update files (#5)

- update files (5afe6449116b70377c10ff869b82f10d36828c73)


Co-authored-by: haoyanli <[email protected]>

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    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %}      \n{%- for message in messages %}\n    {%- for content in message['content'] %}\n        {%- if content['type'] == 'image' %}\n            {%- set image_ns.has_images = true %}\n        {%- endif %}\n    {%- endfor %}\n{%- endfor %}\n\n{#- Error out if there are images and system message #}\n{%- if image_ns.has_images and not system_message == \"\" %}\n    {{- raise_exception(\"Prompting with images is incompatible with system messages.\") }}\n{%- endif %}\n\n{#- System message if there are no images #}\n{%- if not image_ns.has_images %}\n    {{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n    {%- if tools is not none %}\n        {{- \"Environment: ipython\\n\" }}\n    {%- endif %}\n    {{- \"Cutting Knowledge Date: December 2023\\n\" }}\n    {{- \"Today Date: \" + date_string + \"\\n\\n\" }}\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_id|>\" }}\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    {{- '<|start_header_id|>user<|end_header_id|>\\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_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\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_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\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_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n"
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/model_path/Llama-3.2-11B-Vision-Instruct/",
+  "_name_or_path": "/model_path/Llama-3.2-11B-Vision-Instruct",
   "architectures": [
     "MllamaForConditionalGeneration"
   ],
@@ -8,7 +8,10 @@
   "quantization_config": {
     "activation_scheme": "static",
     "ignored_layers": [
-      "lm_head"
+      "*lm_head",
+      "*cross_attn*",
+      "vision_model*",
+      "multi_modal_projector"
     ],
     "kv_cache_scheme": "static",
     "quant_method": "fp8"

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7913886bb1471568324e41653aad932101a8bc86d76b56ff71dade79b0f9afd2
-size 4984341162
+oid sha256:3a3123a5a86e315ff58920026ef7a912fb13788747d38acbbbec47012e89052b
+size 4984320774

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71f3d10886ee124b629c0813a3d01b675650fe49d085fdce7a1cd09bae34292b
-size 4991669352
+oid sha256:da57cc3b84a544a430a742177e2ba98d5870cba85bf0cb7f0c3974f31e73d715
+size 4966480928

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d70e8659c127002e674b5c0ab5f56bbfa6b6bd49ed8cade7fd9169548bdbb9bc
-size 2640468236
+oid sha256:8a6c5ade219cab320a5fef98063d814d9c5005fe4c015f9d75d0c9a6d91bd6b5
+size 3001212912

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 12616291750
+    "total_size": 12951835782
   },
   "weight_map": {
     "language_model.lm_head.weight": "model-00003-of-00003.safetensors",
@@ -64,19 +64,19 @@
     "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.kv_scale": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.10.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.11.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
@@ -126,20 +126,11 @@
     "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.cross_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.kv_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.cross_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.cross_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.cross_attn_attn_gate": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.cross_attn_mlp_gate": "model-00002-of-00003.safetensors",
     "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
@@ -250,20 +241,11 @@
     "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.cross_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.cross_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.cross_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.cross_attn.kv_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.cross_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.cross_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.cross_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.cross_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.cross_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.cross_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.cross_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.cross_attn_attn_gate": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.cross_attn_mlp_gate": "model-00002-of-00003.safetensors",
     "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
@@ -398,20 +380,11 @@
     "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.cross_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.cross_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.cross_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.cross_attn.kv_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.cross_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.cross_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.cross_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.cross_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.cross_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.cross_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.cross_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.cross_attn_attn_gate": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.cross_attn_mlp_gate": "model-00002-of-00003.safetensors",
     "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
@@ -522,20 +495,11 @@
     "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.28.cross_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.28.cross_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.28.cross_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.28.cross_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.28.cross_attn.kv_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.28.cross_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.28.cross_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.28.cross_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.28.cross_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.28.cross_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.28.cross_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.28.cross_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.28.cross_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.28.cross_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.28.cross_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.28.cross_attn_attn_gate": "model-00002-of-00003.safetensors",
     "language_model.model.layers.28.cross_attn_mlp_gate": "model-00002-of-00003.safetensors",
     "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
@@ -574,20 +538,11 @@
     "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.3.cross_attn.k_norm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.cross_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.cross_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.cross_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.cross_attn.kv_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.cross_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.cross_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.cross_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.cross_attn.q_norm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.cross_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.cross_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.cross_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.cross_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.cross_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.cross_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.cross_attn_attn_gate": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.cross_attn_mlp_gate": "model-00001-of-00003.safetensors",
     "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
@@ -625,17 +580,17 @@
     "language_model.model.layers.30.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.31.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.31.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.31.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.31.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.31.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.31.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.31.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.31.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
@@ -649,47 +604,38 @@
     "language_model.model.layers.31.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.31.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.kv_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.kv_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.33.cross_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.33.cross_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.kv_scale": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.33.cross_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.33.cross_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.33.cross_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.33.cross_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn_attn_gate": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.33.cross_attn_mlp_gate": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn_attn_gate": "model-00003-of-00003.safetensors",
+    "language_model.model.layers.33.cross_attn_mlp_gate": "model-00003-of-00003.safetensors",
     "language_model.model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.33.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
@@ -798,20 +744,11 @@
     "language_model.model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "language_model.model.layers.37.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.38.cross_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.38.cross_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.38.cross_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.38.cross_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.38.cross_attn.kv_scale": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.38.cross_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.38.cross_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.38.cross_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.38.cross_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.38.cross_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.38.cross_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.38.cross_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.38.cross_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
     "language_model.model.layers.38.cross_attn_attn_gate": "model-00003-of-00003.safetensors",
     "language_model.model.layers.38.cross_attn_mlp_gate": "model-00003-of-00003.safetensors",
     "language_model.model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
@@ -946,20 +883,11 @@
     "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.8.cross_attn.k_norm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.cross_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.8.cross_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.cross_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.cross_attn.kv_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.cross_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.8.cross_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.cross_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.8.cross_attn.q_norm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.cross_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.8.cross_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.cross_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.cross_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.8.cross_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.cross_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.8.cross_attn_attn_gate": "model-00001-of-00003.safetensors",
     "language_model.model.layers.8.cross_attn_mlp_gate": "model-00001-of-00003.safetensors",
     "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
@@ -973,17 +901,17 @@
     "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
     "language_model.model.layers.9.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.9.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.layers.9.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "language_model.model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",

preprocessor_config.json

@@ -16,6 +16,7 @@
     0.27577711
   ],
   "max_image_tiles": 4,
+  "processor_class": "MllamaProcessor",
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {