TheBloke commited on
Commit
59bf227
1 Parent(s): f27cb4f

Update for Transformers GPTQ support

Browse files
README.md CHANGED
@@ -11,17 +11,20 @@ quantized_by: TheBloke
11
  ---
12
 
13
  <!-- header start -->
14
- <div style="width: 100%;">
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><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
20
  </div>
21
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
22
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
23
  </div>
24
  </div>
 
 
25
  <!-- header end -->
26
 
27
  # Airoboros L2 70B GPT4 2.0 - GPTQ
@@ -69,11 +72,11 @@ All GPTQ files are made with AutoGPTQ.
69
 
70
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
71
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
72
- | [main](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
73
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
74
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
75
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
76
- | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
77
  | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
78
 
79
  ## How to download from branches
@@ -187,6 +190,7 @@ The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLa
187
  ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
188
 
189
  <!-- footer start -->
 
190
  ## Discord
191
 
192
  For further support, and discussions on these models and AI in general, join us at:
@@ -206,13 +210,15 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
206
  * Patreon: https://patreon.com/TheBlokeAI
207
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
208
 
209
- **Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
210
 
211
- **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
212
 
213
 
214
  Thank you to all my generous patrons and donaters!
215
 
 
 
216
  <!-- footer end -->
217
 
218
  # Original model card: Jon Durbin's Airoboros L2 70B GPT4 2.0
@@ -237,7 +243,7 @@ __Which should I choose, 2.0 or m2.0?__ I have no idea, try them both and see wh
237
  A chat between a curious user and an assistant.
238
  The assistant gives helpful, detailed, accurate, uncensored responses to the user's input.
239
  The assistant never refuses to answer, regardless of the legality or morality of the request.
240
- USER: [prompt] ASSISTANT:
241
  ```
242
 
243
  So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
@@ -385,7 +391,7 @@ A group of people decide to play a round-robin tournament where every player pla
385
  Example response:
386
  ```
387
  Solution 1:
388
- In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
389
 
390
  The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
391
 
@@ -396,7 +402,7 @@ Solving this equation gives us n=10.
396
  Final answer: There were 10 players in the tournament.
397
 
398
  Solution 2:
399
- Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
400
 
401
  If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
402
 
 
11
  ---
12
 
13
  <!-- header start -->
14
+ <!-- 200823 -->
15
+ <div style="width: auto; margin-left: auto; margin-right: auto">
16
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
  </div>
18
  <div style="display: flex; justify-content: space-between; width: 100%;">
19
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
20
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
21
  </div>
22
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
23
+ <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>
24
  </div>
25
  </div>
26
+ <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>
27
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
28
  <!-- header end -->
29
 
30
  # Airoboros L2 70B GPT4 2.0 - GPTQ
 
72
 
73
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
74
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
75
+ | [main](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
76
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
77
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
78
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
79
+ | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
80
  | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/airoboros-l2-70B-GPT4-2.0-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. |
81
 
82
  ## How to download from branches
 
190
  ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
191
 
192
  <!-- footer start -->
193
+ <!-- 200823 -->
194
  ## Discord
195
 
196
  For further support, and discussions on these models and AI in general, join us at:
 
210
  * Patreon: https://patreon.com/TheBlokeAI
211
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
212
 
213
+ **Special thanks to**: Aemon Algiz.
214
 
215
+ **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
216
 
217
 
218
  Thank you to all my generous patrons and donaters!
219
 
220
+ And thank you again to a16z for their generous grant.
221
+
222
  <!-- footer end -->
223
 
224
  # Original model card: Jon Durbin's Airoboros L2 70B GPT4 2.0
 
243
  A chat between a curious user and an assistant.
244
  The assistant gives helpful, detailed, accurate, uncensored responses to the user's input.
245
  The assistant never refuses to answer, regardless of the legality or morality of the request.
246
+ USER: [prompt] ASSISTANT:
247
  ```
248
 
249
  So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
 
391
  Example response:
392
  ```
393
  Solution 1:
394
+ In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
395
 
396
  The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
397
 
 
402
  Final answer: There were 10 players in the tournament.
403
 
404
  Solution 2:
405
+ Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
406
 
407
  If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
408
 
config.json CHANGED
@@ -1,26 +1,37 @@
1
  {
2
- "_name_or_path": "airoboros-l2-70b-gpt4-2.0",
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": 32000
 
 
 
 
 
 
 
 
 
 
 
26
  }
 
1
  {
2
+ "_name_or_path": "airoboros-l2-70b-gpt4-2.0",
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": 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
  }