TheBloke commited on
Commit
f5d3641
1 Parent(s): 6fb8b1a

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -15
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  datasets:
3
  - ehartford/samantha-data
4
  inference: false
@@ -6,9 +7,16 @@ language:
6
  - en
7
  license: llama2
8
  model_creator: Eric Hartford
9
- model_link: https://huggingface.co/ehartford/Samantha-1.11-CodeLlama-34b
10
  model_name: Samantha 1.11 CodeLlama 34B
11
  model_type: llama
 
 
 
 
 
 
 
 
12
  quantized_by: TheBloke
13
  ---
14
 
@@ -44,6 +52,7 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
44
  <!-- repositories-available start -->
45
  ## Repositories available
46
 
 
47
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ)
48
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF)
49
  * [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/Samantha-1.11-CodeLlama-34b)
@@ -62,6 +71,7 @@ ASSISTANT:
62
 
63
  <!-- prompt-template end -->
64
 
 
65
  <!-- README_GPTQ.md-provided-files start -->
66
  ## Provided files and GPTQ parameters
67
 
@@ -86,22 +96,22 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
86
 
87
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
88
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
89
- | [main](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 17.69 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
90
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 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. |
91
- | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 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. |
92
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 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. |
93
  | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.54 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
94
- | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 14.14 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
95
 
96
  <!-- README_GPTQ.md-provided-files end -->
97
 
98
  <!-- README_GPTQ.md-download-from-branches start -->
99
  ## How to download from branches
100
 
101
- - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ:gptq-4bit-32g-actorder_True`
102
  - With Git, you can clone a branch with:
103
  ```
104
- git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ
105
  ```
106
  - In Python Transformers code, the branch is the `revision` parameter; see below.
107
  <!-- README_GPTQ.md-download-from-branches end -->
@@ -114,7 +124,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
114
 
115
  1. Click the **Model tab**.
116
  2. Under **Download custom model or LoRA**, enter `TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ`.
117
- - To download from a specific branch, enter for example `TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ:gptq-4bit-32g-actorder_True`
118
  - see Provided Files above for the list of branches for each option.
119
  3. Click **Download**.
120
  4. The model will start downloading. Once it's finished it will say "Done".
@@ -162,10 +172,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
162
 
163
  model_name_or_path = "TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ"
164
  # To use a different branch, change revision
165
- # For example: revision="gptq-4bit-32g-actorder_True"
166
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
167
- torch_dtype=torch.float16,
168
  device_map="auto",
 
169
  revision="main")
170
 
171
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
@@ -181,7 +191,7 @@ ASSISTANT:
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, max_new_tokens=512)
185
  print(tokenizer.decode(output[0]))
186
 
187
  # Inference can also be done using transformers' pipeline
@@ -192,9 +202,11 @@ pipe = pipeline(
192
  model=model,
193
  tokenizer=tokenizer,
194
  max_new_tokens=512,
 
195
  temperature=0.7,
196
  top_p=0.95,
197
- repetition_penalty=1.15
 
198
  )
199
 
200
  print(pipe(prompt_template)[0]['generated_text'])
@@ -219,10 +231,12 @@ For further support, and discussions on these models and AI in general, join us
219
 
220
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
221
 
222
- ## Thanks, and how to contribute.
223
 
224
  Thanks to the [chirper.ai](https://chirper.ai) team!
225
 
 
 
226
  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.
227
 
228
  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.
@@ -234,7 +248,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
234
 
235
  **Special thanks to**: Aemon Algiz.
236
 
237
- **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
238
 
239
 
240
  Thank you to all my generous patrons and donaters!
 
1
  ---
2
+ base_model: https://huggingface.co/ehartford/Samantha-1.11-CodeLlama-34b
3
  datasets:
4
  - ehartford/samantha-data
5
  inference: false
 
7
  - en
8
  license: llama2
9
  model_creator: Eric Hartford
 
10
  model_name: Samantha 1.11 CodeLlama 34B
11
  model_type: llama
12
+ prompt_template: 'You are Samantha, a sentient AI companion.
13
+
14
+
15
+ USER: {prompt}
16
+
17
+ ASSISTANT:
18
+
19
+ '
20
  quantized_by: TheBloke
21
  ---
22
 
 
52
  <!-- repositories-available start -->
53
  ## Repositories available
54
 
55
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-AWQ)
56
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ)
57
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GGUF)
58
  * [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/Samantha-1.11-CodeLlama-34b)
 
71
 
72
  <!-- prompt-template end -->
73
 
74
+
75
  <!-- README_GPTQ.md-provided-files start -->
76
  ## Provided files and GPTQ parameters
77
 
 
96
 
97
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
98
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
99
+ | [main](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 17.69 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
100
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 20.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
101
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 35.07 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
102
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 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. |
103
  | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.54 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
104
+ | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 14.14 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
105
 
106
  <!-- README_GPTQ.md-provided-files end -->
107
 
108
  <!-- README_GPTQ.md-download-from-branches start -->
109
  ## How to download from branches
110
 
111
+ - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ:main`
112
  - With Git, you can clone a branch with:
113
  ```
114
+ git clone --single-branch --branch main https://huggingface.co/TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ
115
  ```
116
  - In Python Transformers code, the branch is the `revision` parameter; see below.
117
  <!-- README_GPTQ.md-download-from-branches end -->
 
124
 
125
  1. Click the **Model tab**.
126
  2. Under **Download custom model or LoRA**, enter `TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ`.
127
+ - To download from a specific branch, enter for example `TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ:main`
128
  - see Provided Files above for the list of branches for each option.
129
  3. Click **Download**.
130
  4. The model will start downloading. Once it's finished it will say "Done".
 
172
 
173
  model_name_or_path = "TheBloke/Samantha-1.11-CodeLlama-34B-GPTQ"
174
  # To use a different branch, change revision
175
+ # For example: revision="main"
176
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 
177
  device_map="auto",
178
+ trust_remote_code=False,
179
  revision="main")
180
 
181
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
191
  print("\n\n*** Generate:")
192
 
193
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
194
+ output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
195
  print(tokenizer.decode(output[0]))
196
 
197
  # Inference can also be done using transformers' pipeline
 
202
  model=model,
203
  tokenizer=tokenizer,
204
  max_new_tokens=512,
205
+ do_sample=True,
206
  temperature=0.7,
207
  top_p=0.95,
208
+ top_k=40,
209
+ repetition_penalty=1.1
210
  )
211
 
212
  print(pipe(prompt_template)[0]['generated_text'])
 
231
 
232
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
233
 
234
+ ## Thanks, and how to contribute
235
 
236
  Thanks to the [chirper.ai](https://chirper.ai) team!
237
 
238
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
239
+
240
  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.
241
 
242
  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.
 
248
 
249
  **Special thanks to**: Aemon Algiz.
250
 
251
+ **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
252
 
253
 
254
  Thank you to all my generous patrons and donaters!