TheBloke commited on
Commit
37cd9b7
1 Parent(s): 86df50f

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -16
README.md CHANGED
@@ -1,13 +1,16 @@
1
  ---
 
2
  inference: false
3
  language:
4
  - code
5
  license: llama2
6
  model_creator: Meta
7
- model_link: https://huggingface.co/codellama/CodeLlama-34b-hf
8
  model_name: CodeLlama 34B
9
  model_type: llama
10
  pipeline_tag: text-generation
 
 
 
11
  quantized_by: TheBloke
12
  tags:
13
  - llama-2
@@ -45,6 +48,7 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
45
  <!-- repositories-available start -->
46
  ## Repositories available
47
 
 
48
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeLlama-34B-GPTQ)
49
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeLlama-34B-GGUF)
50
  * [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/codellama/CodeLlama-34b-hf)
@@ -60,6 +64,7 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
60
 
61
  <!-- prompt-template end -->
62
 
 
63
  <!-- README_GPTQ.md-provided-files start -->
64
  ## Provided files and GPTQ parameters
65
 
@@ -84,22 +89,22 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
84
 
85
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
86
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
87
- | [main](https://huggingface.co/TheBloke/CodeLlama-34B-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 18.33 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
88
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-34B-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 | 20.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
89
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-34B-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 | 18.98 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. |
90
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-34B-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 | 18.33 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. |
91
- | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-34B-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 | 34.30 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
92
- | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-34B-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 | 35.07 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
93
 
94
  <!-- README_GPTQ.md-provided-files end -->
95
 
96
  <!-- README_GPTQ.md-download-from-branches start -->
97
  ## How to download from branches
98
 
99
- - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/CodeLlama-34B-GPTQ:gptq-4bit-32g-actorder_True`
100
  - With Git, you can clone a branch with:
101
  ```
102
- git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/CodeLlama-34B-GPTQ
103
  ```
104
  - In Python Transformers code, the branch is the `revision` parameter; see below.
105
  <!-- README_GPTQ.md-download-from-branches end -->
@@ -112,7 +117,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
112
 
113
  1. Click the **Model tab**.
114
  2. Under **Download custom model or LoRA**, enter `TheBloke/CodeLlama-34B-GPTQ`.
115
- - To download from a specific branch, enter for example `TheBloke/CodeLlama-34B-GPTQ:gptq-4bit-32g-actorder_True`
116
  - see Provided Files above for the list of branches for each option.
117
  3. Click **Download**.
118
  4. The model will start downloading. Once it's finished it will say "Done".
@@ -160,10 +165,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
160
 
161
  model_name_or_path = "TheBloke/CodeLlama-34B-GPTQ"
162
  # To use a different branch, change revision
163
- # For example: revision="gptq-4bit-32g-actorder_True"
164
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
165
- torch_dtype=torch.float16,
166
  device_map="auto",
 
167
  revision="main")
168
 
169
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
@@ -176,7 +181,7 @@ prompt_template=f'''{prompt}
176
  print("\n\n*** Generate:")
177
 
178
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
179
- output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
180
  print(tokenizer.decode(output[0]))
181
 
182
  # Inference can also be done using transformers' pipeline
@@ -187,9 +192,11 @@ pipe = pipeline(
187
  model=model,
188
  tokenizer=tokenizer,
189
  max_new_tokens=512,
 
190
  temperature=0.7,
191
  top_p=0.95,
192
- repetition_penalty=1.15
 
193
  )
194
 
195
  print(pipe(prompt_template)[0]['generated_text'])
@@ -214,10 +221,12 @@ For further support, and discussions on these models and AI in general, join us
214
 
215
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
216
 
217
- ## Thanks, and how to contribute.
218
 
219
  Thanks to the [chirper.ai](https://chirper.ai) team!
220
 
 
 
221
  I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
222
 
223
  If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
@@ -229,7 +238,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
229
 
230
  **Special thanks to**: Aemon Algiz.
231
 
232
- **Patreon special mentions**: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser
233
 
234
 
235
  Thank you to all my generous patrons and donaters!
 
1
  ---
2
+ base_model: https://huggingface.co/codellama/CodeLlama-34b-hf
3
  inference: false
4
  language:
5
  - code
6
  license: llama2
7
  model_creator: Meta
 
8
  model_name: CodeLlama 34B
9
  model_type: llama
10
  pipeline_tag: text-generation
11
+ prompt_template: '{prompt}
12
+
13
+ '
14
  quantized_by: TheBloke
15
  tags:
16
  - llama-2
 
48
  <!-- repositories-available start -->
49
  ## Repositories available
50
 
51
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/CodeLlama-34B-AWQ)
52
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeLlama-34B-GPTQ)
53
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeLlama-34B-GGUF)
54
  * [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/codellama/CodeLlama-34b-hf)
 
64
 
65
  <!-- prompt-template end -->
66
 
67
+
68
  <!-- README_GPTQ.md-provided-files start -->
69
  ## Provided files and GPTQ parameters
70
 
 
89
 
90
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
91
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
92
+ | [main](https://huggingface.co/TheBloke/CodeLlama-34B-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 4096 | 18.33 GB | Yes | 4-bit, without Act Order and group size 128g. |
93
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-34B-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 | 20.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
94
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-34B-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 | 18.98 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
95
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-34B-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 | 18.33 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
96
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-34B-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 | 34.30 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
97
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-34B-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 | 35.07 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
98
 
99
  <!-- README_GPTQ.md-provided-files end -->
100
 
101
  <!-- README_GPTQ.md-download-from-branches start -->
102
  ## How to download from branches
103
 
104
+ - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/CodeLlama-34B-GPTQ:main`
105
  - With Git, you can clone a branch with:
106
  ```
107
+ git clone --single-branch --branch main https://huggingface.co/TheBloke/CodeLlama-34B-GPTQ
108
  ```
109
  - In Python Transformers code, the branch is the `revision` parameter; see below.
110
  <!-- README_GPTQ.md-download-from-branches end -->
 
117
 
118
  1. Click the **Model tab**.
119
  2. Under **Download custom model or LoRA**, enter `TheBloke/CodeLlama-34B-GPTQ`.
120
+ - To download from a specific branch, enter for example `TheBloke/CodeLlama-34B-GPTQ:main`
121
  - see Provided Files above for the list of branches for each option.
122
  3. Click **Download**.
123
  4. The model will start downloading. Once it's finished it will say "Done".
 
165
 
166
  model_name_or_path = "TheBloke/CodeLlama-34B-GPTQ"
167
  # To use a different branch, change revision
168
+ # For example: revision="main"
169
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 
170
  device_map="auto",
171
+ trust_remote_code=False,
172
  revision="main")
173
 
174
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
181
  print("\n\n*** Generate:")
182
 
183
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
184
+ output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
185
  print(tokenizer.decode(output[0]))
186
 
187
  # Inference can also be done using transformers' pipeline
 
192
  model=model,
193
  tokenizer=tokenizer,
194
  max_new_tokens=512,
195
+ do_sample=True,
196
  temperature=0.7,
197
  top_p=0.95,
198
+ top_k=40,
199
+ repetition_penalty=1.1
200
  )
201
 
202
  print(pipe(prompt_template)[0]['generated_text'])
 
221
 
222
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
223
 
224
+ ## Thanks, and how to contribute
225
 
226
  Thanks to the [chirper.ai](https://chirper.ai) team!
227
 
228
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
229
+
230
  I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
231
 
232
  If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
 
238
 
239
  **Special thanks to**: Aemon Algiz.
240
 
241
+ **Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
242
 
243
 
244
  Thank you to all my generous patrons and donaters!