Uploaded from OI Data Volume Exporter

.gitattributes

@@ -2,6 +2,7 @@
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
@@ -21,8 +22,10 @@
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
@@ -30,4 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-model.safetensors filter=lfs diff=lfs merge=lfs -text

LICENSE.txt

@@ -0,0 +1,111 @@
+LLAMA 3.2 COMMUNITY LICENSE AGREEMENT
+Llama 3.2 Version Release Date: September 25, 2024
+
+“Agreement” means the terms and conditions for use, reproduction, distribution 
+and modification of the Llama Materials set forth herein.
+
+“Documentation” means the specifications, manuals and documentation accompanying Llama 3.2
+distributed by Meta at https://llama.meta.com/doc/overview.
+
+“Licensee” or “you” means you, or your employer or any other person or entity (if you are 
+entering into this Agreement on such person or entity’s behalf), of the age required under
+applicable laws, rules or regulations to provide legal consent and that has legal authority
+to bind your employer or such other person or entity if you are entering in this Agreement
+on their behalf.
+
+“Llama 3.2” means the foundational large language models and software and algorithms, including
+machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
+fine-tuning enabling code and other elements of the foregoing distributed by Meta at 
+https://www.llama.com/llama-downloads.
+
+“Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and Documentation (and 
+any portion thereof) made available under this Agreement.
+
+“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, 
+if you are an entity, your principal place of business is in the EEA or Switzerland) 
+and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). 
+
+
+By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials,
+you agree to be bound by this Agreement.
+
+
+1. License Rights and Redistribution.
+
+    a. Grant of Rights. You are granted a non-exclusive, worldwide, 
+non-transferable and royalty-free limited license under Meta’s intellectual property or other rights 
+owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works 
+of, and make modifications to the Llama Materials.  
+
+    b. Redistribution and Use.  
+
+        i. If you distribute or make available the Llama Materials (or any derivative works thereof), 
+or a product or service (including another AI model) that contains any of them, you shall (A) provide
+a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama”
+on a related website, user interface, blogpost, about page, or product documentation. If you use the
+Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or
+otherwise improve an AI model, which is distributed or made available, you shall also include “Llama”
+at the beginning of any such AI model name.
+
+        ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
+of an integrated end user product, then Section 2 of this Agreement will not apply to you. 
+
+        iii. You must retain in all copies of the Llama Materials that you distribute the 
+following attribution notice within a “Notice” text file distributed as a part of such copies: 
+“Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,
+Inc. All Rights Reserved.”
+
+        iv. Your use of the Llama Materials must comply with applicable laws and regulations
+(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for
+the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby 
+incorporated by reference into this Agreement.
+  
+2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users
+of the products or services made available by or for Licensee, or Licensee’s affiliates, 
+is greater than 700 million monthly active users in the preceding calendar month, you must request 
+a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to
+exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
+
+3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND 
+RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS
+ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES
+OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
+FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED
+WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
+
+4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, 
+WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, 
+FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN 
+IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+
+5. Intellectual Property.
+
+    a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, 
+neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, 
+except as required for reasonable and customary use in describing and redistributing the Llama Materials or as 
+set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required 
+to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible 
+at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark 
+will inure to the benefit of Meta.
+
+    b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any
+    derivative works and modifications of the Llama Materials that are made by you, as between you and Meta,
+    you are and will be the owner of such derivative works and modifications.
+
+    c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or
+    counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion
+    of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable
+    by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or
+    claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third
+    party arising out of or related to your use or distribution of the Llama Materials.
+
+6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access
+to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms
+and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this
+Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3,
+4 and 7 shall survive the termination of this Agreement. 
+
+7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of 
+California without regard to choice of law principles, and the UN Convention on Contracts for the International
+Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of
+any dispute arising out of this Agreement. 

