,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 64,
15
+ "num_hidden_layers": 80,
16
+ "num_key_value_heads": 8,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32001,
26
+ "quantization_config": {
27
+ "bits": 4,
28
+ "group_size": -1,
29
+ "damp_percent": 0.1,
30
+ "desc_act": true,
31
+ "sym": true,
32
+ "true_sequential": true,
33
+ "model_name_or_path": null,
34
+ "model_file_base_name": "model",
35
+ "quant_method": "gptq"
36
+ }
37
  }
gptq_model-4bit--1g.safetensors → model.safetensors RENAMED
File without changes
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
  }