Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,189 @@
+---
+library_name: transformers
+language:
+- ar
+- de
+- en
+- es
+- fr
+- hi
+- id
+- it
+- pt
+- th
+- tl
+- vi
+base_model:
+- meta-llama/Llama-4-Scout-17B-16E
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-4
+- mlx
+extra_gated_prompt: '**LLAMA 4 COMMUNITY LICENSE AGREEMENT**
+
+  Llama 4 Version Effective Date: April 5, 2025
+
+  "**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 4 distributed by Meta at [https://www.llama.com/docs/overview](https://llama.com/docs/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 4**" 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](https://www.llama.com/llama-downloads).
+
+  "**Llama Materials**" means, collectively, Meta’s proprietary Llama 4 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 4 is licensed under the Llama 4 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/llama4/use-policy](https://www.llama.com/llama4/use-policy)),
+  which is hereby incorporated by reference into this Agreement.        2\. **Additional
+  Commercial Terms**. If, on the Llama 4 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/](https://about.meta.com/brand/resources/meta/company-brand/)[)](https://en.facebookbrand.com/).
+  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 4 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.'
+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
+extra_gated_heading: Please be sure to provide your full legal name, date of birth,
+  and full organization name with all corporate identifiers. Avoid the use of acronyms
+  and special characters. Failure to follow these instructions may prevent you from
+  accessing this model and others on Hugging Face. You will not have the ability to
+  edit this form after submission, so please ensure all information is accurate.
+license: other
+license_name: llama4
+---
+
+# mlx-community/meta-llama-Llama-4-Scout-17B-16E-Instruct-bf16
+This model was converted to MLX format from [`meta-llama/Llama-4-Scout-17B-16E-Instruct`]() using mlx-vlm version **0.1.21**.
+Refer to the [original model card](https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model mlx-community/meta-llama-Llama-4-Scout-17B-16E-Instruct-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
+```

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}    \n    {%- if messages[0]['content'] is string %}\n        {%- set system_message = messages[0]['content']|trim %}\n    {%- else %}\n        {#- FIXME: The processor requires an array, always. #}\n        {%- set system_message = messages[0]['content'][0]['text']|trim %}\n    {%- endif %}\n    {%- set messages = messages[1:] %}\n    {%- set user_supplied_system_message = true %}\n{%- else %}\n    {%- set system_message = \"\" %}\n    {%- set user_supplied_system_message = false %}\n{%- endif %}\n\n{#- System message if the user supplied one #}\n{%- if user_supplied_system_message %}\n    {{- \"<|header_start|>system<|header_end|>\\n\\n\" }}\n    {%- if tools is not none %}\n        {{- \"Environment: ipython\\n\" }}\n    {%- endif %}\n    {%- if tools is not none and not tools_in_user_message %}\n        {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n        {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n        {{- \"Do not use variables.\\n\\n\" }}\n        {%- for t in tools %}\n            {{- t | tojson(indent=4) }}\n            {{- \"\\n\\n\" }}\n        {%- endfor %}\n    {%- endif %}\n    {{- system_message }}\n    {{- \"<|eot|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|header_start|>user<|header_end|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|header_start|>' + message['role'] + '<|header_end|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- \"<|eot|>\" }}\n    {%- elif 'tool_calls' in message and message.tool_calls|length > 0 %}\n       {{- '<|header_start|>assistant<|header_end|>\\n\\n' -}}\n       {{- '<|python_start|>' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n       {{- '<|python_end|>' }}\n        {%- for tool_call in message.tool_calls %}\n           {{- '{\"name\": \"' + tool_call.function.name + '\", ' }}\n           {{- '\"parameters\": ' }}\n           {{- tool_call.function.arguments | tojson }}\n           {{- \"}\" }}\n        {%- endfor %}\n       {{- \"<|eot|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|header_start|>ipython<|header_end|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|header_start|>assistant<|header_end|>\\n\\n' }}\n{%- endif %}\n"
+}