README.md

@@ -1,437 +1,481 @@
 ---
-language: 
+language:
 - en
-- zh
 - de
-- es
-- ru
-- ko
 - fr
-- ja
-- pt
-- tr
-- pl
-- ca
-- nl
-- ar
-- sv
 - it
-- id
+- pt
 - hi
-- fi
-- vi
-- he
-- uk
-- el
-- ms
-- cs
-- ro
-- da
-- hu
-- ta
-- no
+- es
 - th
-- ur
-- hr
-- bg
-- lt
-- la
-- mi
-- ml
-- cy
-- sk
-- te
-- fa
-- lv
-- bn
-- sr
-- az
-- sl
-- kn
-- et
-- mk
-- br
-- eu
-- is
-- hy
-- ne
-- mn
-- bs
-- kk
-- sq
-- sw
-- gl
-- mr
-- pa
-- si
-- km
-- sn
-- yo
-- so
-- af
-- oc
-- ka
-- be
-- tg
-- sd
-- gu
-- am
-- yi
-- lo
-- uz
-- fo
-- ht
-- ps
-- tk
-- nn
-- mt
-- sa
-- lb
-- my
-- bo
-- tl
-- mg
-- as
-- tt
-- haw
-- ln
-- ha
-- ba
-- jw
-- su
+library_name: transformers
+pipeline_tag: text-generation
 tags:
-- audio
-- automatic-speech-recognition
-- hf-asr-leaderboard
-widget:
-- example_title: Librispeech sample 1
-  src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
-- example_title: Librispeech sample 2
-  src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
-model-index:
-- name: whisper-tiny
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: LibriSpeech (clean)
-      type: librispeech_asr
-      config: clean
-      split: test
-      args: 
-        language: en
-    metrics:
-    - name: Test WER
-      type: wer
-      value: 7.54
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: LibriSpeech (other)
-      type: librispeech_asr
-      config: other
-      split: test
-      args: 
-        language: en
-    metrics:
-    - name: Test WER
-      type: wer
-      value:  17.15
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: Common Voice 11.0
-      type: mozilla-foundation/common_voice_11_0
-      config: hi
-      split: test
-      args:
-        language: hi
-    metrics:
-    - name: Test WER
-      type: wer
-      value: 141
-pipeline_tag: automatic-speech-recognition
-license: apache-2.0
+- facebook
+- meta
+- pytorch
+- llama
+- llama-3
+license: llama3.2
+extra_gated_prompt: >-
+  ### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT
+
+
+  Llama 3.2 Version Release Date: September 25, 2024
+
+  
+  “Agreement” means the terms and conditions for use, reproduction, distribution 
+  and modification of the Llama Materials set forth herein.
+
+  
+  “Documentation” means the specifications, manuals and documentation accompanying Llama 3.2
+  distributed by Meta at https://llama.meta.com/doc/overview.
+
+  
+  “Licensee” or “you” means you, or your employer or any other person or entity (if you are 
+  entering into this Agreement on such person or entity’s behalf), of the age required under
+  applicable laws, rules or regulations to provide legal consent and that has legal authority
+  to bind your employer or such other person or entity if you are entering in this Agreement
+  on their behalf.
+
+  
+  “Llama 3.2” means the foundational large language models and software and algorithms, including
+  machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
+  fine-tuning enabling code and other elements of the foregoing distributed by Meta at 
+  https://www.llama.com/llama-downloads.
+
+  
+  “Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and Documentation (and 
+  any portion thereof) made available under this Agreement.
+
+  
+  “Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, 
+  if you are an entity, your principal place of business is in the EEA or Switzerland) 
+  and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). 
+
+
+  By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials,
+  you agree to be bound by this Agreement.
+
+  
+  1. License Rights and Redistribution.
+  
+  a. Grant of Rights. You are granted a non-exclusive, worldwide, 
+  non-transferable and royalty-free limited license under Meta’s intellectual property or other rights 
+  owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works 
+  of, and make modifications to the Llama Materials.  
+
+  b. Redistribution and Use.  
+
+  i. If you distribute or make available the Llama Materials (or any derivative works thereof), 
+  or a product or service (including another AI model) that contains any of them, you shall (A) provide
+  a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama”
+  on a related website, user interface, blogpost, about page, or product documentation. If you use the
+  Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or
+  otherwise improve an AI model, which is distributed or made available, you shall also include “Llama”
+  at the beginning of any such AI model name.
+
+  ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
+  of an integrated end user product, then Section 2 of this Agreement will not apply to you. 
+
+  iii. You must retain in all copies of the Llama Materials that you distribute the 
+  following attribution notice within a “Notice” text file distributed as a part of such copies: 
+  “Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,
+  Inc. All Rights Reserved.”
+
+  iv. Your use of the Llama Materials must comply with applicable laws and regulations
+  (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for
+  the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby 
+  incorporated by reference into this Agreement.
+    
+  2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users
+  of the products or services made available by or for Licensee, or Licensee’s affiliates, 
+  is greater than 700 million monthly active users in the preceding calendar month, you must request 
+  a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to
+  exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
+  
+  3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND 
+  RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS
+  ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES
+  OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
+  FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED
+  WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
+  
+  4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, 
+  WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, 
+  FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN 
+  IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+  
+  5. Intellectual Property.
+  
+  a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, 
+  neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, 
+  except as required for reasonable and customary use in describing and redistributing the Llama Materials or as 
+  set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required 
+  to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible 
+  at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark 
+  will inure to the benefit of Meta.
+  
+  b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any
+  derivative works and modifications of the Llama Materials that are made by you, as between you and Meta,
+  you are and will be the owner of such derivative works and modifications.
+
+  c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or
+  counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion
+  of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable
+  by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or
+  claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third
+  party arising out of or related to your use or distribution of the Llama Materials.
+  
+  6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access
+  to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms
+  and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this
+  Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3,
+  4 and 7 shall survive the termination of this Agreement. 
+  
+  7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of 
+  California without regard to choice of law principles, and the UN Convention on Contracts for the International
+  Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of
+  any dispute arising out of this Agreement. 
+  
+  ### Llama 3.2 Acceptable Use Policy
+  
+  Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2. 
+  If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“**Policy**”). 
+  The most recent copy of this policy can be found at
+  [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).
+  
+  #### Prohibited Uses
+  
+  We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to:
+  
+  1. Violate the law or others’ rights, including to:
+      1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
+          1. Violence or terrorism
+          2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
+          3. Human trafficking, exploitation, and sexual violence
+          4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
+          5. Sexual solicitation
+          6. Any other criminal activity
+      1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
+      2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
+      3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
+      4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
+      5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
+      6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
+      7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta 
+  2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following:
+      8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
+      9. Guns and illegal weapons (including weapon development)
+      10. Illegal drugs and regulated/controlled substances
+      11. Operation of critical infrastructure, transportation technologies, or heavy machinery
+      12. Self-harm or harm to others, including suicide, cutting, and eating disorders
+      13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
+  3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following:
+      14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
+      15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
+      16. Generating, promoting, or further distributing spam
+      17. Impersonating another individual without consent, authorization, or legal right
+      18. Representing that the use of Llama 3.2 or outputs are human-generated
+      19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 
+  4. Fail to appropriately disclose to end users any known dangers of your AI system
+  5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2
+
+
+  With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
+
+
+  Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
+
+
+  * Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)
+  
+  * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
+  
+  * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
+  
+  * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: LlamaUseReport@meta.com
+extra_gated_fields:
+  First Name: text
+  Last Name: text
+  Date of birth: date_picker
+  Country: country
+  Affiliation: text
+  Job title:
+    type: select
+    options:
+    - Student
+    - Research Graduate
+    - AI researcher
+    - AI developer/engineer
+    - Reporter
+    - Other
+  geo: ip_location
+  By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
+extra_gated_description: >-
+  The information you provide will be collected, stored, processed and shared in
+  accordance with the [Meta Privacy
+  Policy](https://www.facebook.com/privacy/policy/).
+extra_gated_button_content: Submit
 ---
 
-# Whisper
+## Model Information
 
-Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours 
-of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains **without** the need 
-for fine-tuning.
+The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.
 
-Whisper was proposed in the paper [Robust Speech Recognition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356) 
-by Alec Radford et al from OpenAI. The original code repository can be found [here](https://github.com/openai/whisper).
+**Model Developer:** Meta
 
-**Disclaimer**: Content for this model card has partly been written by the Hugging Face team, and parts of it were 
-copied and pasted from the original model card.
+**Model Architecture:** Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
 
-## Model details
+|  | Training Data | Params | Input modalities | Output modalities | Context Length | GQA | Shared Embeddings | Token count | Knowledge cutoff |
+| :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
+| Llama 3.2 (text only)  | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code  | 128k | Yes | Yes | Up to 9T tokens | December 2023 |
+|  |  | 3B (3.21B) | Multilingual Text | Multilingual Text and code  |  |  |  |  |  |
+| Llama 3.2 Quantized (text only)  | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code  | 8k | Yes | Yes | Up to 9T tokens | December 2023 |
+|  |  | 3B (3.21B) | Multilingual Text | Multilingual Text and code |  |  |  |  |  |
 
-Whisper is a Transformer based encoder-decoder model, also referred to as a _sequence-to-sequence_ model. 
-It was trained on 680k hours of labelled speech data annotated using large-scale weak supervision. 
+**Supported Languages:** English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
 
-The models were trained on either English-only data or multilingual data. The English-only models were trained 
-on the task of speech recognition. The multilingual models were trained on both speech recognition and speech 
-translation. For speech recognition, the model predicts transcriptions in the *same* language as the audio. 
-For speech translation, the model predicts transcriptions to a *different* language to the audio.
+**Llama 3.2 Model Family:** Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
 
-Whisper checkpoints come in five configurations of varying model sizes.
-The smallest four are trained on either English-only or multilingual data.
-The largest checkpoints are multilingual only. All ten of the pre-trained checkpoints 
-are available on the [Hugging Face Hub](https://huggingface.co/models?search=openai/whisper). The 
-checkpoints are summarised in the following table with links to the models on the Hub:
+**Model Release Date:** Sept 25, 2024
 
-| Size     | Parameters | English-only                                         | Multilingual                                        |
-|----------|------------|------------------------------------------------------|-----------------------------------------------------|
-| tiny     | 39 M       | [✓](https://huggingface.co/openai/whisper-tiny.en)   | [✓](https://huggingface.co/openai/whisper-tiny)     |
-| base     | 74 M       | [✓](https://huggingface.co/openai/whisper-base.en)   | [✓](https://huggingface.co/openai/whisper-base)     |
-| small    | 244 M      | [✓](https://huggingface.co/openai/whisper-small.en)  | [✓](https://huggingface.co/openai/whisper-small)    |
-| medium   | 769 M      | [✓](https://huggingface.co/openai/whisper-medium.en) | [✓](https://huggingface.co/openai/whisper-medium)   |
-| large    | 1550 M     | x                                                    | [✓](https://huggingface.co/openai/whisper-large)    |
-| large-v2 | 1550 M     | x                                                    | [✓](https://huggingface.co/openai/whisper-large-v2) |
+**Status:** This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
 
-# Usage
+**License:** Use of Llama 3.2 is governed by the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) (a custom, commercial license agreement).
 
-To transcribe audio samples, the model has to be used alongside a [`WhisperProcessor`](https://huggingface.co/docs/transformers/model_doc/whisper#transformers.WhisperProcessor).
+**Feedback:** Instructions on how to provide feedback or comments on the model can be found in the Llama Models [README](https://github.com/meta-llama/llama-models/blob/main/README.md). For more technical information about generation parameters and recipes for how to use Llama 3.2 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
 
-The `WhisperProcessor` is used to:
-1. Pre-process the audio inputs (converting them to log-Mel spectrograms for the model)
-2. Post-process the model outputs (converting them from tokens to text)
+## Intended Use
 
-The model is informed of which task to perform (transcription or translation) by passing the appropriate "context tokens". These context tokens 
-are a sequence of tokens that are given to the decoder at the start of the decoding process, and take the following order:
-1. The transcription always starts with the `<|startoftranscript|>` token
-2. The second token is the language token (e.g. `<|en|>` for English)
-3. The third token is the "task token". It can take one of two values: `<|transcribe|>` for speech recognition or `<|translate|>` for speech translation
-4. In addition, a `<|notimestamps|>` token is added if the model should not include timestamp prediction
+**Intended Use Cases:** Llama 3.2 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat and agentic applications like knowledge retrieval and summarization, mobile AI powered writing assistants and query and prompt rewriting. Pretrained models can be adapted for a variety of additional natural language generation tasks. Similarly, quantized models can be adapted for a variety of on-device use-cases with limited compute resources.
 
-Thus, a typical sequence of context tokens might look as follows:
-```
-<|startoftranscript|> <|en|> <|transcribe|> <|notimestamps|>
-```
-Which tells the model to decode in English, under the task of speech recognition, and not to predict timestamps.
+**Out of Scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.2 Community License. Use in languages beyond those explicitly referenced as supported in this model card.
 
-These tokens can either be forced or un-forced. If they are forced, the model is made to predict each token at 
-each position. This allows one to control the output language and task for the Whisper model. If they are un-forced, 
-the Whisper model will automatically predict the output langauge and task itself.
+## How to use
 
-The context tokens can be set accordingly:
+This repository contains two versions of Llama-3.2-1B-Instruct, for use with transformers and with the original `llama` codebase.
+
+### Use with transformers
+
+Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.
+
+Make sure to update your transformers installation via `pip install --upgrade transformers`.
 
 ```python
-model.config.forced_decoder_ids = WhisperProcessor.get_decoder_prompt_ids(language="english", task="transcribe")
+import torch
+from transformers import pipeline
+
+model_id = "meta-llama/Llama-3.2-1B-Instruct"
+pipe = pipeline(
+    "text-generation",
+    model=model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+outputs = pipe(
+    messages,
+    max_new_tokens=256,
+)
+print(outputs[0]["generated_text"][-1])
 ```
 
-Which forces the model to predict in English under the task of speech recognition.
+Note: You can also find detailed recipes on how to use the model locally, with `torch.compile()`, assisted generations, quantised and more at [`huggingface-llama-recipes`](https://github.com/huggingface/huggingface-llama-recipes)
 
-## Transcription
+### Use with `llama`
 
-### English to English 
-In this example, the context tokens are 'unforced', meaning the model automatically predicts the output language
-(English) and task (transcribe).
+Please, follow the instructions in the [repository](https://github.com/meta-llama/llama)
 
-```python
->>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
->>> from datasets import load_dataset
-
->>> # load model and processor
->>> processor = WhisperProcessor.from_pretrained("openai/whisper-tiny")
->>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny")
->>> model.config.forced_decoder_ids = None
-
->>> # load dummy dataset and read audio files
->>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
->>> sample = ds[0]["audio"]
->>> input_features = processor(sample["array"], sampling_rate=sample["sampling_rate"], return_tensors="pt").input_features 
-
->>> # generate token ids
->>> predicted_ids = model.generate(input_features)
->>> # decode token ids to text
->>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=False)
-['<|startoftranscript|><|en|><|transcribe|><|notimestamps|> Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.<|endoftext|>']
-
->>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
-[' Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.']
+To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
+
+```
+huggingface-cli download meta-llama/Llama-3.2-1B-Instruct --include "original/*" --local-dir Llama-3.2-1B-Instruct
 ```
-The context tokens can be removed from the start of the transcription by setting `skip_special_tokens=True`.
 
-### French to French 
-The following example demonstrates French to French transcription by setting the decoder ids appropriately. 
+## Hardware and Software
 
-```python
->>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
->>> from datasets import Audio, load_dataset
-
->>> # load model and processor
->>> processor = WhisperProcessor.from_pretrained("openai/whisper-tiny")
->>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny")
->>> forced_decoder_ids = processor.get_decoder_prompt_ids(language="french", task="transcribe")
-
->>> # load streaming dataset and read first audio sample
->>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
->>> ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
->>> input_speech = next(iter(ds))["audio"]
->>> input_features = processor(input_speech["array"], sampling_rate=input_speech["sampling_rate"], return_tensors="pt").input_features
-
->>> # generate token ids
->>> predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids)
->>> # decode token ids to text
->>> transcription = processor.batch_decode(predicted_ids)
-['<|startoftranscript|><|fr|><|transcribe|><|notimestamps|> Un vrai travail intéressant va enfin être mené sur ce sujet.<|endoftext|>']
-
->>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
-[' Un vrai travail intéressant va enfin être mené sur ce sujet.']
-```
+**Training Factors:** We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, quantization, annotation, and evaluation were also performed on production infrastructure.
 
-## Translation 
-Setting the task to "translate" forces the Whisper model to perform speech translation.
+**Training Energy Use:** Training utilized a cumulative of **916k** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
 
-### French to English
+**Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **240** tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
 
-```python
->>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
->>> from datasets import Audio, load_dataset
-
->>> # load model and processor
->>> processor = WhisperProcessor.from_pretrained("openai/whisper-tiny")
->>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny")
->>> forced_decoder_ids = processor.get_decoder_prompt_ids(language="french", task="translate")
-
->>> # load streaming dataset and read first audio sample
->>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
->>> ds = ds.cast_column("audio", Audio(sampling_rate=16_000))
->>> input_speech = next(iter(ds))["audio"]
->>> input_features = processor(input_speech["array"], sampling_rate=input_speech["sampling_rate"], return_tensors="pt").input_features
-
->>> # generate token ids
->>> predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids)
->>> # decode token ids to text
->>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
-[' A very interesting work, we will finally be given on this subject.']
-```
+|  | Training Time (GPU hours) | Logit Generation Time (GPU Hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
+| :---- | :---: | ----- | :---: | :---: | :---: |
+| Llama 3.2 1B | 370k | \- | 700 | 107 | 0 |
+| Llama 3.2 3B | 460k | \- | 700 | 133 | 0 |
+| Llama 3.2 1B SpinQuant | 1.7 | 0 | 700 | *Negligible*\*\* | 0 |
+| Llama 3.2 3B SpinQuant | 2.4 | 0 | 700 | *Negligible*\*\* | 0 |
+| Llama 3.2 1B QLora | 1.3k | 0 | 700 | 0.381 | 0 |
+| Llama 3.2 3B QLora | 1.6k | 0 | 700 | 0.461 | 0 |
+| Total | 833k |         86k |  | 240 | 0 |
 
-## Evaluation
+\*\* The location-based CO2e emissions of Llama 3.2 1B SpinQuant and Llama 3.2 3B SpinQuant are less than 0.001 metric tonnes each. This is due to the minimal training GPU hours that are required.
 
-This code snippet shows how to evaluate Whisper Tiny on [LibriSpeech test-clean](https://huggingface.co/datasets/librispeech_asr):
- 
-```python
->>> from datasets import load_dataset
->>> from transformers import WhisperForConditionalGeneration, WhisperProcessor
->>> import torch
->>> from evaluate import load
-
->>> librispeech_test_clean = load_dataset("librispeech_asr", "clean", split="test")
-
->>> processor = WhisperProcessor.from_pretrained("openai/whisper-tiny")
->>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny").to("cuda")
-
->>> def map_to_pred(batch):
->>>     audio = batch["audio"]
->>>     input_features = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_features
->>>     batch["reference"] = processor.tokenizer._normalize(batch['text'])
->>> 
->>>     with torch.no_grad():
->>>         predicted_ids = model.generate(input_features.to("cuda"))[0]
->>>     transcription = processor.decode(predicted_ids)
->>>     batch["prediction"] = processor.tokenizer._normalize(transcription)
->>>     return batch
-
->>> result = librispeech_test_clean.map(map_to_pred)
-
->>> wer = load("wer")
->>> print(100 * wer.compute(references=result["reference"], predictions=result["prediction"]))
-7.547098647858638
-```
+The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
 
-## Long-Form Transcription
+## Training Data
 
-The Whisper model is intrinsically designed to work on audio samples of up to 30s in duration. However, by using a chunking 
-algorithm, it can be used to transcribe audio samples of up to arbitrary length. This is possible through Transformers 
-[`pipeline`](https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline) 
-method. Chunking is enabled by setting `chunk_length_s=30` when instantiating the pipeline. With chunking enabled, the pipeline 
-can be run with batched inference. It can also be extended to predict sequence level timestamps by passing `return_timestamps=True`:
+**Overview:** Llama 3.2 was pretrained on up to 9 trillion tokens of data from publicly available sources. For the 1B and 3B Llama 3.2 models, we incorporated logits from the Llama 3.1 8B and 70B models into the pretraining stage of the model development, where outputs (logits) from these larger models were used as token-level targets. Knowledge distillation was used after pruning to recover performance. In post-training we used a similar recipe as Llama 3.1 and produced final chat models by doing several rounds of alignment on top of the pre-trained model. Each round involved Supervised Fine-Tuning (SFT), Rejection Sampling (RS), and Direct Preference Optimization (DPO).
 
-```python
->>> import torch
->>> from transformers import pipeline
->>> from datasets import load_dataset
+**Data Freshness:** The pretraining data has a cutoff of December 2023\.
 
->>> device = "cuda:0" if torch.cuda.is_available() else "cpu"
+## Quantization
 
->>> pipe = pipeline(
->>>   "automatic-speech-recognition",
->>>   model="openai/whisper-tiny",
->>>   chunk_length_s=30,
->>>   device=device,
->>> )
+### Quantization Scheme
 
->>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
->>> sample = ds[0]["audio"]
+We designed the current quantization scheme with the [PyTorch’s ExecuTorch](https://github.com/pytorch/executorch) inference framework and Arm CPU backend in mind, taking into account metrics including model quality, prefill/decoding speed, and memory footprint. Our quantization scheme involves three parts:
+- All linear layers in all transformer blocks are quantized to a 4-bit groupwise scheme (with a group size of 32) for weights and 8-bit per-token dynamic quantization for activations.
+- The classification layer is quantized to 8-bit per-channel for weight and 8-bit per token dynamic quantization for activation.
+- Similar to classification layer, an 8-bit per channel quantization is used for embedding layer.
 
->>> prediction = pipe(sample.copy(), batch_size=8)["text"]
-" Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel."
 
->>> # we can also return timestamps for the predictions
->>> prediction = pipe(sample.copy(), batch_size=8, return_timestamps=True)["chunks"]
-[{'text': ' Mr. Quilter is the apostle of the middle classes and we are glad to welcome his gospel.',
-  'timestamp': (0.0, 5.44)}]
-```
+### Quantization-Aware Training and LoRA
 
-Refer to the blog post [ASR Chunking](https://huggingface.co/blog/asr-chunking) for more details on the chunking algorithm.
+The quantization-aware training (QAT) with low-rank adaptation (LoRA) models went through only post-training stages, using the same data as the full precision models. To initialize QAT, we utilize BF16 Llama 3.2 model checkpoints obtained after supervised fine-tuning (SFT) and perform an additional full round of SFT training with QAT. We then freeze the backbone of the QAT model and perform another round of SFT with LoRA adaptors applied to all layers within the transformer block. Meanwhile, the LoRA adaptors' weights and activations are maintained in BF16. Because our approach is similar to QLoRA of Dettmers et al., (2023) (i.e., quantization followed by LoRA adapters), we refer this method as QLoRA. Finally, we fine-tune the resulting model (both backbone and LoRA adaptors) using direct preference optimization (DPO).
 
-## Fine-Tuning
+### SpinQuant
 
-The pre-trained Whisper model demonstrates a strong ability to generalise to different datasets and domains. However, 
-its predictive capabilities can be improved further for certain languages and tasks through *fine-tuning*. The blog 
-post [Fine-Tune Whisper with 🤗 Transformers](https://huggingface.co/blog/fine-tune-whisper) provides a step-by-step 
-guide to fine-tuning the Whisper model with as little as 5 hours of labelled data.
+[SpinQuant](https://arxiv.org/abs/2405.16406) was applied, together with generative post-training quantization (GPTQ). For the SpinQuant rotation matrix fine-tuning, we optimized for 100 iterations, using 800 samples with sequence-length 2048 from the WikiText 2 dataset. For GPTQ, we used 128 samples from the same dataset with the same sequence-length.
 
-### Evaluated Use
+## Benchmarks \- English Text
 
-The primary intended users of these models are AI researchers studying robustness, generalization, capabilities, biases, and constraints of the current model. However, Whisper is also potentially quite useful as an ASR solution for developers, especially for English speech recognition. We recognize that once models are released, it is impossible to restrict access to only “intended” uses or to draw reasonable guidelines around what is or is not research.
+In this section, we report the results for Llama 3.2 models on standard automatic benchmarks. For all these evaluations, we used our internal evaluations library.
 
-The models are primarily trained and evaluated on ASR and speech translation to English tasks. They show strong ASR results in ~10 languages. They may exhibit additional capabilities, particularly if fine-tuned on certain tasks like voice activity detection, speaker classification, or speaker diarization but have not been robustly evaluated in these areas. We strongly recommend that users perform robust evaluations of the models in a particular context and domain before deploying them.
+### Base Pretrained Models
 
-In particular, we caution against using Whisper models to transcribe recordings of individuals taken without their consent or purporting to use these models for any kind of subjective classification. We recommend against use in high-risk domains like decision-making contexts, where flaws in accuracy can lead to pronounced flaws in outcomes. The models are intended to transcribe and translate speech, use of the model for classification is not only not evaluated but also not appropriate, particularly to infer human attributes.
+| Category | Benchmark | \# Shots | Metric | Llama 3.2 1B | Llama 3.2 3B | Llama 3.1 8B |
+| ----- | ----- | :---: | :---: | :---: | :---: | :---: |
+| General | MMLU | 5 | macro\_avg/acc\_char | 32.2 | 58 | 66.7 |
+|  | AGIEval English | 3-5 | average/acc\_char | 23.3 | 39.2 | 47.8 |
+|  | ARC-Challenge | 25 | acc\_char | 32.8 | 69.1 | 79.7 |
+| Reading comprehension | SQuAD | 1 | em | 49.2 | 67.7 | 77 |
+|  | QuAC (F1) | 1 | f1 | 37.9 | 42.9 | 44.9 |
+|  | DROP (F1) | 3 | f1 | 28.0 | 45.2 | 59.5 |
+| Long Context | Needle in Haystack | 0 | em | 96.8 | 1 | 1 |
 
+### Instruction Tuned Models
 
-## Training Data
+| Capability |  | Benchmark | \# Shots | Metric | Llama 3.2 1B bf16 | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B bf16 | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
+| :---: | ----- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| General |  | MMLU | 5 | macro\_avg/acc | 49.3 | 43.3 | 47.3 | 49.0 | 63.4 | 60.5 | 62 | 62.4 | 69.4 |
+| Re-writing |  | Open-rewrite eval | 0 | micro\_avg/rougeL | 41.6 | 39.2 | 40.9 | 41.2 | 40.1 | 40.3 | 40.8 | 40.7 | 40.9 |
+| Summarization |  | TLDR9+ (test) | 1 | rougeL | 16.8 | 14.9 | 16.7 | 16.8 | 19.0 | 19.1 | 19.2 | 19.1 | 17.2 |
+| Instruction following |  | IFEval | 0 | Avg(Prompt/Instruction acc Loose/Strict) | 59.5 | 51.5 | 58.4 | 55.6 | 77.4 | 73.9 | 73.5 | 75.9 | 80.4 |
+| Math |  | GSM8K (CoT) | 8 | em\_maj1@1 | 44.4 | 33.1 | 40.6 | 46.5 | 77.7 | 72.9 | 75.7 | 77.9 | 84.5 |
+|  |  | MATH (CoT) | 0 | final\_em | 30.6 | 20.5 | 25.3 | 31.0 | 48.0 | 44.2 | 45.3 | 49.2 | 51.9 |
+| Reasoning |  | ARC-C | 0 | acc | 59.4 | 54.3 | 57 | 60.7 | 78.6 | 75.6 | 77.6 | 77.6 | 83.4 |
+|  |  | GPQA | 0 | acc | 27.2 | 25.9 | 26.3 | 25.9 | 32.8 | 32.8 | 31.7 | 33.9 | 32.8 |
+|  |  | Hellaswag | 0 | acc | 41.2 | 38.1 | 41.3 | 41.5 | 69.8 | 66.3 | 68 | 66.3 | 78.7 |
+| Tool Use |  | BFCL V2 | 0 | acc | 25.7 | 14.3 | 15.9 | 23.7 | 67.0 | 53.4 | 60.1 | 63.5 | 67.1 |
+|  |  | Nexus | 0 | macro\_avg/acc | 13.5 | 5.2 | 9.6 | 12.5 | 34.3 | 32.4 | 31.5 | 30.1 | 38.5 |
+| Long Context |  | InfiniteBench/En.QA | 0 | longbook\_qa/f1 | 20.3 | N/A | N/A | N/A | 19.8 | N/A | N/A | N/A | 27.3 |
+|  |  | InfiniteBench/En.MC | 0 | longbook\_choice/acc | 38.0 | N/A | N/A | N/A | 63.3 | N/A | N/A | N/A | 72.2 |
