Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1,121 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = 'You are Ministral-3-8B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYou power an AI assistant called Le Chat.\nYour knowledge base was last updated on 2023-10-01.\nThe current date is {today}.\n\nWhen you\'re not sure about some information or when the user\'s request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don\'t have the information and avoid making up anything.\nIf the user\'s question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?").\nYou are always very attentive to dates, in particular you try to resolve dates (e.g. "yesterday" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.\nYou follow these instructions in all languages, and always respond to the user in the language they use or request.\nNext sections describe the capabilities that you have.\n\n# WEB BROWSING INSTRUCTIONS\n\nYou cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.\n\n# MULTI-MODAL INSTRUCTIONS\n\nYou have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.\nYou cannot read nor transcribe audio files or videos.\n\n# TOOL CALLING INSTRUCTIONS\n\nYou may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:\n\n1. When the request requires up-to-date information.\n2. When the request requires specific data that you do not have in your knowledge base.\n3. When the request involves actions that you cannot perform without tools.\n\nAlways prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment.' %}
+
+{#- Begin of sequence token. #}
+{{- bos_token }}
+
+{#- Handle system prompt if it exists. #}
+{#- System prompt supports text content or text chunks. #}
+{%- if messages[0]['role'] == 'system' %}
+    {{- '[SYSTEM_PROMPT]' -}}
+    {%- if messages[0]['content'] is string %}
+        {{- messages[0]['content'] -}}
+    {%- else %}        
+        {%- for block in messages[0]['content'] %}
+            {%- if block['type'] == 'text' %}
+                {{- block['text'] }}
+            {%- else %}
+                {{- raise_exception('Only text chunks are supported in system message contents.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+    {{- '[/SYSTEM_PROMPT]' -}}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- if default_system_message != '' %}
+        {{- '[SYSTEM_PROMPT]' + default_system_message + '[/SYSTEM_PROMPT]' }}
+    {%- endif %}
+{%- endif %}
+
+
+{#- Tools definition #}
+{%- set tools_definition = '' %}
+{%- set has_tools = false %}
+{%- if tools is defined and tools is not none and tools|length > 0 %}
+    {%- set has_tools = true %}
+    {%- set tools_definition = '[AVAILABLE_TOOLS]' + (tools| tojson) + '[/AVAILABLE_TOOLS]' %}
+    {{- tools_definition }}
+{%- endif %}
+
+{#- Checks for alternating user/assistant messages. #}
+{%- set ns = namespace(index=0) %}
+{%- for message in loop_messages %}
+    {%- if message.role == 'user' or (message.role == 'assistant' and (message.tool_calls is not defined or message.tool_calls is none or message.tool_calls | length == 0)) %}
+        {%- if (message['role'] == 'user') != (ns.index % 2 == 0) %}
+            {{- raise_exception('After the optional system message, conversation roles must alternate user and assistant roles except for tool calls and results.') }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{#- Handle conversation messages. #}
+{%- for message in loop_messages %}
+
+    {#- User messages supports text content or text and image chunks. #}
+    {%- if message['role'] == 'user' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- elif message['content'] | length > 0 %}
+            {{- '[INST]' }}
+            {%- if message['content'] | length == 2 %}
+                {%- set blocks = message['content'] | sort(attribute='type') %}
+            {%- else %}
+                {%- set blocks = message['content'] %}
+            {%- endif %}
+            {%- for block in blocks %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text, image and image_url chunks are supported in user message content.') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- else %}
+            {{- raise_exception('User message must have a string or a list of chunks in content') }}
+        {%- endif %}
+
+    {#- Assistant messages supports text content or text and image chunks. #}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if (message['content'] is none or message['content'] == '' or message['content']|length == 0) and (message['tool_calls'] is not defined or message['tool_calls'] is none or message['tool_calls']|length == 0) %}
+            {{- raise_exception('Assistant message must have a string or a list of chunks in content or a list of tool calls.') }}
+        {%- endif %}
+
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- elif message['content'] | length > 0 %}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- else %}
+                    {{- raise_exception('Only text chunks are supported in assistant message contents.') }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        
+        {%- if message['tool_calls'] is defined and message['tool_calls'] is not none and message['tool_calls']|length > 0 %}
+            {%- for tool in message['tool_calls'] %}
+                {%- set arguments = tool['function']['arguments'] %}
+                {%- if arguments is not string %}
+                    {%- set arguments = arguments|tojson|safe %}
+                {%- elif arguments == '' %}
+                    {%- set arguments = '{}' %}
+                {%- endif %}
+                {{- '[TOOL_CALLS]' + tool['function']['name'] + '[ARGS]' + arguments }}
+            {%- endfor %}
+        {%- endif %}
+
+        {#- End of sequence token for each assistant messages. #}
+        {{- eos_token }}
+
+    {#- Tool messages only supports text content. #}
+    {%- elif message['role'] == 'tool' %}
+        {{- '[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]' }}
+
+    {#- Raise exception for unsupported roles. #}
+    {%- else %}
+        {{- raise_exception('Only user, assistant and tool roles are supported, got ' + message['role'] + '.') }}
+    {%- endif %}
+{%- endfor %}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88317e337902389ac038c60a458967d43bf82492e665b2a9f74fdfee76848139
-size 9563643372
+oid sha256:b40acb4f97417aee271f889a165459dd3b66aaa501a2a8f88fe83c1d319a8736
+size 16979144064

model.safetensors.index.json

@@ -1,8 +1,10 @@
 {
   "metadata": {
-    "total_size": 9563578844
+    "total_size": 16979107840
   },
   "weight_map": {
+    "lm_head.weight": "model.safetensors",
+    "model.embed_tokens.weight": "model.safetensors",
     "model.layers.0.input_layernorm.weight": "model.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
     "model.layers.1.input_layernorm.weight": "model.safetensors",
@@ -14,6 +16,113 @@
     "model.layers.12.input_layernorm.weight": "model.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
     "model.layers.13.input_layernorm.weight": "model.safetensors",
+    "model.layers.2.input_layernorm.weight": "model.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.3.input_layernorm.weight": "model.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.4.input_layernorm.weight": "model.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.5.input_layernorm.weight": "model.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.6.input_layernorm.weight": "model.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.7.input_layernorm.weight": "model.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.8.input_layernorm.weight": "model.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.9.input_layernorm.weight": "model.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
     "model.layers.14.input_layernorm.weight": "model.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
@@ -27,8 +136,6 @@
     "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
     "model.layers.19.input_layernorm.weight": "model.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
-    "model.layers.2.input_layernorm.weight": "model.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
     "model.layers.20.input_layernorm.weight": "model.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
     "model.layers.21.input_layernorm.weight": "model.safetensors",
@@ -49,8 +156,6 @@
     "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
     "model.layers.29.input_layernorm.weight": "model.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
-    "model.layers.3.input_layernorm.weight": "model.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
     "model.layers.30.input_layernorm.weight": "model.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
     "model.layers.31.input_layernorm.weight": "model.safetensors",
@@ -59,496 +164,153 @@
     "model.layers.32.post_attention_layernorm.weight": "model.safetensors",
     "model.layers.33.input_layernorm.weight": "model.safetensors",
     "model.layers.33.post_attention_layernorm.weight": "model.safetensors",
-    "model.layers.4.input_layernorm.weight": "model.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
-    "model.layers.5.input_layernorm.weight": "model.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
-    "model.layers.6.input_layernorm.weight": "model.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
-    "model.layers.7.input_layernorm.weight": "model.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
-    "model.layers.8.input_layernorm.weight": "model.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
-    "model.layers.9.input_layernorm.weight": "model.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
     "model.norm.weight": "model.safetensors",
-    "lm_head.weight": "model.safetensors",
-    "model.embed_tokens.weight": "model.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model.safetensors",
     "model.layers.32.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.32.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.32.self_attn.q_proj.weight": "model.safetensors",
     "model.layers.32.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model.safetensors",
     "model.layers.33.self_attn.k_proj.weight": "model.safetensors",
     "model.layers.33.self_attn.o_proj.weight": "model.safetensors",
     "model.layers.33.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model.safetensors",