config.json

@@ -0,0 +1,356 @@
+{
+    "_attn_implementation_autoset": false,
+    "add_cross_attention": false,
+    "architectures": [
+        "Llama4ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "boi_token_index": 200080,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eoi_token_index": 200081,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "image_token_index": 200092,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "llama4",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "text_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": "bfloat16",
+        "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": null,
+        "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": 200000,
+        "pad_token_id": 200018,
+        "eos_token_id": [
+            200001,
+            200007,
+            200008
+        ],
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "_attn_implementation_autoset": true,
+        "attention_bias": false,
+        "for_llm_compressor": false,
+        "model_type": "llama4_text",
+        "attn_temperature_tuning": 4,
+        "attn_scale": 0.1,
+        "floor_scale": 8192,
+        "vocab_size": 202048,
+        "max_position_embeddings": 10485760,
+        "hidden_size": 5120,
+        "intermediate_size": 8192,
+        "intermediate_size_mlp": 16384,
+        "num_hidden_layers": 48,
+        "num_attention_heads": 40,
+        "rope_scaling": {
+            "factor": 8.0,
+            "high_freq_factor": 4.0,
+            "low_freq_factor": 1.0,
+            "original_max_position_embeddings": 8192,
+            "rope_type": "llama3"
+        },
+        "num_key_value_heads": 8,
+        "hidden_act": "silu",
+        "initializer_range": 0.02,
+        "rms_norm_eps": 1e-05,
+        "use_cache": true,
+        "rope_theta": 500000.0,
+        "attention_dropout": 0.0,
+        "head_dim": 128,
+        "use_qk_norm": true,
+        "num_experts_per_tok": 1,
+        "num_local_experts": 16,
+        "output_router_logits": false,
+        "router_aux_loss_coef": 0.001,
+        "router_jitter_noise": 0.0,
+        "no_rope_layers": [
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0
+        ],
+        "interleave_moe_layer_step": 1,
+        "moe_layers": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15,
+            16,
+            17,
+            18,
+            19,
+            20,
+            21,
+            22,
+            23,
+            24,
+            25,
+            26,
+            27,
+            28,
+            29,
+            30,
+            31,
+            32,
+            33,
+            34,
+            35,
+            36,
+            37,
+            38,
+            39,
+            40,
+            41,
+            42,
+            43,
+            44,
+            45,
+            46,
+            47
+        ],
+        "attention_chunk_size": 8192
+    },
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.51.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vision_config": {
+        "hidden_size": 1408,
+        "hidden_act": "gelu",
+        "num_hidden_layers": 34,
+        "num_channels": 3,
+        "intermediate_size": 5632,
+        "image_size": 336,
+        "vision_output_dim": 4096,
+        "patch_size": 14,
+        "norm_eps": 1e-05,
+        "num_attention_heads": 16,
+        "initializer_range": 0.02,
+        "pixel_shuffle_ratio": 0.5,
+        "projector_input_dim": 4096,
+        "projector_output_dim": 4096,
+        "multi_modal_projector_bias": false,
+        "projector_dropout": 0.0,
+        "attention_dropout": 0.0,
+        "vision_feature_layer": -1,
+        "vision_feature_select_strategy": "default",
+        "rope_theta": 10000,
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": null,
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "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": null,
+        "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": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "_attn_implementation_autoset": true,
+        "model_type": "llama4_vision_model"
+    }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 200000,
+  "do_sample": true,
+  "eos_token_id": [
+    200001,
+    200007,
+    200008
+  ],
+  "pad_token_id": 200018,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.0.dev0"
+}

model-00001-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191db7fbcfcee71ed768447164a4c37d46dfd8143473181537a4ecae04eeb4a7
+size 5280912197

model-00002-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:494191a98f07040f240bbdb0b9ac442426a178fa3a52c8f297546b7eb3e717c5
+size 4404205351

model-00003-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a870eca768075928e2779aabe92aedfa81d44f3e63f2575e5a112f767b1f4061
+size 4404205373

model-00004-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ebce21aab1ad65aaba116a3c40c41a86e0efa1eee524f549c7ad6f0f8d97a1
+size 4404205357

model-00005-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7389e9b123c6e79d4fa51ad68743bac9b0a1f95980406ee768d5c34b6750a39
+size 4404205373

model-00006-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e9200b9501f1269ece05ba64fc39bbe40a1d5b2864988659fb54b639be1333a
+size 4404205373

model-00007-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb00c1f42b8295b99b698bfc16a28c54557321ff3c9974c994ea2434387ae3d
+size 4404205373

model-00008-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83886981cfd2c159a0b8867ca052437d429c6d5d2ad0e681b672f28356c0468c
+size 4404205359

model-00009-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9942af831d53db7d6482f2818469e57e7832664629b9a51711784b3d76c9b8d4
+size 4404205373

model-00010-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83da7068af139fa285c26fc39da5857cbbdd1384000be23dc6cb3b56445d663
+size 4404205373

model-00011-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ca9b84504bdae880144cf9a1ed7c9829a94114c99d3752b35a6352a92b839c
+size 4404205358

model-00012-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef077b73233558956ca23f5d9506cedc7d7ec97705db40efa9a4606722c4388
+size 4404205386