+|  |  | NIH/Multi-needle | 0 | recall | 75.0 | N/A | N/A | N/A | 84.7 | N/A | N/A | N/A | 98.8 |
+| Multilingual |  | MGSM (CoT) | 0 | em | 24.5 | 13.7 | 18.2 | 24.4 | 58.2 | 48.9 | 54.3 | 56.8 | 68.9 |
 
-The models are trained on 680,000 hours of audio and the corresponding transcripts collected from the internet. 65% of this data (or 438,000 hours) represents English-language audio and matched English transcripts, roughly 18% (or 126,000 hours) represents non-English audio and English transcripts, while the final 17% (or 117,000 hours) represents non-English audio and the corresponding transcript. This non-English data represents 98 different languages. 
+\*\*for comparison purposes only. Model not released.
 
-As discussed in [the accompanying paper](https://cdn.openai.com/papers/whisper.pdf), we see that performance on transcription in a given language is directly correlated with the amount of training data we employ in that language.
+### Multilingual Benchmarks
 
+| Category | Benchmark | Language | Llama 3.2 1B | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
+| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| General | MMLU (5-shot, macro_avg/acc) | Portuguese | 39.8 | 34.9 | 38.9 | 40.2 | 54.5 | 50.9 | 53.3 | 53.4 | 62.1 |
+| | | Spanish | 41.5 | 36.0 | 39.8 | 41.8 | 55.1 | 51.9 | 53.6 | 53.6 | 62.5 |
+| | | Italian | 39.8 | 34.9 | 38.1 | 40.6 | 53.8 | 49.9 | 52.1 | 51.7 | 61.6 |
+| | | German | 39.2 | 34.9 | 37.5 | 39.6 | 53.3 | 50.0 | 52.2 | 51.3 | 60.6 |
+| | | French | 40.5 | 34.8 | 39.2 | 40.8 | 54.6 | 51.2 | 53.3 | 53.3 | 62.3 |
+| | | Hindi | 33.5 | 30.0 | 32.1 | 34.0 | 43.3 | 40.4 | 42.0 | 42.1 | 50.9 |
+| | | Thai | 34.7 | 31.2 | 32.4 | 34.9 | 44.5 | 41.3 | 44.0 | 42.2 | 50.3 |
 
-## Performance and Limitations
+\*\*for comparison purposes only. Model not released.
 
-Our studies show that, over many existing ASR systems, the models exhibit improved robustness to accents, background noise, technical language, as well as zero shot translation from multiple languages into English; and that accuracy on speech recognition and translation is near the state-of-the-art level. 
+## Inference time
 
-However, because the models are trained in a weakly supervised manner using large-scale noisy data, the predictions may include texts that are not actually spoken in the audio input (i.e. hallucination). We hypothesize that this happens because, given their general knowledge of language, the models combine trying to predict the next word in audio with trying to transcribe the audio itself.
+In the below table, we compare the performance metrics of different quantization methods (SpinQuant and QAT \+ LoRA) with the BF16 baseline. The evaluation was done using the [ExecuTorch](https://github.com/pytorch/executorch) framework as the inference engine, with the ARM CPU as a backend using Android OnePlus 12 device.
 
-Our models perform unevenly across languages, and we observe lower accuracy on low-resource and/or low-discoverability languages or languages where we have less training data. The models also exhibit disparate performance on different accents and dialects of particular languages, which may include higher word error rate across speakers of different genders, races, ages, or other demographic criteria. Our full evaluation results are presented in [the paper accompanying this release](https://cdn.openai.com/papers/whisper.pdf). 
+| Category | Decode (tokens/sec)  | Time-to-first-token (sec) | Prefill (tokens/sec) | Model size (PTE file size in MB) | Memory size (RSS in MB) |
+| :---- | ----- | ----- | ----- | ----- | ----- |
+| 1B BF16 (baseline) | 19.2 | 1.0 | 60.3 | 2358 | 3,185 |
+| 1B SpinQuant | 50.2 (2.6x) | 0.3 (-76.9%) | 260.5 (4.3x) | 1083 (-54.1%) | 1,921 (-39.7%) |
+| 1B QLoRA | 45.8 (2.4x) | 0.3 (-76.0%) | 252.0 (4.2x) | 1127 (-52.2%) | 2,255 (-29.2%) |
+| 3B BF16 (baseline) | 7.6 | 3.0 | 21.2 | 6129 | 7,419 |
+| 3B SpinQuant | 19.7 (2.6x) | 0.7 (-76.4%) | 89.7 (4.2x) | 2435 (-60.3%) | 3,726 (-49.8%) |
+| 3B QLoRA | 18.5 (2.4x) | 0.7 (-76.1%) | 88.8 (4.2x) | 2529 (-58.7%) | 4,060 (-45.3%) |
 
-In addition, the sequence-to-sequence architecture of the model makes it prone to generating repetitive texts, which can be mitigated to some degree by beam search and temperature scheduling but not perfectly. Further analysis on these limitations are provided in [the paper](https://cdn.openai.com/papers/whisper.pdf). It is likely that this behavior and hallucinations may be worse on lower-resource and/or lower-discoverability languages.
+(\*) The performance measurement is done using an adb binary-based approach.
+(\*\*) It is measured on an Android OnePlus 12 device.
+(\*\*\*) Time-to-first-token (TTFT)  is measured with prompt length=64
 
+*Footnote:*
 
-## Broader Implications
+- *Decode (tokens/second) is for how quickly it keeps generating. Higher is better.*
+- *Time-to-first-token (TTFT for shorthand) is for how fast it generates the first token for a given prompt. Lower is better.*
+- *Prefill is the inverse of TTFT (aka 1/TTFT)  in tokens/second. Higher is better*
+- *Model size \- how big is the model, measured by, PTE file, a binary file format for ExecuTorch*
+- *RSS size \- Memory usage in resident set size (RSS)*
 
-We anticipate that Whisper models’ transcription capabilities may be used for improving accessibility tools. While Whisper models cannot be used for real-time transcription out of the box – their speed and size suggest that others may be able to build applications on top of them that allow for near-real-time speech recognition and translation. The real value of beneficial applications built on top of Whisper models suggests that the disparate performance of these models may have real economic implications.
+## Responsibility & Safety
 
-There are also potential dual use concerns that come with releasing Whisper. While we hope the technology will be used primarily for beneficial purposes, making ASR technology more accessible could enable more actors to build capable surveillance technologies or scale up existing surveillance efforts, as the speed and accuracy allow for affordable automatic transcription and translation of large volumes of audio communication. Moreover, these models may have some capabilities to recognize specific individuals out of the box, which in turn presents safety concerns related both to dual use and disparate performance. In practice, we expect that the cost of transcription is not the limiting factor of scaling up surveillance projects.
+As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:
 
+1. Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama
+2. Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm
+3. Provide protections for the community to help prevent the misuse of our models
 
-### BibTeX entry and citation info
-```bibtex
-@misc{radford2022whisper,
-  doi = {10.48550/ARXIV.2212.04356},
-  url = {https://arxiv.org/abs/2212.04356},
-  author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
-  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
-  publisher = {arXiv},
-  year = {2022},
-  copyright = {arXiv.org perpetual, non-exclusive license}
-}
-```
+### Responsible Deployment
+
+**Approach:** Llama is a foundational technology designed to be used in a variety of use cases. Examples on how Meta’s Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models, enabling the world to benefit from the technology power, by aligning our model safety for generic use cases and addressing a standard set of harms. Developers are then in the driver’s seat to tailor safety for their use cases, defining their own policies and deploying the models with the necessary safeguards in their Llama systems. Llama 3.2 was developed following the best practices outlined in our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/).
