TheBloke commited on
Commit
1e85574
1 Parent(s): f2927b5

Initial GGUF model commit

Browse files
Files changed (1) hide show
  1. README.md +47 -88
README.md CHANGED
@@ -1,14 +1,16 @@
1
  ---
2
  inference: false
 
 
3
  license: llama2
4
  model_creator: Meta
5
- model_link: https://ai.meta.com/resources/models-and-libraries/llama-downloads
6
  model_name: CodeLlama 7B Python
7
  model_type: llama
 
8
  quantized_by: TheBloke
9
  tags:
10
  - llama-2
11
- - codellama
12
  ---
13
 
14
  <!-- header start -->
@@ -30,11 +32,11 @@ tags:
30
 
31
  # CodeLlama 7B Python - GGUF
32
  - Model creator: [Meta](https://huggingface.co/meta-llama)
33
- - Original model: [CodeLlama 7B Python](https://ai.meta.com/resources/models-and-libraries/llama-downloads)
34
 
35
  ## Description
36
 
37
- This repo contains GGUF format model files for [Meta's CodeLlama 7B Python](https://ai.meta.com/resources/models-and-libraries/llama-downloads).
38
 
39
  <!-- README_GGUF.md-about-gguf start -->
40
  ### About GGUF
@@ -62,7 +64,7 @@ The clients and libraries below are expecting to add GGUF support shortly:
62
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeLlama-7B-Python-GPTQ)
63
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeLlama-7B-Python-GGUF)
64
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/CodeLlama-7B-Python-GGML)
65
- * [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/CodeLlama-7B-Python-fp16)
66
  <!-- repositories-available end -->
67
 
68
  <!-- prompt-template start -->
@@ -178,125 +180,82 @@ And thank you again to a16z for their generous grant.
178
  <!-- original-model-card start -->
179
  # Original model card: Meta's CodeLlama 7B Python
180
 
 
 
181
 
182
- <!-- header start -->
183
- <!-- 200823 -->
184
- <div style="width: auto; margin-left: auto; margin-right: auto">
185
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
186
- </div>
187
- <div style="display: flex; justify-content: space-between; width: 100%;">
188
- <div style="display: flex; flex-direction: column; align-items: flex-start;">
189
- <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
190
- </div>
191
- <div style="display: flex; flex-direction: column; align-items: flex-end;">
192
- <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>
193
- </div>
194
- </div>
195
- <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>
196
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
197
- <!-- header end -->
198
-
199
- # CodeLlama 7B-Python fp16
200
- - Model creator: [Meta](https://ai.meta.com/llama/)
201
-
202
- ## Description
203
-
204
- This is Transformers/HF format fp16 weights for CodeLlama 7B-Python. It is the result of downloading CodeLlama 7B-Python from [Meta](https://ai.meta.com/blog/code-llama-large-language-model-coding/) and converting to HF using `convert_llama_weights_to_hf.py`.
205
-
206
- Quantisations will be coming shortly.
207
-
208
- Please note that due to a change in the RoPE Theta value, for correct results you must load these FP16 models with `trust_remote_code=True`
209
-
210
- Credit to @emozilla for creating the necessary modelling code to achieve this!
211
 
212
- ## Prompt template: TBC
213
 
 
214
 
215
- <!-- footer start -->
216
- <!-- 200823 -->
217
- ## Discord
218
-
219
- For further support, and discussions on these models and AI in general, join us at:
220
-
221
- [TheBloke AI's Discord server](https://discord.gg/theblokeai)
222
-
223
- ## Thanks, and how to contribute.
224
-
225
- Thanks to the [chirper.ai](https://chirper.ai) team!
226
-
227
- 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.
228
-
229
- 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.
230
-
231
- Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
232
-
233
- * Patreon: https://patreon.com/TheBlokeAI
234
- * Ko-Fi: https://ko-fi.com/TheBlokeAI
235
-
236
- **Special thanks to**: Aemon Algiz.
237
-
238
- **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
239
-
240
-
241
- Thank you to all my generous patrons and donaters!
242
 
243
- And thank you again to a16z for their generous grant.
244
 
245
- <!-- footer end -->
 
 
 
246
 
247
- # Original model card
 
248
 
249
- # Code Llama
250
 
251
- ## **Model Details**
252
 
253
- **Model Developers** Meta AI
 
 
254
 
255
- **Variations** Code Llama comes in three model sizes, and three variants:
256
- 1) Code Llama: our base models designed for general code synthesis and understanding
257
- 2) Code Llama - Python: designed specifically for Python
258
- 3) Code Llama - Instruct: for instruction following and safer deployment
259
-
260
  All variants are available in sizes of 7B, 13B and 34B parameters.
261
 
 
 
262
  **Input** Models input text only.
263
 
264
- **Output** Models output text only.
265
 
266
- **Model Architecture** Code Llama and its variants are autoregressive language models using optimized transformer architectures. Code Llama 7B and 13B additionally support infilling text generation. All models were fine-tuned with up to 16K tokens, and support up to 100K tokens at inference time.
267
 
268
  **Model Dates** Code Llama and its variants have been trained between January 2023 and July 2023.
269
 
270
- **Status** This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.
271
 
272
- **Licence** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/).
273
 
274
  **Research Paper** More information can be found in the paper "[Code Llama: Open Foundation Models for Code](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)".
275
 
