Upload instruct model files

chat_template.jinja

@@ -0,0 +1,111 @@
+{{- bos_token }}
+{%- if custom_tools is defined and custom_tools%}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if tools is defined and tools %}
+    {%- set tool_definition = tool_definition ~ (tools | tojson(indent=4)) %}
+{%- else %}
+    {%- set tools = none %}
+{%- endif %}
+
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set user_provided_system_message = true %}
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content']|trim %}
+    {%- else %}
+        {%- set system_message = messages[0]['content'][0]['text']|trim %}
+    {%- endif %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- if tools is not none  %}
+        {#- Since not system_message was provided by user, if tool is provided, system_message is now default tool system message #}
+        {#- This system message is from llama website:https://www.llama.com/docs/model-cards-and-prompt-formats/llama4/  #}
+        {%- set system_message = "You are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n" %}
+    {%- else %}
+        {%- set system_message = "" %}
+    {%- endif %}
+{%- endif %}
+{#- Now writing the system message: use the user provided system message if user_provided_system_message, else default tool system message if tools presented #}
+{%- if system_message %}
+    {#- always use user provided system message to override default tool system message #}
+    {{- "<|header_start|>system<|header_end|>\n\n" }}
+    {{- system_message }}
+    {%- if user_provided_system_message and tools %}
+        {{- "\nHere is a list of functions in JSON format that you can invoke. Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\n" }}
+        {{- tool_definition -}}
+        {%- elif tool_definition %}
+        {{- tool_definition -}}
+    {%- endif %}
+    {{- "<|eot|>" }}
+{%- endif %}
+
+{#- Now deal with all other messages #}
+{%- for message in messages %}
+    {#- Base case: messages that are not from tool role and has empty tool_call list  #}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or ('tool_calls' in message and  message.tool_calls|length != 0 )) %}
+        {{- '<|header_start|>' + message['role'] + '<|header_end|>\n\n' }}
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- else %}
+            {%- for content in message['content'] %}
+                {%- if content['type'] == 'image' %}
+                    {{- '<|image|>' }}
+                {%- elif content['type'] == 'text' %}
+                    {{- content['text'] | trim }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {{- "<|eot|>" }}
+    {#- Tool case: messages has non-empty tool_call list, must from assistant #}
+    {%- elif 'tool_calls' in message %}
+        {#- assume tool_calls are always coming from assistant #}
+        {%- if message.role == 'assistant' %}
+            {{- '<|header_start|>assistant<|header_end|>\n\n' -}}
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- else %}
+            {%- for content in message['content'] %}
+                {%- if content['type'] == 'image' %}
+                    {{- '<|image|>' }}
+                {%- elif content['type'] == 'text' %}
+                    {{- content['text'] }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+            {{- "[" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+                {{-  tool_call.name + '(' -}}
+            {%- for param in tool_call.arguments %}
+                {{- param + '="' -}}
+                {{- "%s" | format(tool_call.arguments[param]) -}}
+                {{- '"' -}}
+                {% if not loop.last %}, {% endif %}
+            {%- endfor %}
+            {{- ')' -}}
+            {% if not loop.last %}, {% endif %}
+        {%- endfor %}
+        {{- "]<|eot|>" }}
+{%- endif %}
+{#- Tool_response case: messages are from tool_response  #}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|header_start|>ipython<|header_end|>\n\n" }}
+        {%- if message.content is string %}
+            {{-  message.content  | tojson }}
+        {%- else %}
+            {%- for content in message['content']  %}
+                {%- if content['type']  == 'text' %}
+                    {{-  content['text'] | tojson }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- "<|eot|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|header_start|>assistant<|header_end|>\n\n' }}
+{%- endif %}

config.json

@@ -497,14 +497,12 @@
     "quantization_status": "compressed"
   },
   "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,
+    "attn_temperature_tuning": true,
     "bos_token_id": 200000,
-    "cache_implementation": "hybrid",
     "eos_token_id": [
       200001,
       200007,
@@ -519,7 +517,57 @@
     "interleave_moe_layer_step": 1,
     "intermediate_size": 8192,
     "intermediate_size_mlp": 16384,
-    "max_position_embeddings": 262144,
+    "layer_types": [
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "chunked_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 10485760,
     "model_type": "llama4_text",
     "moe_layers": [
       0,
@@ -646,9 +694,8 @@
   },
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.53.1",
   "vision_config": {
-    "_attn_implementation_autoset": true,
     "attention_dropout": 0.0,
     "hidden_act": "gelu",
     "hidden_size": 1408,

generation_config.json

@@ -9,5 +9,5 @@
   "pad_token_id": 200018,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.53.1"
 }

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc7b88bc57571ff82228e80c6be212280ef638d2dd9d258d88a75f339c6a9a8b
+oid sha256:a4da8407d857d17bcd05231f7e41c35bcc293e54c163849297374ea68a2dac7d
 size 4997823520

