TheBloke commited on
Commit
d6ce55f
1 Parent(s): 78e749e

Update for Transformers GPTQ support

Browse files
README.md CHANGED
@@ -8,17 +8,20 @@ inference: false
8
  ---
9
 
10
  <!-- header start -->
11
- <div style="width: 100%;">
12
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 
13
  </div>
14
  <div style="display: flex; justify-content: space-between; width: 100%;">
15
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
16
- <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
17
  </div>
18
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
19
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
20
  </div>
21
  </div>
 
 
22
  <!-- header end -->
23
 
24
  # Falcon-7B-Instruct GPTQ
@@ -98,7 +101,7 @@ model_name_or_path = "TheBloke/falcon-7b-instruct-GPTQ"
98
  # You could also download the model locally, and access it there
99
  # model_name_or_path = "/path/to/TheBloke_falcon-7b-instruct-GPTQ"
100
 
101
- model_basename = "gptq_model-4bit-64g"
102
 
103
  use_triton = False
104
 
@@ -159,6 +162,7 @@ It was created with groupsize 64 to give higher inference quality, and without `
159
  * Parameters: Groupsize = 64. No act-order.
160
 
161
  <!-- footer start -->
 
162
  ## Discord
163
 
164
  For further support, and discussions on these models and AI in general, join us at:
@@ -178,12 +182,15 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
178
  * Patreon: https://patreon.com/TheBlokeAI
179
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
180
 
181
- **Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
 
 
182
 
183
- **Patreon special mentions**: RoA, Lone Striker, Gabriel Puliatti, Derek Yates, Randy H, Jonathan Leane, Eugene Pentland, Karl Bernard, Viktor Bowallius, senxiiz, Daniel P. Andersen, Pierre Kircher, Deep Realms, Cory Kujawski, Oscar Rangel, Fen Risland, Ajan Kanaga, LangChain4j, webtim, Nikolai Manek, Trenton Dambrowitz, Raven Klaugh, Kalila, Khalefa Al-Ahmad, Chris McCloskey, Luke @flexchar, Ai Maven, Dave, Asp the Wyvern, Sean Connelly, Imad Khwaja, Space Cruiser, Rainer Wilmers, subjectnull, Alps Aficionado, Willian Hasse, Fred von Graf, Artur Olbinski, Johann-Peter Hartmann, WelcomeToTheClub, Willem Michiel, Michael Levine, Iucharbius , Spiking Neurons AB, K, biorpg, John Villwock, Pyrater, Greatston Gnanesh, Mano Prime, Junyu Yang, Stephen Murray, John Detwiler, Luke Pendergrass, terasurfer , Pieter, zynix , Edmond Seymore, theTransient, Nathan LeClaire, vamX, Kevin Schuppel, Preetika Verma, ya boyyy, Alex , SuperWojo, Ghost , Joseph William Delisle, Matthew Berman, Talal Aujan, chris gileta, Illia Dulskyi.
184
 
185
  Thank you to all my generous patrons and donaters!
186
 
 
 
187
  <!-- footer end -->
188
 
189
  # ✨ Original model card: Falcon-7B-Instruct
 
8
  ---
9
 
10
  <!-- header start -->
11
+ <!-- 200823 -->
12
+ <div style="width: auto; margin-left: auto; margin-right: auto">
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 style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
18
  </div>
19
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
20
+ <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>
21
  </div>
22
  </div>
23
+ <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>
24
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
25
  <!-- header end -->
26
 
27
  # Falcon-7B-Instruct GPTQ
 
101
  # You could also download the model locally, and access it there
102
  # model_name_or_path = "/path/to/TheBloke_falcon-7b-instruct-GPTQ"
103
 
104
+ model_basename = "model"
105
 
106
  use_triton = False
107
 
 
162
  * Parameters: Groupsize = 64. No act-order.
163
 
164
  <!-- footer start -->
165
+ <!-- 200823 -->
166
  ## Discord
167
 
168
  For further support, and discussions on these models and AI in general, join us at:
 
182
  * Patreon: https://patreon.com/TheBlokeAI
183
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
184
 
185
+ **Special thanks to**: Aemon Algiz.
186
+
187
+ **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
188
 
 
189
 
190
  Thank you to all my generous patrons and donaters!
191
 
192
+ And thank you again to a16z for their generous grant.
193
+
194
  <!-- footer end -->
195
 
196
  # ✨ Original model card: Falcon-7B-Instruct
config.json CHANGED
@@ -25,5 +25,15 @@
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.29.2",
27
  "use_cache": true,
28
- "vocab_size": 65024
29
- }
 
 
 
 
 
 
 
 
 
 
 
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.29.2",
27
  "use_cache": true,
28
+ "vocab_size": 65024,
29
+ "quantization_config": {
30
+ "bits": 4,
31
+ "group_size": 64,
32
+ "damp_percent": 0.01,
33
+ "desc_act": false,
34
+ "sym": true,
35
+ "true_sequential": true,
36
+ "model_file_base_name": "model",
37
+ "quant_method": "gptq"
38
+ }
39
+ }
gptq_model-4bit-64g.safetensors → model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ceb8ec3d0c432d043ec563d42e2571c94a5e884aedfb5acc6b38612a60490c7b
3
- size 5942953456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba5affa21beebeaf04a74ed4118853a1e67474b30b6fdce95a08e4824ccfa7b6
3
+ size 5942953520
quantize_config.json CHANGED
@@ -4,5 +4,6 @@
4
  "damp_percent": 0.01,
5
  "desc_act": false,
6
  "sym": true,
7
- "true_sequential": true
 
8
  }
 
4
  "damp_percent": 0.01,
5
  "desc_act": false,
6
  "sym": true,
7
+ "true_sequential": true,
8
+ "model_file_base_name": "model"
9
  }