276
- **Where to send comments** Instructions on how to provide feedback or comments on the model can be found in the model [README](README.md), or by opening an issue in the GitHub repository ([https://github.com/facebookresearch/codellama/](https://github.com/facebookresearch/codellama/)).
277
-
278
- ## **Intended Use**
279
  **Intended Use Cases** Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.
280
 
281
  **Out-of-Scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.
282
 
283
- ## **Hardware and Software**
284
- **Training Factors**
285
- We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.
286
 
287
  **Carbon Footprint** In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.
288
 
289
- **Training data**
 
290
  All experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the [research paper](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/) for details).
291
- Code Llama - Instruct uses additional instruction fine-tuning data.
292
 
293
- **Evaluation Results**
 
294
  See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.
295
 
296
- ## **Ethical Considerations and Limitations**
 
 
297
  Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.
298
 
299
  Please see the Responsible Use Guide available available at [https://ai.meta.com/llama/responsible-user-guide](https://ai.meta.com/llama/responsible-user-guide).
300
 
301
-
302
  <!-- original-model-card end -->
 
1
  ---
2
  inference: false
3
+ language:
4
+ - code
5
  license: llama2
6
  model_creator: Meta
7
+ model_link: https://huggingface.co/codellama/CodeLlama-7b-python-hf
8
  model_name: CodeLlama 7B Python
9
  model_type: llama
10
+ pipeline_tag: text-generation
11
  quantized_by: TheBloke
12
  tags:
13
  - llama-2
 
14
  ---
15
 
16
  <!-- header start -->
 
32
 
33
  # CodeLlama 7B Python - GGUF
34
  - Model creator: [Meta](https://huggingface.co/meta-llama)
35
+ - Original model: [CodeLlama 7B Python](https://huggingface.co/codellama/CodeLlama-7b-python-hf)
36
 
37
  ## Description
38
 
39
+ This repo contains GGUF format model files for [Meta's CodeLlama 7B Python](https://huggingface.co/codellama/CodeLlama-7b-python-hf).
40
 
41
  <!-- README_GGUF.md-about-gguf start -->
42
  ### About GGUF
 
64
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeLlama-7B-Python-GPTQ)
65
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeLlama-7B-Python-GGUF)
66
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/CodeLlama-7B-Python-GGML)
67
+ * [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/codellama/CodeLlama-7b-python-hf)
68
  <!-- repositories-available end -->
69
 
70
  <!-- prompt-template start -->
 
180
  <!-- original-model-card start -->
181
  # Original model card: Meta's CodeLlama 7B Python
182
 
183
+ # **Code Llama**
184
+ Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the 7B Python specialist version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
185
 
186
+ | | Base Model | Python | Instruct |
187
+ | --- | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
188
+ | 7B | [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) |
189
+ | 13B | [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) | [codellama/CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf) | [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) |
190
+ | 34B | [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) | [codellama/CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf) | [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
191
 
192
+ ## Model Use
193
 
194
+ To use this model, please make sure to install transformers from `main` until the next version is released:
195
 
196
+ ```bash
197
+ pip install git+https://github.com/huggingface/transformers.git@main accelerate
198
+ ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
199
 
200
+ Model capabilities:
201
 
202
+ - [x] Code completion.
203
+ - [ ] Infilling.
204
+ - [ ] Instructions / chat.
205
+ - [x] Python specialist.
206
 
207
+ ## Model Details
208
+ *Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs).
209
 
210
+ **Model Developers** Meta
211
 
212
+ **Variations** Code Llama comes in three model sizes, and three variants:
213
 
214
+ * Code Llama: base models designed for general code synthesis and understanding
215
+ * Code Llama - Python: designed specifically for Python
216
+ * Code Llama - Instruct: for instruction following and safer deployment
217
 
 
 
 
 
 
218
  All variants are available in sizes of 7B, 13B and 34B parameters.
219
 
220
+ **This repository contains the Python version of the 7B parameters model.**
221
+
222
  **Input** Models input text only.
223
 
224
+ **Output** Models generate text only.
225
 
226
+ **Model Architecture** Code Llama is an auto-regressive language model that uses an optimized transformer architecture.
227
 
228
  **Model Dates** Code Llama and its variants have been trained between January 2023 and July 2023.
229
 
230
+ **Status** This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.
231
 
232
+ **License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
233
 
234
  **Research Paper** More information can be found in the paper "[Code Llama: Open Foundation Models for Code](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)".
235
 
236
+ ## Intended Use
 
 
237
  **Intended Use Cases** Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.
238
 
239
  **Out-of-Scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.
240
 
241
+ ## Hardware and Software
242
+ **Training Factors** We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.
 
243
 
244
  **Carbon Footprint** In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.
245
 
246
+ ## Training Data
247
+
248
  All experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the [research paper](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/) for details).
 
249
 
250
+ ## Evaluation Results
251
+
252
  See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.
253
 
254
+
255
+ ## Ethical Considerations and Limitations
256
+
257
  Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.
258
 
259
  Please see the Responsible Use Guide available available at [https://ai.meta.com/llama/responsible-user-guide](https://ai.meta.com/llama/responsible-user-guide).
260
 
 
261
  <!-- original-model-card end -->