TheBloke commited on
Commit
8e86030
1 Parent(s): 482ab4b

Update for Transformers GPTQ support

Browse files
README.md CHANGED
@@ -16,17 +16,20 @@ quantized_by: TheBloke
16
  ---
17
 
18
  <!-- header start -->
19
- <div style="width: 100%;">
20
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 
21
  </div>
22
  <div style="display: flex; justify-content: space-between; width: 100%;">
23
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
24
- <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
25
  </div>
26
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
27
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
28
  </div>
29
  </div>
 
 
30
  <!-- header end -->
31
 
32
  # Orca Mini v3 70B - GPTQ
@@ -80,11 +83,11 @@ All GPTQ files are made with AutoGPTQ.
80
 
81
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
82
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
83
- | [main](https://huggingface.co/TheBloke/orca_mini_v3_70B-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. |
84
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/orca_mini_v3_70B-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. |
85
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/orca_mini_v3_70B-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. |
86
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/orca_mini_v3_70B-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. |
87
- | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/orca_mini_v3_70B-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.77 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
88
  | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/orca_mini_v3_70B-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. |
89
 
90
  ## How to download from branches
@@ -204,6 +207,7 @@ The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLa
204
  ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
205
 
206
  <!-- footer start -->
 
207
  ## Discord
208
 
209
  For further support, and discussions on these models and AI in general, join us at:
@@ -225,11 +229,13 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
225
 
226
  **Special thanks to**: Aemon Algiz.
227
 
228
- **Patreon special mentions**: Ajan Kanaga, David Ziegler, Raymond Fosdick, SuperWojo, Sam, webtim, Steven Wood, knownsqashed, Tony Hughes, Junyu Yang, J, Olakabola, Dan Guido, Stephen Murray, John Villwock, vamX, William Sang, Sean Connelly, LangChain4j, Olusegun Samson, Fen Risland, Derek Yates, Karl Bernard, transmissions 11, Trenton Dambrowitz, Pieter, Preetika Verma, Swaroop Kallakuri, Andrey, Slarti, Jonathan Leane, Michael Levine, Kalila, Joseph William Delisle, Rishabh Srivastava, Deo Leter, Luke Pendergrass, Spencer Kim, Geoffrey Montalvo, Thomas Belote, Jeffrey Morgan, Mandus, ya boyyy, Matthew Berman, Magnesian, Ai Maven, senxiiz, Alps Aficionado, Luke @flexchar, Raven Klaugh, Imad Khwaja, Gabriel Puliatti, Johann-Peter Hartmann, usrbinkat, Spiking Neurons AB, Artur Olbinski, chris gileta, danny, Willem Michiel, WelcomeToTheClub, Deep Realms, alfie_i, Dave, Leonard Tan, NimbleBox.ai, Randy H, Daniel P. Andersen, Pyrater, Will Dee, Elle, Space Cruiser, Gabriel Tamborski, Asp the Wyvern, Illia Dulskyi, Nikolai Manek, Sid, Brandon Frisco, Nathan LeClaire, Edmond Seymore, Enrico Ros, Pedro Madruga, Eugene Pentland, John Detwiler, Mano Prime, Stanislav Ovsiannikov, Alex, Vitor Caleffi, K, biorpg, Michael Davis, Lone Striker, Pierre Kircher, theTransient, Fred von Graf, Sebastain Graf, Vadim, Iucharbius, Clay Pascal, Chadd, Mesiah Bishop, terasurfer, Rainer Wilmers, Alexandros Triantafyllidis, Stefan Sabev, Talal Aujan, Cory Kujawski, Viktor Bowallius, subjectnull, ReadyPlayerEmma, zynix
229
 
230
 
231
  Thank you to all my generous patrons and donaters!
232
 
 
 
233
  <!-- footer end -->
234
 
235
  # Original model card: Pankaj Mathur's Orca Mini v3 70B
@@ -255,7 +261,7 @@ This model is bound by the license & usage restrictions of the original Llama-2
255
 
256
  ## Evaluation
257
 
258
- We evaluated orca_mini_v3_70b on a wide range of tasks using [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) from EleutherAI.
259
 
260
  Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
261
 
@@ -315,9 +321,9 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
315
 
316
  #### Limitations & Biases:
317
 
318
- While this model aims for accuracy, it can occasionally produce inaccurate or misleading results.
319
 
320
- Despite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content.
321
 
322
  Exercise caution and cross-check information when necessary.
323
 
@@ -340,7 +346,7 @@ Please kindly cite using the following BibTeX:
340
 
341
  ```
342
  @misc{mukherjee2023orca,
343
- title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
344
  author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
345
  year={2023},
346
  eprint={2306.02707},
 
16
  ---
17
 
18
  <!-- header start -->
19
+ <!-- 200823 -->
20
+ <div style="width: auto; margin-left: auto; margin-right: auto">
21
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
22
  </div>
23
  <div style="display: flex; justify-content: space-between; width: 100%;">
24
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
25
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
26
  </div>
27
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
28
+ <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>
29
  </div>
30
  </div>
31
+ <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>
32
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
33
  <!-- header end -->
34
 
35
  # Orca Mini v3 70B - GPTQ
 
83
 
84
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
85
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
86
+ | [main](https://huggingface.co/TheBloke/orca_mini_v3_70B-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. |
87
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/orca_mini_v3_70B-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. |
88
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/orca_mini_v3_70B-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. |
89
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/orca_mini_v3_70B-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. |
90
+ | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/orca_mini_v3_70B-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.77 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
91
  | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/orca_mini_v3_70B-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. |
92
 
93
  ## How to download from branches
 
207
  ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
208
 
209
  <!-- footer start -->
210
+ <!-- 200823 -->
211
  ## Discord
212
 
213
  For further support, and discussions on these models and AI in general, join us at:
 
229
 
230
  **Special thanks to**: Aemon Algiz.
231
 
232
+ **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
233
 
234
 
235
  Thank you to all my generous patrons and donaters!
236
 
237
+ And thank you again to a16z for their generous grant.
238
+
239
  <!-- footer end -->
240
 
241
  # Original model card: Pankaj Mathur's Orca Mini v3 70B
 
261
 
262
  ## Evaluation
263
 
264
+ We evaluated orca_mini_v3_70b on a wide range of tasks using [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) from EleutherAI.
265
 
266
  Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
267
 
 
321
 
322
  #### Limitations & Biases:
323
 
324
+ While this model aims for accuracy, it can occasionally produce inaccurate or misleading results.
325
 
326
+ Despite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content.
327
 
328
  Exercise caution and cross-check information when necessary.
329
 
 
346
 
347
  ```
348
  @misc{mukherjee2023orca,
349
+ title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
350
  author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
351
  year={2023},
352
  eprint={2306.02707},
config.json CHANGED
@@ -1,26 +1,37 @@
1
  {
2
- "_name_or_path": "TheBloke/Llama-2-70B-fp16",
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": "4.32.0.dev0",
24
- "use_cache": true,
25
- "vocab_size": 32000
 
 
 
 
 
 
 
 
 
 
 
26
  }
 
1
  {
2
+ "_name_or_path": "TheBloke/Llama-2-70B-fp16",
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": "4.32.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000,
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
  }