model-00013-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88613dece965dbafe2906516754141a7e666fcc418530e5f69436df0c1676fc9
+size 4404205386

model-00014-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a6c0bda272f2c3027e9e7cda25e4c6f0bbf87230372193c615d14190f3b11bf
+size 4404205386

model-00015-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becde0c15df82a086581c5c52816b35008c9e663e0bb923bc7828de1e80a7a50
+size 4404205386

model-00016-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c40bfae5315fb5517e481d2577c796f9b5527ff4e6f37c5741997ac9c654810
+size 4404205380

model-00017-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b315d906dbeb113bf0eb1f1584fa4fa6d4c6bf6aa465bfb2f8a1334c84ff618c
+size 4404205386

model-00018-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa92a6ebdd31e0453f6f2347263885b8351363a487f63deb425758b0c035b2e3
+size 4404205386

model-00019-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c03211a7f7e065d44cc6691edaadacf1f81a17cbef4208bd0e67bcf7396eb4
+size 4404205386

model-00020-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d62ec1a1176017fec3ae9346ade0249043ef29a5ea582ddb945df684d3f2fb
+size 4404205386

model-00021-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e538ef41827dbd85c80938495ae3b2391742a524447e1ed8ec1761331b6000c6
+size 4404205382

model-00022-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3545937f6081e05843a83bcae405e760f3a196a9669f50dd85e44b516eeccbe0
+size 4404205386

model-00023-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc12ca2eef3d546d73b7e57651b2db413404325535bdaaedffce334ac6f03328
+size 4404205386

model-00024-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0dd167513ac6e1cffcebb07bb4b4749906174fcfd192bf5b946d93d754da39
+size 4404205386

model-00025-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb4c7f75463cfac2b57aff83a62aa4cd445ae999b630664720387a28418ce9d
+size 4404205378

model-00026-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff3a8e09d08aa341582cc488f8271f866328bae21c8e3b65326e197aa81793df
+size 4404205378

model-00027-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec61d2cc483fba8af179540c9f2e74d2d907f1f7b29d99033c01773b4e65a1f
+size 4404205386

model-00028-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c9e7c630e6f230592beadd92939b81fc09dc9f2c0b4c04dc50e9e13b381dca3
+size 4404205386

model-00029-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82aa4740cc2958a2a96b5916bc23332e82965de3a87685d9513733a60024af8
+size 4404205378

model-00030-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa415d1fd8d29687b1a8251daf5ed0ccd7d3e752e54f78ac63102f204f1aa442
+size 4404205386

model-00031-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f222dee9e5057e031d811bd21cc1e05851eda9b9e05e029ed64b46c7d2063072
+size 4404205386

model-00032-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f648690dc71a414d053d273afe389eac9250aefe3eb5966e33d8d67888f317
+size 4404205386

model-00033-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aff1948dcc6c4de251ab136527d1c9de8a294a3916c9d141682a54f3e73d2e1
+size 4404205386

model-00034-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b98c2a895425dd759f82809a498d5eb4551afbed3115fc49bd782286bcb5532
+size 4404205386

model-00035-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9058b630e025d0d454a71dc8547dd4101d2ef7ed98ca5747aef6f97f040c451d
+size 4404205386

model-00036-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd22c61bce5bfaa29a39e52fb5bff8d7a9f9a3b99d303f10d3e0c4e458bd69e
+size 4404205374

model-00037-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d587d16a111270f9fee6e48ffe9fb556218f34fca7bab687f1faf97f9faf5b9
+size 4404205386

model-00038-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d6865bcef1d971100b5e827baeddfd2a37947f2d6271b7b3228defee3634c3
+size 4404205386

model-00039-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea327ba4ea389a117b2c97caa877e4805fb4d9da420fc317984a61a2474ac13
+size 4404205386

model-00040-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f9691c11726db0d916194cae9a95a8ea0f0234bb6542bad232a44e29e5d6a4
+size 4404205386

model-00041-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93e273765cba5a96f608ddcc81a1e4473488ae52cf1fd8039839964d96671ba
+size 4404205386

model-00042-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695bf4ac9dffc7fa93618784147ee17256d87af0d4c042d00e2607042f48038b
+size 4404205364

model-00043-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9c3ca119030a35b0da7f243d9d07ae5ce8dd6ded644c999353d944f3cb6c01
+size 4404205374

model-00044-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602d5db956e67da207e3791e7208d011cba78df7832e34ea446463ac667aa44b
+size 4404205386

model-00045-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba416e7fae93d870bffb68790b3ba2c76279bdde0452f04bbdc2ca1805c092f5
+size 4404205386