TheBloke commited on
Commit
49bfdeb
1 Parent(s): a22be5f

Update for Transformers GPTQ support

Browse files
README.md CHANGED
@@ -4,17 +4,20 @@ license: other
4
  ---
5
 
6
  <!-- header start -->
7
- <div style="width: 100%;">
8
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 
9
  </div>
10
  <div style="display: flex; justify-content: space-between; width: 100%;">
11
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
12
- <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
13
  </div>
14
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
15
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
16
  </div>
17
  </div>
 
 
18
  <!-- header end -->
19
 
20
  # OpenAccess AI Collective's Manticore 13B GPTQ
@@ -146,6 +149,7 @@ It was created with group_size 128 to increase inference accuracy, but without -
146
  * Parameters: Groupsize = 128. Act Order / desc_act = False.
147
 
148
  <!-- footer start -->
 
149
  ## Discord
150
 
151
  For further support, and discussions on these models and AI in general, join us at:
@@ -165,12 +169,15 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
165
  * Patreon: https://patreon.com/TheBlokeAI
166
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
167
 
168
- **Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
 
 
169
 
170
- **Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
171
 
172
  Thank you to all my generous patrons and donaters!
173
 
 
 
174
  <!-- footer end -->
175
 
176
  # Original model card: Kaio Ken's SuperHOT 8K
@@ -246,8 +253,8 @@ Try out the model in HF Spaces. The demo uses a quantized GGML version of the mo
246
 
247
  ## Build
248
 
249
- Manticore was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 8xA100 80GB
250
- - Preview Release: 3 epochs taking approximately 24 hours.
251
  - The configuration to duplicate this build is provided in this repo's [/config folder](https://huggingface.co/openaccess-ai-collective/manticore-13b/tree/main/configs).
252
 
253
  ## Bias, Risks, and Limitations
@@ -265,20 +272,20 @@ Here’s an example of how you can use memoization to efficiently calculate the
265
  def fib(n):
266
  # Memoize the last calculated Fibonacci number for each index
267
  cache = {}
268
-
269
  def fib_memoized(n):
270
  if n not in cache:
271
  cache[n] = [0, 1]
272
  else:
273
  return cache[n][-1], cache[n][-2]
274
-
275
  # Recursive helper function to calculate the Fibonacci sequence up to a given index
276
  def fib_helper(n):
277
  if n == 0 or n == 1:
278
  return 0, 1
279
  else:
280
  return fib_helper(n - 1) + fib_helper(n - 2)
281
-
282
  # Calculate the first n numbers of the Fibonacci sequence using memoization
283
  def fib_memoized_seq(n):
284
  if n == 0 or n == 1:
@@ -287,7 +294,7 @@ def fib(n):
287
  result = fib_helper(n - 1) + fib_helper(n - 2)
288
  cache[n] = [result]
289
  return result, cache[n][-1], cache[n][-2]
290
-
291
  # Example usage
292
  for i in range(len(fib_memoized_seq(3))):
293
  print(fib_memoized_seq(3)[i])
@@ -297,18 +304,18 @@ In this implementation, we use a cache dictionary to memoize the last calculated
297
  ````
298
 
299
  ```
300
- USER: Finish the joke, a mechanic and a car salesman walk into a bar...
301
  ASSISTANT: … and when they get up to leave, they realize that they’ve left their keys in their cars. The mechanic says “I know how to fix this” and opens his toolbox to grab something. Then he stops and looks at the salesman. He says “You drive a Toyota, right?” The salesman nods. The mechanic then takes out a tiny screwdriver from his toolbox and starts working on the lock of the car door. The salesman is amazed and asks how he knew that. The mechanic replies “I can tell by the way you parked your car.”
302
  ```
303
 
304
  ```
305
  USER: Describe how a tsunami would affect the residents of Denver Colorado
306
- ASSISTANT: The impact of a tsunami in Denver, Colorado would likely be minimal. As there are no coastal areas or bodies of water nearby, a tsunami generated from an earthquake or volcanic activity elsewhere in the world would have little effect on the city and its residents. Even if a large tsunami were to hit the coastline of California or Mexico, the distance between Denver and these locations means that any impacts on the city itself would be minimal.
307
  ```
308
 
309
  ```
310
  USER: If you could do one thing right now, what would it be?
311
- ASSISTANT: I’d hug my loved ones a little tighter today and tell them how much they mean to me.
312
  USER: And who are your loved ones?
313
  ASSISTANT: My closest friends and family members.
314
  USER: What are their names?
 
4
  ---
5
 
6
  <!-- header start -->
7
+ <!-- 200823 -->
8
+ <div style="width: auto; margin-left: auto; margin-right: auto">
9
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
10
  </div>
11
  <div style="display: flex; justify-content: space-between; width: 100%;">
12
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
13
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
14
  </div>
15
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
16
+ <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>
17
  </div>
18
  </div>
19
+ <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>
20
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
21
  <!-- header end -->
22
 
23
  # OpenAccess AI Collective's Manticore 13B GPTQ
 
149
  * Parameters: Groupsize = 128. Act Order / desc_act = False.
150
 
151
  <!-- footer start -->
152
+ <!-- 200823 -->
153
  ## Discord
154
 
155
  For further support, and discussions on these models and AI in general, join us at:
 
169
  * Patreon: https://patreon.com/TheBlokeAI
170
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
171
 
172
+ **Special thanks to**: Aemon Algiz.
173
+
174
+ **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
175
 
 
176
 
177
  Thank you to all my generous patrons and donaters!
178
 
179
+ And thank you again to a16z for their generous grant.
180
+
181
  <!-- footer end -->
182
 
