Upload folder using huggingface_hub

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{%- for message in messages -%}\n  {%- if loop.first and messages[0]['role'] != 'system' -%}\n    {{'<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>'}}\n  {%- endif -%}\n  {%- if message['role'] == 'system' -%}\n    {{'<|im_system|>'}}\n  {%- endif -%}\n  {%- if message['role'] == 'user' -%}\n    {{'<|im_user|>'}}\n  {%- endif -%}\n  {%- if message['role'] == 'assistant' -%}\n    {{'<|im_assistant|>'}}\n  {%- endif -%}\n  {{- message['role'] -}}\n  {{'<|im_middle|>'}}\n  {%- if message['content'] is string -%}\n    {{- message['content'] + '<|im_end|>' -}}\n  {%- else -%}\n    {%- for content in message['content'] -%}\n      {%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}\n        {{'<|media_start|>image<|media_content|><|media_pad|><|media_end|>'}}\n      {%- else -%}\n        {{content['text']}}\n      {%- endif -%}\n    {%- endfor -%}\n    {{'<|im_end|>'}}\n  {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n  {{'<|im_assistant|>assistant<|im_middle|>'}}\n{%- endif -%}\n"
+}

config.json

@@ -0,0 +1,82 @@
+{
+  "architectures": [
+    "KimiVLForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "moonshotai/Kimi-VL-A3B-Thinking-2506--configuration_kimi_vl.KimiVLConfig",
+    "AutoModel": "moonshotai/Kimi-VL-A3B-Thinking-2506--modeling_kimi_vl.KimiVLForConditionalGeneration",
+    "AutoModelForCausalLM": "moonshotai/Kimi-VL-A3B-Thinking-2506--modeling_kimi_vl.KimiVLForConditionalGeneration"
+  },
+  "ignore_index": -100,
+  "media_placeholder_token_id": 163605,
+  "model_type": "kimi_vl",
+  "pad_token_id": 0,
+  "quantization_config": {
+    "group_size": 16,
+    "quant_algo": "NVFP4",
+    "quant_type": "modelopt_fp4"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "aux_loss_alpha": 0.001,
+    "bos_token_id": 163584,
+    "eos_token_id": 163585,
+    "ep_size": 1,
+    "first_k_dense_replace": 1,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 11264,
+    "kv_lora_rank": 512,
+    "max_position_embeddings": 131072,
+    "model_type": "deepseek_v3",
+    "moe_intermediate_size": 1408,
+    "moe_layer_freq": 1,
+    "n_group": 1,
+    "n_routed_experts": 64,
+    "n_shared_experts": 2,
+    "norm_topk_prob": true,
+    "num_attention_heads": 16,
+    "num_experts_per_tok": 6,
+    "num_hidden_layers": 27,
+    "num_key_value_heads": 16,
+    "num_nextn_predict_layers": 1,
+    "pad_token_id": 163839,
+    "pretraining_tp": 1,
+    "q_lora_rank": null,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 800000.0,
+    "routed_scaling_factor": 2.446,
+    "scoring_func": "sigmoid",
+    "seq_aux": true,
+    "topk_group": 1,
+    "topk_method": "noaux_tc",
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "v_head_dim": 128,
+    "vocab_size": 163840
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "vision_config": {
+    "hidden_size": 1152,
+    "init_pos_emb_height": 64,
+    "init_pos_emb_width": 64,
+    "intermediate_size": 4304,
+    "merge_kernel_size": [
+      2,
+      2
+    ],
+    "model_type": "moonvit",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16"
+  },
+  "vocab_size": 163840
+}

hf_quant_config.json

@@ -0,0 +1,42 @@
+{
+  "producer": {
+    "name": "modelopt",
+    "version": "0.39.0"
+  },
+  "quantization": {
+    "quant_algo": "NVFP4",
+    "kv_cache_quant_algo": null,
+    "group_size": 16,
+    "exclude_modules": [
+      "lm_head",
+      "model.layers.0.self_attn*",
+      "model.layers.1.self_attn*",
+      "model.layers.10.self_attn*",
+      "model.layers.11.self_attn*",
+      "model.layers.12.self_attn*",
+      "model.layers.13.self_attn*",
+      "model.layers.14.self_attn*",
+      "model.layers.15.self_attn*",
+      "model.layers.16.self_attn*",
+      "model.layers.17.self_attn*",
+      "model.layers.18.self_attn*",
+      "model.layers.19.self_attn*",
+      "model.layers.2.self_attn*",
+      "model.layers.20.self_attn*",
+      "model.layers.21.self_attn*",
+      "model.layers.22.self_attn*",
+      "model.layers.23.self_attn*",
+      "model.layers.24.self_attn*",
+      "model.layers.25.self_attn*",
+      "model.layers.26.self_attn*",
+      "model.layers.3.self_attn*",
+      "model.layers.4.self_attn*",
+      "model.layers.5.self_attn*",
+      "model.layers.6.self_attn*",
+      "model.layers.7.self_attn*",
+      "model.layers.8.self_attn*",
+      "model.layers.9.self_attn*",
+      "lm_head"
+    ]
+  }
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846282b96c84c31112932dd88ba9ac160963fb7f3ffeffb67f12715af3dc3be7
+size 5000886552

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8dacaa71e958f216e810b9763c21b04cce172f2292a0e40be4068e7f25cfef3
+size 4812303464

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836c6d6df4d3755775e5d8c619daf3512c5b0af87804b426e8c09fc146ba2c4f
+size 671088752

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "moonshotai/Kimi-VL-A3B-Thinking-2506--image_processing_kimi_vl.KimiVLImageProcessor",
+    "AutoProcessor": "moonshotai/Kimi-VL-A3B-Thinking-2506--processing_kimi_vl.KimiVLProcessor"
+  },
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "KimiVLImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "in_token_limit": 16384,
+  "merge_kernel_size": [
+    2,
+    2
+  ],
+  "num_pooled_tokens": 1024,
+  "pad_input": true,
+  "patch_size": 14,
+  "processor_class": "KimiVLProcessor"
+}

special_tokens_map.json

@@ -0,0 +1,41 @@
+{
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_user|>",
+    "<|im_assistant|>",
+    "<|im_system|>",
+    "<|im_middle|>",
+    "<|media_start|>",
+    "<|media_content|>",
+    "<|media_end|>",
+    "<|media_pad|>"
+  ],
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[EOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tiktoken.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c497a7469b33ced9c38afb1ad6e47f03f5e5dc05f15930799210ec050c5103
+size 2795286

tokenizer_config.json

@@ -0,0 +1,135 @@
+{
+  "added_tokens_decoder": {
+    "163584": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163585": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163586": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163587": {
+      "content": "<|im_user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163588": {
+      "content": "<|im_assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163594": {
+      "content": "<|im_system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163601": {
+      "content": "<|im_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163602": {
+      "content": "<|media_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163603": {
+      "content": "<|media_content|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163604": {
+      "content": "<|media_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163605": {
+      "content": "<|media_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163838": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163839": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_user|>",
+    "<|im_assistant|>",
+    "<|im_system|>",
+    "<|im_middle|>",
+    "<|media_start|>",
+    "<|media_content|>",
+    "<|media_end|>",
+    "<|media_pad|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "moonshotai/Kimi-VL-A3B-Thinking-2506--tokenization_moonshot.TikTokenTokenizer",
+      null
+    ]
+  },
+  "bos_token": "[BOS]",
+  "chat_template": "{%- for message in messages -%}\n  {%- if loop.first and messages[0]['role'] != 'system' -%}\n    {{'<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>'}}\n  {%- endif -%}\n  {%- if message['role'] == 'system' -%}\n    {{'<|im_system|>'}}\n  {%- endif -%}\n  {%- if message['role'] == 'user' -%}\n    {{'<|im_user|>'}}\n  {%- endif -%}\n  {%- if message['role'] == 'assistant' -%}\n    {{'<|im_assistant|>'}}\n  {%- endif -%}\n  {{- message['role'] -}}\n  {{'<|im_middle|>'}}\n  {%- if message['content'] is string -%}\n    {{- message['content'] + '<|im_end|>' -}}\n  {%- else -%}\n    {%- for content in message['content'] -%}\n      {%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}\n        {{'<|media_start|>image<|media_content|><|media_pad|><|media_end|>'}}\n      {%- else -%}\n        {{content['text']}}\n      {%- endif -%}\n    {%- endfor -%}\n    {{'<|im_end|>'}}\n  {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n  {{'<|im_assistant|>assistant<|im_middle|>'}}\n{%- endif -%}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "extra_special_tokens": {},
+  "model_max_length": 1048576,
+  "pad_token": "[PAD]",
+  "processor_class": "KimiVLProcessor",
+  "tokenizer_class": "TikTokenTokenizer",
+  "unk_token": "[UNK]"
+}

vision_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622d06355905894c2f218c3909ea577c44941f2814b2c067a4365cf362a802da
+size 895130216