Add FP8 block quantized model weights

.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
+*.json filter=lfs diff=lfs merge=lfs -text

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5820eace27887e07ce37c3486e034b0c0ea93b4cb40b7a2e7aeaa2af653dda
+size 12484

generation_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da63062f150d32d123b122fdec08ad2152ed50c07a64d37f4d1d4d004d534971
+size 210

model-00001-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da00ef6bde21f8cf2cbd95b99bdbe4aadae05c717fce7913a811e3236a17df5d
+size 4963566632

model-00002-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51b673e2f256b00cdecb91368e2833751100fe07b9300359fad857f97905df7
+size 4992200312

model-00003-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6a632824d275b66a4b4bd5d08a7138af467cb15b20c1a9bebb0ae9abab55f8
+size 4992200392

model-00004-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10c2d97f15d485b4ae4b52baa54d55743877ddacef7d738401c08046811a8419
+size 4992200472

model-00005-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4f6218fc6089128ea3038175de0742c705b32f52d6a82a76e48240a677f70a
+size 4992369912

model-00006-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b115a06f880f206052465782b5c68f54f0657e09576ecae092c681bd07c5846
+size 4992200496

model-00007-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f181658e971bf87e2e5b880180f939aef6b2bcaca82936bf26262fa12e44da
+size 4992200560

model-00008-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8800570f4d265b95e1e1f6604d0315bb87cf5c28a44932b6c9dd52fa4e41ad8a
+size 4992200632

model-00009-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a85997ce46d82102a9ad8273bb1badd3e638619cf9ec41efe6647f44774a3d
+size 4992200728

model-00010-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc404d939f5c3e83f986af37c5b31db8ab893574f4b90f1c5d01f82b9f1e5c6
+size 4992369784

model-00011-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c25a0399ca9c4f08502d7704de2d5b2d82c15cac5e3a3ae314765df1aabb6e9
+size 4992200496

model-00012-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4bc8cb4ccf9dce71ba3a673249874423598c10cf72b4c02c693f921e5ba40a
+size 4992200568

model-00013-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb488de84a4684791ddafe34bc0d39d61c186954f6cd1d942373b557faab2f1
+size 4992200640

model-00014-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f42a281cfed85ab6fd7bbeda9fd3ed7ff190d9119b11740233ffe4a23aa291a
+size 4992200728

model-00015-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b78a14ef86a14bec481ea8c869ee81313463351c5e645f4bedbb93914f957d
+size 4992369792

model-00016-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b57e1d7e43b7f5165ddb48ebc16e34ed932263b146cc091cdec025d89d9dfe
+size 4992200504

model-00017-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba44b6986c97bf51ca19e242418880548490f65b5152201fd9181b912589ac19
+size 4992200568

model-00018-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e11d49346c0213af7fce0c38f2e5f18fd3c536d11056c1d06f8147a1a7a12adb
+size 4992200656

model-00019-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43c4d0228bbeab23053303d55ee348d9acaf114ce43340809ed36fff650ad3a
+size 4992364696

model-00020-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f5362e3c43a8b9f9452abc342dc5c3c9bae6feee725f6e90bc35f60fc359170
+size 4992205808

model-00021-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7bea22bf436a2cc823ef472a3d0c6db334ff35524eb695b118877bee9ccbc7
+size 4992200512

model-00022-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:defb4ef3bbd8c975317c6da0003ef136a0d3b0c5c082b5490c781f99cd944429
+size 4992200576

model-00023-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c836a2deebb1688b9c5f665c594d72ac66c53e5029550f2553553dbadc18638c
+size 3075929072

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9337b064e78a2ac29cf446cc9ba8cb72749527a61791c91c15df48d60000fb0
+size 526589

preprocessor_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165d252185da3e66af57af729aa407a94e1398c728c66bd8b53530aed4e0c056
+size 664

processor_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc23f929e2a90ba534426072b2e0288909820f34ae79d8ff3934edda29e1f3a
+size 128

recipe.yaml

@@ -0,0 +1,7 @@
+default_stage:
+  default_modifiers:
+    QuantizationModifier:
+      targets: [Linear]
+      ignore: ['re:.*lm_head', 're:.*self_attn', 're:.*router', 're:.*vision_model.*', 're:.*multi_modal_projector.*',
+        Llama4TextAttention]
+      scheme: FP8_BLOCK

special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39aa13d7e53f700671e7af6464a745ed2d23ac3d2edba757a77b28ecb9a615cf
+size 448

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a74c3ff4e1f564995a5f66f6e70938bd6ad1c7688c0ccf30c34d1c1ed1aab1
+size 231950