+
+#### Llama 3.2 Instruct
+
+**Objective:** Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. We implemented the same set of safety mitigations as in Llama 3, and you can learn more about these in the Llama 3 [paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/).
+
+**Fine-Tuning Data:** We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
+
+**Refusals and Tone:** Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
+
+#### Llama 3.2 Systems
+
+**Safety as a System:** Large language models, including Llama 3.2, **are not designed to be deployed in isolation** but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.
+
+### New Capabilities and Use Cases
+
+**Technological Advancement:** Llama releases usually introduce new capabilities that require specific considerations in addition to the best practices that generally apply across all Generative AI use cases. For prior release capabilities also supported by Llama 3.2, see [Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), as the same considerations apply here as well.
+
+**Constrained Environments:** Llama 3.2 1B and 3B models are expected to be deployed in highly constrained environments, such as mobile devices. LLM Systems using smaller models will have a different alignment profile and safety/helpfulness tradeoff than more complex, larger systems. Developers should ensure the safety of their system meets the requirements of their use case. We recommend using lighter system safeguards for such use cases, like Llama Guard 3-1B or its mobile-optimized version.
+
+### Evaluations
+
+**Scaled Evaluations:** We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Purple Llama safeguards to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case.
+
+**Red Teaming:** We conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
+
+### Critical Risks
+
+In addition to our safety work above, we took extra care on measuring and/or mitigating the following critical risk areas:
+
+**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive Weapons):** Llama 3.2 1B and 3B models are smaller and less capable derivatives of Llama 3.1. For Llama 3.1 70B and 405B, to assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons and have determined that such testing also applies to the smaller 1B and 3B models.
+
+**2\. Child Safety:** Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
+
+**3\. Cyber Attacks:** For Llama 3.1 405B, our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
+Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Because Llama 3.2’s 1B and 3B models are smaller and less capable models than Llama 3.1 405B, we broadly believe that the testing conducted for the 405B model also applies to Llama 3.2 models.
+
+### Community
+
+**Industry Partnerships:** Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
+
+**Grants:** We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists).
+
+**Reporting:** Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
+
+## Ethical Considerations and Limitations
+
+**Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
+
+**Testing:** Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.

USE_POLICY.md

@@ -0,0 +1,52 @@
+**Llama 3.2** **Acceptable Use Policy**
+
+Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“**Policy**”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).
+
+**Prohibited Uses**
+
+We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to:
+
+
+
+1. Violate the law or others’ rights, including to:
+    1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
+        1. Violence or terrorism
+        2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
+        3. Human trafficking, exploitation, and sexual violence
+        4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
+        5. Sexual solicitation
+        6. Any other criminal activity
+    1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
+    2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
+    3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
+    4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
+    5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
+    6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
+    7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta 
+2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following:
+    8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
+    9. Guns and illegal weapons (including weapon development)
+    10. Illegal drugs and regulated/controlled substances
+    11. Operation of critical infrastructure, transportation technologies, or heavy machinery
+    12. Self-harm or harm to others, including suicide, cutting, and eating disorders
+    13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
+3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following:
+    14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
+    15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
+    16. Generating, promoting, or further distributing spam
+    17. Impersonating another individual without consent, authorization, or legal right
+    18. Representing that the use of Llama 3.2 or outputs are human-generated
+    19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 
+4. Fail to appropriately disclose to end users any known dangers of your AI system
+5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2
+
+With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
+
+Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
+
+
+
+* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)
+* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
+* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
+* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: LlamaUseReport@meta.com

config.json

@@ -1,144 +1,39 @@
 {
-  "_name_or_path": "openai/whisper-tiny",
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
   "architectures": [
-    "WhisperForConditionalGeneration"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "begin_suppress_tokens": [
-    220,
-    50257
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
   ],
-  "bos_token_id": 50257,
-  "d_model": 384,
-  "decoder_attention_heads": 6,
-  "decoder_ffn_dim": 1536,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 4,
-  "decoder_start_token_id": 50258,
-  "dropout": 0.0,
-  "encoder_attention_heads": 6,
-  "encoder_ffn_dim": 1536,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 4,
-  "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      50259
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
-  ],
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "max_length": 448,
-  "max_source_positions": 1500,
-  "max_target_positions": 448,
-  "model_type": "whisper",
-  "num_hidden_layers": 4,
-  "num_mel_bins": 80,
-  "pad_token_id": 50257,
-  "scale_embedding": false,
-  "suppress_tokens": [
-    1,
-    2,
-    7,
-    8,
-    9,
-    10,
-    14,
-    25,
-    26,
-    27,
-    28,
-    29,
-    31,
-    58,
-    59,
-    60,
-    61,
-    62,
-    63,
-    90,
-    91,
-    92,
-    93,
-    359,
-    503,
-    522,
-    542,
-    873,
-    893,
-    902,
-    918,
-    922,
-    931,
-    1350,
-    1853,
-    1982,
-    2460,
-    2627,
-    3246,
-    3253,
-    3268,
-    3536,
-    3846,
-    3961,
-    4183,
-    4667,
-    6585,
-    6647,
-    7273,
-    9061,
-    9383,
-    10428,
-    10929,
-    11938,
-    12033,
-    12331,
-    12562,
-    13793,
-    14157,
-    14635,
-    15265,
-    15618,
-    16553,
-    16604,
-    18362,
-    18956,
-    20075,
-    21675,
-    22520,
-    26130,
-    26161,
-    26435,
-    28279,
-    29464,
-    31650,
-    32302,
-    32470,
-    36865,
-    42863,
-    47425,
-    49870,
-    50254,
-    50258,
-    50358,
-    50359,
-    50360,
-    50361,
-    50362
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.27.0.dev0",
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
   "use_cache": true,
-  "vocab_size": 51865
+  "vocab_size": 128256
 }

generation_config.json

@@ -1,248 +1,12 @@
 {
-  "alignment_heads": [
-    [
-      2,
-      2
-    ],
-    [
-      3,
-      0
-    ],
-    [
-      3,
-      2
-    ],
-    [
-      3,
-      3
-    ],
-    [
-      3,
-      4
-    ],
-    [
-      3,
-      5
-    ]
-  ],
-  "begin_suppress_tokens": [
-    220,
-    50257
-  ],
-  "bos_token_id": 50257,
-  "decoder_start_token_id": 50258,
-  "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      null
-    ],
-    [
-      2,
-      50359
-    ]
-  ],
-  "is_multilingual": true,
-  "lang_to_id": {
-    "<|af|>": 50327,
-    "<|am|>": 50334,
-    "<|ar|>": 50272,
-    "<|as|>": 50350,
-    "<|az|>": 50304,
-    "<|ba|>": 50355,
-    "<|be|>": 50330,
-    "<|bg|>": 50292,
-    "<|bn|>": 50302,
-    "<|bo|>": 50347,
-    "<|br|>": 50309,
-    "<|bs|>": 50315,
-    "<|ca|>": 50270,
-    "<|cs|>": 50283,
-    "<|cy|>": 50297,
-    "<|da|>": 50285,
-    "<|de|>": 50261,
-    "<|el|>": 50281,
-    "<|en|>": 50259,
-    "<|es|>": 50262,
-    "<|et|>": 50307,
-    "<|eu|>": 50310,
-    "<|fa|>": 50300,
-    "<|fi|>": 50277,
-    "<|fo|>": 50338,
-    "<|fr|>": 50265,
-    "<|gl|>": 50319,
-    "<|gu|>": 50333,
-    "<|haw|>": 50352,
-    "<|ha|>": 50354,
-    "<|he|>": 50279,
-    "<|hi|>": 50276,
-    "<|hr|>": 50291,
-    "<|ht|>": 50339,
-    "<|hu|>": 50286,
-    "<|hy|>": 50312,
-    "<|id|>": 50275,
-    "<|is|>": 50311,
-    "<|it|>": 50274,
-    "<|ja|>": 50266,
-    "<|jw|>": 50356,
-    "<|ka|>": 50329,
-    "<|kk|>": 50316,
-    "<|km|>": 50323,
-    "<|kn|>": 50306,
-    "<|ko|>": 50264,
-    "<|la|>": 50294,
-    "<|lb|>": 50345,
-    "<|ln|>": 50353,
-    "<|lo|>": 50336,
-    "<|lt|>": 50293,
-    "<|lv|>": 50301,
-    "<|mg|>": 50349,
-    "<|mi|>": 50295,
-    "<|mk|>": 50308,
-    "<|ml|>": 50296,
-    "<|mn|>": 50314,
-    "<|mr|>": 50320,
-    "<|ms|>": 50282,
-    "<|mt|>": 50343,
-    "<|my|>": 50346,
-    "<|ne|>": 50313,
-    "<|nl|>": 50271,
-    "<|nn|>": 50342,
-    "<|no|>": 50288,
-    "<|oc|>": 50328,
-    "<|pa|>": 50321,
-    "<|pl|>": 50269,
-    "<|ps|>": 50340,
-    "<|pt|>": 50267,
-    "<|ro|>": 50284,
-    "<|ru|>": 50263,
-    "<|sa|>": 50344,
-    "<|sd|>": 50332,
-    "<|si|>": 50322,
-    "<|sk|>": 50298,
-    "<|sl|>": 50305,
-    "<|sn|>": 50324,
-    "<|so|>": 50326,
-    "<|sq|>": 50317,
-    "<|sr|>": 50303,
-    "<|su|>": 50357,
-    "<|sv|>": 50273,
-    "<|sw|>": 50318,
-    "<|ta|>": 50287,
-    "<|te|>": 50299,
-    "<|tg|>": 50331,
-    "<|th|>": 50289,
-    "<|tk|>": 50341,
-    "<|tl|>": 50348,
-    "<|tr|>": 50268,
-    "<|tt|>": 50351,
-    "<|uk|>": 50280,
-    "<|ur|>": 50290,
-    "<|uz|>": 50337,
-    "<|vi|>": 50278,
-    "<|yi|>": 50335,
-    "<|yo|>": 50325,
-    "<|zh|>": 50260
-  },
-  "max_initial_timestamp_index": 50,
-  "max_length": 448,
-  "no_timestamps_token_id": 50363,
-  "pad_token_id": 50257,
-  "prev_sot_token_id": 50361,
-  "return_timestamps": false,
-  "suppress_tokens": [
-    1,
-    2,
-    7,
-    8,
-    9,
-    10,
-    14,
-    25,
-    26,
-    27,
-    28,
-    29,
-    31,
-    58,
-    59,
-    60,
-    61,
-    62,
-    63,
-    90,
-    91,
-    92,
-    93,
-    359,
-    503,
-    522,
-    542,
-    873,
-    893,
-    902,
-    918,
-    922,
-    931,
-    1350,
-    1853,
-    1982,
-    2460,
-    2627,
-    3246,
-    3253,
-    3268,
-    3536,
-    3846,
-    3961,
-    4183,
-    4667,
-    6585,
-    6647,
-    7273,
-    9061,
-    9383,
-    10428,
-    10929,
-    11938,
-    12033,
-    12331,
-    12562,
-    13793,
-    14157,
-    14635,
-    15265,
-    15618,
-    16553,
-    16604,
-    18362,
-    18956,
-    20075,
-    21675,
-    22520,
-    26130,
-    26161,
-    26435,
-    28279,
-    29464,
-    31650,
-    32302,
-    32470,
-    36865,
-    42863,
-    47425,
-    49870,
-    50254,
-    50258,
-    50358,
-    50359,
-    50360,
-    50361,
-    50362
-  ],
-  "task_to_id": {
-    "transcribe": 50359,
-    "translate": 50358
-  },
-  "transformers_version": "4.31.0.dev0"
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ebd0e69e78190ffe1438491fa05cc1f5c1aa3a4c4db3bc1723adbb551ea2395
-size 151061672
+oid sha256:1ff795ff6a07e6a68085d206fb84417da2f083f68391c2843cd2b8ac6df8538f
+size 2471645608

original/consolidated.00.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc17d497df5e4175b3a8acb4f5865b26f7fc1b009b25bef814b95fde10e8a1f3
+size 2471677246

original/params.json

@@ -0,0 +1,12 @@
+{
+  "dim": 2048,
+  "n_layers": 16,
+  "n_heads": 32,
+  "n_kv_heads": 8,
+  "vocab_size": 128256,
+  "ffn_dim_multiplier": 1.5,
+  "multiple_of": 256,
+  "norm_eps": 1e-05,
+  "rope_theta": 500000.0,
+  "use_scaled_rope": true
+}

original/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e9d31979e92ab929cd544440f129d9ecd797b69e327f80f17e1c50d5551b55
+size 2183982

special_tokens_map.json

@@ -1,136 +1,13 @@
 {
-  "additional_special_tokens": [
-    "<|endoftext|>",
-    "<|startoftranscript|>",
-    "<|en|>",
-    "<|zh|>",
-    "<|de|>",
-    "<|es|>",
-    "<|ru|>",
-    "<|ko|>",
-    "<|fr|>",
-    "<|ja|>",
-    "<|pt|>",
-    "<|tr|>",
-    "<|pl|>",
-    "<|ca|>",
-    "<|nl|>",
-    "<|ar|>",
-    "<|sv|>",
-    "<|it|>",
-    "<|id|>",
-    "<|hi|>",
-    "<|fi|>",
-    "<|vi|>",
-    "<|he|>",
-    "<|uk|>",
-    "<|el|>",
-    "<|ms|>",
-    "<|cs|>",
-    "<|ro|>",
-    "<|da|>",
-    "<|hu|>",
-    "<|ta|>",
-    "<|no|>",
-    "<|th|>",
-    "<|ur|>",
-    "<|hr|>",
-    "<|bg|>",
-    "<|lt|>",
-    "<|la|>",
-    "<|mi|>",
-    "<|ml|>",
-    "<|cy|>",
-    "<|sk|>",
-    "<|te|>",
-    "<|fa|>",
-    "<|lv|>",
-    "<|bn|>",
-    "<|sr|>",
-    "<|az|>",
-    "<|sl|>",
-    "<|kn|>",
-    "<|et|>",
-    "<|mk|>",
-    "<|br|>",
-    "<|eu|>",
-    "<|is|>",
-    "<|hy|>",
-    "<|ne|>",
-    "<|mn|>",
-    "<|bs|>",
-    "<|kk|>",
-    "<|sq|>",
-    "<|sw|>",
-    "<|gl|>",
-    "<|mr|>",
-    "<|pa|>",
-    "<|si|>",
-    "<|km|>",
-    "<|sn|>",
-    "<|yo|>",
-    "<|so|>",
-    "<|af|>",
-    "<|oc|>",
-    "<|ka|>",
-    "<|be|>",
-    "<|tg|>",
-    "<|sd|>",
-    "<|gu|>",
-    "<|am|>",
-    "<|yi|>",
-    "<|lo|>",
-    "<|uz|>",
-    "<|fo|>",
-    "<|ht|>",
-    "<|ps|>",
-    "<|tk|>",
-    "<|nn|>",
-    "<|mt|>",
-    "<|sa|>",
-    "<|lb|>",
-    "<|my|>",
-    "<|bo|>",
-    "<|tl|>",
-    "<|mg|>",
-    "<|as|>",
-    "<|tt|>",
-    "<|haw|>",
-    "<|ln|>",
-    "<|ha|>",
-    "<|ba|>",
-    "<|jw|>",
-    "<|su|>",
-    "<|translate|>",
-    "<|transcribe|>",
-    "<|startoflm|>",
-    "<|startofprev|>",
-    "<|nocaptions|>",
-    "<|notimestamps|>"
-  ],
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "<|begin_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
+    "content": "<|eot_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,