Upload folder using huggingface_hub

README.md

@@ -0,0 +1,184 @@
+---
+language:
+- en
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-2
+- mlx
+extra_gated_heading: You need to share contact information with Meta to access this
+  model
+extra_gated_prompt: "### LLAMA 2 COMMUNITY LICENSE AGREEMENT\n\"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 2 distributed by Meta at https://ai.meta.com/resources/models-and-libraries/llama-downloads/.\
+  \   \"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 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 ai.meta.com/resources/models-and-libraries/llama-downloads/. \"Llama\
+  \ Materials\" means, collectively, Meta's proprietary Llama 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.  \n   \nb. Redistribution and Use.   i. If you distribute or make\
+  \ the Llama Materials, or any derivative works  thereof, available to a third party,\
+  \ you shall provide a copy of this Agreement to such  third party.  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 2 is licensed under the LLAMA 2\
+  \ Community License,  Copyright (c) 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://ai.meta.com/llama/use-policy),\
+  \ which is hereby incorporated by reference into  this Agreement. v. You will not\
+  \ use the Llama Materials or any output or results of the  Llama Materials to improve\
+  \ any other large language model (excluding Llama 2 or  derivative works thereof).\
+  \   2. Additional Commercial Terms. If, on the Llama 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,  EITHER EXPRESS OR 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. 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 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.\
+  \  USE POLICY ### Llama 2 Acceptable Use Policy Meta is committed to promoting safe\
+  \ and fair use of its tools and features, including Llama 2. If you access or use\
+  \ Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy\
+  \ of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).\
+  \ #### Prohibited Uses We want everyone to use Llama 2 safely and responsibly. You\
+  \ agree you will not use, or allow others to use, Llama 2 to:  1. Violate the law\
+  \ or others’ rights, including to:\n  1. Engage in, promote, generate, contribute\
+  \ to, encourage, plan, incite, or further illegal or unlawful activity or content,\
+  \ such as: \n    1. Violence or terrorism \n    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\n    3. Human trafficking,\
+  \ exploitation, and sexual violence\n    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.\n    5.\
+  \ Sexual solicitation\n    6. Any other criminal activity\n  2. Engage in, promote,\
+  \ incite, or facilitate the harassment, abuse, threatening, or bullying of individuals\
+  \ or groups of individuals\n  3. 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\n  4. Engage in the unauthorized or unlicensed practice of any profession\
+  \ including, but not limited to, financial, legal, medical/health, or related professional\
+  \ practices \n  5. Collect, process, disclose, generate, or infer health, demographic,\
+  \ or other sensitive personal or private information about individuals without rights\
+  \ and consents required by applicable laws\n  6. 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 2 Materials\n  7. 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 \n2. 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 2 related\
+  \ to the following:\n  1. 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\n  2. Guns and illegal weapons (including weapon development)\n  3. Illegal\
+  \ drugs and regulated/controlled substances\n  4. Operation of critical infrastructure,\
+  \ transportation technologies, or heavy machinery\n  5. Self-harm or harm to others,\
+  \ including suicide, cutting, and eating disorders\n  6. Any content intended to\
+  \ incite or promote violence, abuse, or any infliction of bodily harm to an individual\n\
+  3. Intentionally deceive or mislead others, including use of Llama 2 related to\
+  \ the following:\n  1. Generating, promoting, or furthering fraud or the creation\
+  \ or promotion of disinformation\n  2. Generating, promoting, or furthering defamatory\
+  \ content, including the creation of defamatory statements, images, or other content\n\
+  \  3. Generating, promoting, or further distributing spam\n  4. Impersonating another\
+  \ individual without consent, authorization, or legal right\n  5. Representing that\
+  \ the use of Llama 2 or outputs are human-generated\n  6. Generating or facilitating\
+  \ false online engagement, including fake reviews and other means of fake online\
+  \ engagement \n  4. Fail to appropriately disclose to end users any known dangers\
+  \ of your AI system \nPlease 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: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)\
+  \ * 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:\
+  \ [[email protected]](mailto:[email protected])"
+extra_gated_fields:
+  First Name: text
+  Last Name: text
+  Date of birth: date_picker
+  Country: country
+  Affiliation: text
+  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
+pipeline_tag: text-generation
+---
+
+# mlx-community/llama2-70b-qnt4bit
+This model was converted to MLX format from [`meta-llama/Llama-2-70b-chat-hf`]().
+Refer to the [original model card](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/llama2-70b-qnt4bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,86 @@
+{
+    "vocab_size": 32000,
+    "max_position_embeddings": 4096,
+    "hidden_size": 8192,
+    "intermediate_size": 28672,
+    "num_hidden_layers": 80,
+    "num_attention_heads": 64,
+    "num_key_value_heads": 8,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-05,
+    "pretraining_tp": 1,
+    "use_cache": true,
+    "rope_theta": 10000.0,
+    "rope_scaling": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "float16",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 1,
+    "pad_token_id": null,
+    "eos_token_id": 2,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/Users/macpro/.cache/huggingface/hub/models--meta-llama--Llama-2-70b-chat-hf/snapshots/8b17e6f4e86be78cf54afd49ddb517d4e274c13f",
+    "transformers_version": "4.38.1",
+    "model_type": "llama",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    }
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9170e4865a44c21f7096e0f075fd625b46f500637c12e548ac53eefc73eea0ee
+size 5368373784

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d6126e0361109716aa8f3057388655012586b90603c16b0135b84db7a955c9
+size 5337605804

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38dc784f8b605573078a467bd57943504901294c21ab963864ce5f7b8e0488a
+size 2189270906

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:012321d7a93662d15492032d50a9be51544150bc4b480525f8145babb81fbedc
+size 5341836690

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d6ff9a80600bdf630ba2af6483e7eee9de920046e316da9d3e336224ebeb398
+size 5332398774

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5d3db59219a4ac678a7e98970ad501767334f88ac4e7fd138191a44962b0d8
+size 5294649693

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdf1b8e3d09bc6020a16a0de0bbbd2bea2e7ab9af1ccd935aa26da7113c3d038
+size 5294649675

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f0659a737a963d5203a8698252cb0ecf6154da3adc72a077d5da994e213f2b
+size 5294649647

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4bd6ea3db3abe39494c56ef38e9e8dd736cae7d804b72c40e34af1d354fe0d
+size 5294649703

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6eb5d452a5e46dbc95ad98fb84cf0bd7d3de3318efc9e1fb90d5362085bddc3
+size 1987863837

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112711e4b6a2501d20988726bdc1556800931d30b9e0abf1148e5ff4feeb761d
+size 3979241482

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}