TheBloke commited on
Commit
351caf9
1 Parent(s): aa0aa9c

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. README.md +16 -12
README.md CHANGED
@@ -45,10 +45,12 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
45
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GGML)
46
  * [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-fp16)
47
 
48
- ## Prompt template: TBC
49
 
50
  ```
51
- Info on prompt template will be added shortly.
 
 
52
  ```
53
 
54
  ## Provided files and GPTQ parameters
@@ -74,12 +76,12 @@ All GPTQ files are made with AutoGPTQ.
74
 
75
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
76
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
77
- | [main](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 7.26 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
78
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
79
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 7.51 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. |
80
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 7.26 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. |
81
- | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
82
- | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
83
 
84
  ## How to download from branches
85
 
@@ -139,7 +141,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
139
 
140
  model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
141
  use_safetensors=True,
142
- trust_remote_code=True,
143
  device="cuda:0",
144
  use_triton=use_triton,
145
  quantize_config=None)
@@ -151,13 +153,15 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
151
  model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
152
  revision="gptq-4bit-32g-actorder_True",
153
  use_safetensors=True,
154
- trust_remote_code=True,
155
  device="cuda:0",
156
  quantize_config=None)
157
  """
158
 
159
  prompt = "Tell me about AI"
160
- prompt_template=f'''Info on prompt template will be added shortly.
 
 
161
  '''
162
 
163
  print("\n\n*** Generate:")
@@ -214,7 +218,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
214
 
215
  **Special thanks to**: Aemon Algiz.
216
 
217
- **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
218
 
219
 
220
  Thank you to all my generous patrons and donaters!
 
45
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GGML)
46
  * [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-fp16)
47
 
48
+ ## Prompt template: CodeLlama
49
 
50
  ```
51
+ [INST] Write code to solve the following coding problem that obeys the constraints and passes the example test cases. Please wrap your code answer using ```:
52
+ {prompt}
53
+ [/INST]
54
  ```
55
 
56
  ## Provided files and GPTQ parameters
 
76
 
77
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
78
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
79
+ | [main](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 7.26 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
80
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
81
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 7.51 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. |
82
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 7.26 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. |
83
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
84
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
85
 
86
  ## How to download from branches
87
 
 
141
 
142
  model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
143
  use_safetensors=True,
144
+ trust_remote_code=False,
145
  device="cuda:0",
146
  use_triton=use_triton,
147
  quantize_config=None)
 
153
  model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
154
  revision="gptq-4bit-32g-actorder_True",
155
  use_safetensors=True,
156
+ trust_remote_code=False,
157
  device="cuda:0",
158
  quantize_config=None)
159
  """
160
 
161
  prompt = "Tell me about AI"
162
+ prompt_template=f'''[INST] Write code to solve the following coding problem that obeys the constraints and passes the example test cases. Please wrap your code answer using ```:
163
+ {prompt}
164
+ [/INST]
165
  '''
166
 
167
  print("\n\n*** Generate:")
 
218
 
219
  **Special thanks to**: Aemon Algiz.
220
 
221
+ **Patreon special mentions**: Kacper Wikieł, knownsqashed, Leonard Tan, Asp the Wyvern, Daniel P. Andersen, Luke Pendergrass, Stanislav Ovsiannikov, RoA, Dave, Ai Maven, Kalila, Will Dee, Imad Khwaja, Nitin Borwankar, Joseph William Delisle, Tony Hughes, Cory Kujawski, Rishabh Srivastava, Russ Johnson, Stephen Murray, Lone Striker, Johann-Peter Hartmann, Elle, J, Deep Realms, SuperWojo, Raven Klaugh, Sebastain Graf, ReadyPlayerEmma, Alps Aficionado, Mano Prime, Derek Yates, Gabriel Puliatti, Mesiah Bishop, Magnesian, Sean Connelly, biorpg, Iucharbius, Olakabola, Fen Risland, Space Cruiser, theTransient, Illia Dulskyi, Thomas Belote, Spencer Kim, Pieter, John Detwiler, Fred von Graf, Michael Davis, Swaroop Kallakuri, subjectnull, Clay Pascal, Subspace Studios, Chris Smitley, Enrico Ros, usrbinkat, Steven Wood, alfie_i, David Ziegler, Willem Michiel, Matthew Berman, Andrey, Pyrater, Jeffrey Morgan, vamX, LangChain4j, Luke @flexchar, Trenton Dambrowitz, Pierre Kircher, Alex, Sam, James Bentley, Edmond Seymore, Eugene Pentland, Pedro Madruga, Rainer Wilmers, Dan Guido, Nathan LeClaire, Spiking Neurons AB, Talal Aujan, zynix, Artur Olbinski, Michael Levine, 阿明, K, John Villwock, Nikolai Manek, Femi Adebogun, senxiiz, Deo Leter, NimbleBox.ai, Viktor Bowallius, Geoffrey Montalvo, Mandus, Ajan Kanaga, ya boyyy, Jonathan Leane, webtim, Brandon Frisco, danny, Alexandros Triantafyllidis, Gabriel Tamborski, Randy H, terasurfer, Vadim, Junyu Yang, Vitor Caleffi, Chadd, transmissions 11
222
 
223
 
224
  Thank you to all my generous patrons and donaters!