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1bac3c424c76ef64a7857cd426bd0d358ceba1244c3dc4131f7deb2feb4d970
+oid sha256:6bdc7cf9113309ed9dd69745974862104b833c126d55472680df1570249a3c53
 size 4989453616

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91de6560623a44a52062cecaaa3dbc3ebe36258b4f5262e8ed53c60697b432f0
+oid sha256:d725a42361ae6254b4f26eb52714ad9b67dec525738a40d027f84ecda86d259f
 size 4986832064

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5967e8cd6d63de00c2b7820fb5b857db80584deaacb74d8ab04d37b036e5c9fd
+oid sha256:e0892df63ced6ea6416d308631c12be54ea9d26d2d6e73f90f7b938c9baf3af6
 size 4986832528

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41351802c2cf716aac5bc4e8c8cf33488fe286bf66023c53960276410e07877
+oid sha256:c0bacd195d34c2a6f7592b98cb9e646e4480dcdf638766c29f31476c97f04b27
 size 4999758176

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb387ad077829e40dde85b4da96b5fe76d18ce14ce0fe3fd5c883e04bda029b
+oid sha256:da3cb51b52e3899d605846550ab2dcd0a83085e9b758a3b946f3d38d56f83cbe
 size 4989454400

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b67a56a5fc6b2c6caf546145878b757a29d8a5e51359d3002ea4ddc8fea9ec
+oid sha256:0816f5416e8154f3e420c3b5947bea9d20097ed2c4855d51d7b51afaa149d549
 size 4986832856

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03115aa98c59a7fab0180a2be0b00b655c2f0ba3b3d71e4fb56126820fc2a064
+oid sha256:4edd3862bebdea962395292445eb2ab691c451c1e156900ce490f5dc9dbd5c8e
 size 4986832864

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6304b9722fedc44e3922ff72f4a1745b0fec866f3d44860fb6fc93eb2619537a
+oid sha256:d00f7112cbeeee08dbc5d71ea183aa86c1a6c9ddd2c4e5dc6ae1902b5f571b4a
 size 4999758176

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c7b4b302c780b58b60cfffe94f0a3834d0b1aa345551e452a0ec3c03862afc
+oid sha256:9d63562829bfb753204a01670fbc811c3aa71e257b5b1149771aed0a8a7f6c40
 size 4989454400

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17420dbe5720ae83e5be36b5adca51444039cb3c5f3cd6c0351f8a142c353e09
+oid sha256:807d4fbbc5b6789b5f90217b5b9ba0ece1d7a23f13d19417fc00fe222a5503f4
 size 4986832848

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a059faa7122aa0a4da64c725e208ec89cf9b4f541ea100193e4c0b186a1ed4f1
+oid sha256:7545058c39f50c49cb535deb990953ca3459de47a48f206002d4b7c11c59896b
 size 4986832856

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:666b4874f30af5a7f77bdc66eacceb2ec5a1c16d5a65bebe421141794872adca
+oid sha256:721bcf76f6a0fb50fa3971da9df9b9de70889fddda6817d731c538cccd1917f3
 size 4999758184

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd82f83dbd50da85a939538085369c3b0142367b6bf8635e46bbea2a373a832
+oid sha256:57158a6bed072933c8322bf6524c966f3d5acab2646671c59149de776d4ef469
 size 4801140400

model.safetensors.index.json

@@ -1,5 +1,6 @@
 {
   "metadata": {
+    "total_parameters": 63720802592,
     "total_size": 69686048896
   },
   "weight_map": {

preprocessor_config.json

@@ -3,6 +3,7 @@
   "data_format": "channels_first",
   "default_to_square": true,
   "device": null,
+  "disable_grouping": null,
   "do_center_crop": null,
   "do_convert_rgb": true,
   "do_normalize": true,

recipe.yaml

@@ -2,6 +2,6 @@ default_stage:
   default_modifiers:
     QuantizationModifier:
       targets: [Linear]
-      ignore: ['re:.*lm_head', 're:.*self_attn', 're:.*router', 're:.*vision_model', 're:.*multi_modal_projector',
-        're:.*multi_modal_projector', Llama4TextAttention]
+      ignore: ['re:.*lm_head*', 're:.*self_attn*', 're:.*router*', 're:.*vision_model*', 're:.*multi_modal_projector*',
+        're:.*multi_modal_projector*', Llama4TextAttention]
       scheme: NVFP4

tokenizer_config.json

@@ -9082,7 +9082,6 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "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",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|eot|>",
   "extra_special_tokens": {},
@@ -9090,8 +9089,8 @@
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 262144,
+  "model_max_length": 10485760,
   "pad_token": "<|finetune_right_pad|>",
   "processor_class": "Llama4Processor",
-  "tokenizer_class": "PreTrainedTokenizer"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }