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 +1,3 @@
+---
+license: llama4
+---

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 +1,372 @@
+{
+  "architectures": [
+    "Llama4ForConditionalGeneration"
+  ],
+  "boi_token_index": 200080,
+  "eoi_token_index": 200081,
+  "image_token_index": 200092,
+  "model_type": "llama4",
+  "quantization_config": {
+    "algo_config": null,
+    "exclude": [
+      "vision_model.patch_embedding.linear",
+      "vision_model.model.layers.0.self_attn.q_proj",
+      "vision_model.model.layers.0.self_attn.k_proj",
+      "vision_model.model.layers.0.self_attn.v_proj",
+      "vision_model.model.layers.0.self_attn.o_proj",
+      "vision_model.model.layers.0.mlp.fc1",
+      "vision_model.model.layers.0.mlp.fc2",
+      "vision_model.model.layers.1.self_attn.q_proj",
+      "vision_model.model.layers.1.self_attn.k_proj",
+      "vision_model.model.layers.1.self_attn.v_proj",
+      "vision_model.model.layers.1.self_attn.o_proj",
+      "vision_model.model.layers.1.mlp.fc1",
+      "vision_model.model.layers.1.mlp.fc2",
+      "vision_model.vision_adapter.mlp.fc1",
+      "vision_model.vision_adapter.mlp.fc2",
+      "multi_modal_projector.linear_1",
+      "language_model.model.layers.0.self_attn.q_proj",
+      "language_model.model.layers.0.self_attn.k_proj",
+      "language_model.model.layers.0.self_attn.v_proj",
+      "language_model.model.layers.0.self_attn.o_proj",
+      "language_model.model.layers.0.feed_forward.router",
+      "language_model.model.layers.1.self_attn.q_proj",
+      "language_model.model.layers.1.self_attn.k_proj",
+      "language_model.model.layers.1.self_attn.v_proj",
+      "language_model.model.layers.1.self_attn.o_proj",
+      "language_model.model.layers.1.feed_forward.router",
+      "language_model.lm_head"
+    ],
+    "export": {
+      "kv_cache_group": [
+        "*language_model.*k_proj",
+        "*language_model.*v_proj"
+      ],
+      "min_kv_scale": 0.0,
+      "pack_method": "reorder",
+      "weight_format": "real_quantized",
+      "weight_merge_groups": null
+    },
+    "global_quant_config": {
+      "bias": null,
+      "input_tensors": {
+        "ch_axis": -1,
+        "dtype": "fp4",
+        "group_size": 32,
+        "is_dynamic": true,
+        "is_mx_scale_constraint": false,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerBlockMXObserver",
+        "qscheme": "per_group",
+        "round_method": "half_even",
+        "scale_calculation_mode": "even",
+        "scale_format": "e8m0",
+        "scale_type": "float",
+        "symmetric": null
+      },
+      "output_tensors": null,
+      "target_device": null,
+      "weight": {
+        "ch_axis": -1,
+        "dtype": "fp4",
+        "group_size": 32,
+        "is_dynamic": false,
+        "is_mx_scale_constraint": false,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerBlockMXObserver",
+        "qscheme": "per_group",
+        "round_method": "half_even",
+        "scale_calculation_mode": "even",
+        "scale_format": "e8m0",
+        "scale_type": "float",
+        "symmetric": null
+      }
+    },
+    "layer_quant_config": {
+      "*language_model.*k_proj": {
+        "bias": null,
+        "input_tensors": {
+          "ch_axis": -1,
+          "dtype": "fp4",
+          "group_size": 32,
+          "is_dynamic": true,
+          "is_mx_scale_constraint": false,
+          "is_scale_quant": false,
+          "mx_element_dtype": null,
+          "observer_cls": "PerBlockMXObserver",
+          "qscheme": "per_group",
+          "round_method": "half_even",
+          "scale_calculation_mode": "even",
+          "scale_format": "e8m0",
+          "scale_type": "float",
+          "symmetric": null
+        },
+        "output_tensors": {
+          "ch_axis": null,
+          "dtype": "fp8_e4m3",
+          "group_size": null,
+          "is_dynamic": false,
+          "is_mx_scale_constraint": null,
+          "is_scale_quant": false,
+          "mx_element_dtype": null,
+          "observer_cls": "PerTensorMinMaxObserver",
+          "qscheme": "per_tensor",
+          "round_method": null,
+          "scale_calculation_mode": null,
+          "scale_format": null,
+          "scale_type": null,
+          "symmetric": null
+        },
+        "target_device": null,
+        "weight": {
+          "ch_axis": -1,
+          "dtype": "fp4",
+          "group_size": 32,
+          "is_dynamic": false,
+          "is_mx_scale_constraint": false,
+          "is_scale_quant": false,
+          "mx_element_dtype": null,
+          "observer_cls": "PerBlockMXObserver",
+          "qscheme": "per_group",
+          "round_method": "half_even",
+          "scale_calculation_mode": "even",
+          "scale_format": "e8m0",
+          "scale_type": "float",
+          "symmetric": null
+        }
+      },
+      "*language_model.*v_proj": {
+        "bias": null,
+        "input_tensors": {
+          "ch_axis": -1,
+          "dtype": "fp4",
+          "group_size": 32,
+          "is_dynamic": true,
+          "is_mx_scale_constraint": false,
+          "is_scale_quant": false,
+          "mx_element_dtype": null,
+          "observer_cls": "PerBlockMXObserver",
+          "qscheme": "per_group",
+          "round_method": "half_even",
+          "scale_calculation_mode": "even",
+          "scale_format": "e8m0",
+          "scale_type": "float",
+          "symmetric": null
+        },
+        "output_tensors": {
+          "ch_axis": null,
+          "dtype": "fp8_e4m3",
+          "group_size": null,
+          "is_dynamic": false,
+          "is_mx_scale_constraint": null,
+          "is_scale_quant": false,
+          "mx_element_dtype": null,
+          "observer_cls": "PerTensorMinMaxObserver",
+          "qscheme": "per_tensor",
+          "round_method": null,
+          "scale_calculation_mode": null,
+          "scale_format": null,
+          "scale_type": null,
+          "symmetric": null
+        },
+        "target_device": null,
+        "weight": {
+          "ch_axis": -1,
+          "dtype": "fp4",
+          "group_size": 32,
+          "is_dynamic": false,
+          "is_mx_scale_constraint": false,
+          "is_scale_quant": false,
+          "mx_element_dtype": null,
+          "observer_cls": "PerBlockMXObserver",
+          "qscheme": "per_group",
+          "round_method": "half_even",
+          "scale_calculation_mode": "even",
+          "scale_format": "e8m0",
+          "scale_type": "float",
+          "symmetric": null
+        }
+      }
+    },
+    "layer_type_quant_config": {},
+    "quant_method": "quark",
+    "quant_mode": "eager_mode",
+    "softmax_quant_spec": null
+  },
+  "text_config": {
+    "_attn_implementation_autoset": true,
+    "attention_bias": false,
+    "attention_chunk_size": 8192,
+    "attention_dropout": 0.0,
+    "attn_scale": 0.1,
+    "attn_temperature_tuning": 4,
+    "bos_token_id": 200000,
+    "eos_token_id": [
+      200001,
+      200007,
+      200008
+    ],
+    "floor_scale": 8192,
+    "for_llm_compressor": false,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "interleave_moe_layer_step": 1,
+    "intermediate_size": 8192,
+    "intermediate_size_mlp": 16384,
+    "max_position_embeddings": 10485760,
+    "model_type": "llama4_text",
+    "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
+    ],
+    "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
+    ],
+    "num_attention_heads": 40,
+    "num_experts_per_tok": 1,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 8,
+    "num_local_experts": 16,
+    "output_router_logits": false,
+    "pad_token_id": 200018,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 16.0,
+      "high_freq_factor": 1.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "router_aux_loss_coef": 0.001,
+    "router_jitter_noise": 0.0,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_qk_norm": true,
+    "vocab_size": 202048
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1408,
+    "image_size": 336,
+    "initializer_range": 0.02,
+    "intermediate_size": 5632,
+    "model_type": "llama4_vision_model",
+    "multi_modal_projector_bias": false,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_size": 14,
+    "pixel_shuffle_ratio": 0.5,
+    "projector_dropout": 0.0,
+    "projector_input_dim": 4096,
+    "projector_output_dim": 4096,
+    "rope_theta": 10000,
+    "vision_feature_layer": -1,
+    "vision_feature_select_strategy": "default",
+    "vision_output_dim": 4096
+  }
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "attn_implementation": "eager",
+  "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"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd9f0c83417d33dff22c05fb1d7a329c11e55dbf88e21cd53ca45f0190f302e
+size 3462246892

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6c58ff49f793600ee07f336896f9b4e1432eef118f55652519e36161e3cb6b
+size 1351738668

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2246b5deed41f5a9e859f1c8aae777136348ef0f8f39e679ae3e1167ad95b3
+size 10344

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a464e8b9d4ee51a76765c231720b677c1c2fe9efde77b306310d9d5a846219
+size 2068971632

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {}, "weight_map": {"language_model.lm_head.weight": "model-00004-of-00004.safetensors", "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.0.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.0.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.0.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.0.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.0.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.1.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.1.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.1.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.1.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.1.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.10.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.10.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.10.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.10.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.10.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.10.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.11.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.11.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.11.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.11.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.11.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.11.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.12.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.12.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.12.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.12.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.12.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.12.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.13.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.13.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.13.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.13.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.13.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.13.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.14.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.14.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.14.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.14.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.14.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.14.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.15.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.15.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.15.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.15.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.15.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.2.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.2.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.2.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.2.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.2.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.2.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.3.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.3.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.3.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.3.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.3.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.3.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.4.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.4.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.4.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.4.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.4.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.4.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.5.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.5.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.5.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.5.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.5.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.5.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.6.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.6.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.6.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.6.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.6.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.6.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.7.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.7.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.7.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.7.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.7.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.7.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.8.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.8.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.8.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.8.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.8.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.8.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.9.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.9.down_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.9.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.9.gate_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.9.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.experts.9.up_proj.weight_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.feed_forward.router.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.0.feed_forward.shared_expert.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.0.feed_forward.shared_expert.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.0.feed_forward.shared_expert.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.0.feed_forward.shared_expert.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.0.feed_forward.shared_expert.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.0.feed_forward.shared_expert.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.0.self_attn.k_proj.output_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.v_proj.output_scale": "model-00001-of-00004.safetensors", "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.0.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.0.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.0.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.0.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.0.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.0.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.1.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.1.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.1.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.1.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.1.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.1.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.10.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.10.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.10.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.10.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.10.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.10.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.11.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.11.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.11.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.11.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.11.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.11.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.12.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.12.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.12.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.12.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.12.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.12.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.13.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.13.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.13.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.13.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.13.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.13.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.14.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.14.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.14.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.14.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.14.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.14.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.15.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.15.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.15.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.15.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.15.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.15.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.2.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.2.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.2.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.2.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.2.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.3.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.3.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.3.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.3.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.3.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.4.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.4.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.4.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.4.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.4.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.5.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.5.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.5.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.5.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.5.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.6.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.6.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.6.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.6.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.6.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.7.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.7.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.7.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.7.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.7.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.8.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.8.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.8.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.8.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.8.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.8.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.9.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.9.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.9.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.9.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.9.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.experts.9.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.router.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.shared_expert.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.shared_expert.down_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.shared_expert.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.shared_expert.gate_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.shared_expert.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.feed_forward.shared_expert.up_proj.weight_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.layers.1.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors", "language_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.model.norm.weight": "model-00003-of-00004.safetensors", "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors", "vision_model.class_embedding": "model-00001-of-00004.safetensors", "vision_model.layernorm_post.bias": "model-00001-of-00004.safetensors", "vision_model.layernorm_post.weight": "model-00001-of-00004.safetensors", "vision_model.layernorm_pre.bias": "model-00001-of-00004.safetensors", "vision_model.layernorm_pre.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.self_attn.o_proj.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "vision_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "vision_model.patch_embedding.linear.weight": "model-00001-of-00004.safetensors", "vision_model.positional_embedding_vlm": "model-00001-of-00004.safetensors", "vision_model.vision_adapter.mlp.fc1.weight": "model-00001-of-00004.safetensors", "vision_model.vision_adapter.mlp.fc2.weight": "model-00001-of-00004.safetensors"}}

preprocessor_config.json

@@ -0,0 +1,33 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Llama4ImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_patches": 16,
+  "processor_class": "Llama4Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "resize_to_max_canvas": false,
+  "return_tensors": null,
+  "size": {
+    "height": 336,
+    "width": 336
+  }
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "fake_image_token": "<|image|>",
+  "image_token": "<|image|>",
+  "patch_size": 14,
+  "processor_class": "Llama4Processor"
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172c9eb4beafc72601690da3ccfcede5c2e6806a8d5ec1fca33e22acea8023a4
+size 27948578