183
  # Original model card: Kaio Ken's SuperHOT 8K
 
253
 
254
  ## Build
255
 
256
+ Manticore was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 8xA100 80GB
257
+ - Preview Release: 3 epochs taking approximately 24 hours.
258
  - The configuration to duplicate this build is provided in this repo's [/config folder](https://huggingface.co/openaccess-ai-collective/manticore-13b/tree/main/configs).
259
 
260
  ## Bias, Risks, and Limitations
 
272
  def fib(n):
273
  # Memoize the last calculated Fibonacci number for each index
274
  cache = {}
275
+
276
  def fib_memoized(n):
277
  if n not in cache:
278
  cache[n] = [0, 1]
279
  else:
280
  return cache[n][-1], cache[n][-2]
281
+
282
  # Recursive helper function to calculate the Fibonacci sequence up to a given index
283
  def fib_helper(n):
284
  if n == 0 or n == 1:
285
  return 0, 1
286
  else:
287
  return fib_helper(n - 1) + fib_helper(n - 2)
288
+
289
  # Calculate the first n numbers of the Fibonacci sequence using memoization
290
  def fib_memoized_seq(n):
291
  if n == 0 or n == 1:
 
294
  result = fib_helper(n - 1) + fib_helper(n - 2)
295
  cache[n] = [result]
296
  return result, cache[n][-1], cache[n][-2]
297
+
298
  # Example usage
299
  for i in range(len(fib_memoized_seq(3))):
300
  print(fib_memoized_seq(3)[i])
 
304
  ````
305
 
306
  ```
307
+ USER: Finish the joke, a mechanic and a car salesman walk into a bar...
308
  ASSISTANT: … and when they get up to leave, they realize that they’ve left their keys in their cars. The mechanic says “I know how to fix this” and opens his toolbox to grab something. Then he stops and looks at the salesman. He says “You drive a Toyota, right?” The salesman nods. The mechanic then takes out a tiny screwdriver from his toolbox and starts working on the lock of the car door. The salesman is amazed and asks how he knew that. The mechanic replies “I can tell by the way you parked your car.”
309
  ```
310
 
311
  ```
312
  USER: Describe how a tsunami would affect the residents of Denver Colorado
313
+ ASSISTANT: The impact of a tsunami in Denver, Colorado would likely be minimal. As there are no coastal areas or bodies of water nearby, a tsunami generated from an earthquake or volcanic activity elsewhere in the world would have little effect on the city and its residents. Even if a large tsunami were to hit the coastline of California or Mexico, the distance between Denver and these locations means that any impacts on the city itself would be minimal.
314
  ```
315
 
316
  ```
317
  USER: If you could do one thing right now, what would it be?
318
+ ASSISTANT: I’d hug my loved ones a little tighter today and tell them how much they mean to me.
319
  USER: And who are your loved ones?
320
  ASSISTANT: My closest friends and family members.
321
  USER: What are their names?
config.json CHANGED
@@ -1,29 +1,39 @@
1
  {
2
- "_name_or_path": "/workspace/superhot_process/manticore-13b/source",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "bos_token_id": 1,
7
- "eos_token_id": 2,
8
- "hidden_act": "silu",
9
- "hidden_size": 5120,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 13824,
12
- "max_position_embeddings": 8192,
13
- "max_sequence_length": 2048,
14
- "model_type": "llama",
15
- "num_attention_heads": 40,
16
- "num_hidden_layers": 40,
17
- "pad_token_id": 0,
18
- "rms_norm_eps": 1e-06,
19
- "tie_word_embeddings": false,
20
- "torch_dtype": "float16",
21
- "transformers_version": "4.30.0.dev0",
22
- "use_cache": true,
23
- "vocab_size": 32000,
24
- "auto_map": {
25
- "AutoModel": "modelling_llama.LlamaModel",
26
- "AutoModelForCausalLM": "modelling_llama.LlamaForCausalLM",
27
- "AutoModelForSequenceClassification": "modelling_llama.LlamaForSequenceClassification"
28
- }
 
 
 
 
 
 
 
 
 
 
29
  }
 
1
  {
2
+ "_name_or_path": "/workspace/superhot_process/manticore-13b/source",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 8192,
13
+ "max_sequence_length": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "pad_token_id": 0,
18
+ "rms_norm_eps": 1e-06,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float16",
21
+ "transformers_version": "4.30.0.dev0",
22
+ "use_cache": true,
23
+ "vocab_size": 32000,
24
+ "auto_map": {
25
+ "AutoModel": "modelling_llama.LlamaModel",
26
+ "AutoModelForCausalLM": "modelling_llama.LlamaForCausalLM",
27
+ "AutoModelForSequenceClassification": "modelling_llama.LlamaForSequenceClassification"
28
+ },
29
+ "quantization_config": {
30
+ "bits": 4,
31
+ "group_size": 128,
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
  }
manticore-13b-superhot-8k-GPTQ-4bit-128g.no-act.order.safetensors → model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e6358e48ff549d0403cfa0c159278630d6d228fabd910413d1520c434d2cfee
3
- size 7454797160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0077198bcf20e8ebe7e6790d8dbcbd86288b74fe9fca1217d6a35f51b8b5c73
3
+ size 7454797216
quantize_config.json CHANGED
@@ -1,8 +1,9 @@
1
  {
2
- "bits": 4,
3
- "group_size": 128,
4
- "damp_percent": 0.01,
5
- "desc_act": false,
6
- "sym": true,
7
- "true_sequential": true
 
8
  }
 
1
  {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.01,
5
+ "desc_act": false,
6
+ "sym": true,
7
+ "true_sequential": true,
8
+ "model_file_base_name": "model"
9
  }