-    "model.layers.0.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.0.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.0.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.0.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.0.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.0.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.0.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.1.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.1.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.1.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.1.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.1.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.1.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.1.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.10.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.10.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.10.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.10.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.10.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.10.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.10.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.11.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.11.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.11.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.11.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.11.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.11.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.11.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.12.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.12.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.12.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.12.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.12.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.12.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.12.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.2.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.2.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.2.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.2.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.2.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.2.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.2.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.3.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.3.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.3.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.3.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.3.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.3.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.3.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.4.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.4.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.4.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.4.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.4.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.4.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.4.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.5.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.5.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.5.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.5.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.5.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.5.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.5.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.6.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.6.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.6.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.6.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.6.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.6.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.6.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.7.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.7.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.7.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.7.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.7.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.7.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.7.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.8.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.8.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.8.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.8.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.8.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.8.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.8.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.9.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.9.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.9.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.9.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.9.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.9.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.9.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.13.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.13.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.13.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.13.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.13.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.13.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.13.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.14.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.14.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.14.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.14.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.14.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.14.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.14.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.15.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.15.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.15.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.15.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.15.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.15.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.15.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.16.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.16.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.16.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.16.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.16.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.16.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.16.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.17.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.17.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.17.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.17.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.17.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.17.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.17.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.18.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.18.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.18.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.18.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.18.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.18.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.18.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.19.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.19.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.19.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.19.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.19.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.19.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.19.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.20.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.20.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.20.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.20.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.20.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.20.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.20.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.21.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.21.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.21.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.21.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.21.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.21.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.21.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.22.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.22.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.22.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.22.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.22.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.22.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.22.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.23.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.23.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.23.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.23.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.23.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.23.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.23.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.24.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.24.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.24.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.24.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.24.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.24.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.24.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.25.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.25.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.25.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.25.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.25.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.25.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.25.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.26.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.26.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.26.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.26.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.26.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.26.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.26.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.27.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.27.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.27.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.27.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.27.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.27.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.27.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.28.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.28.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.28.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.28.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.28.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.28.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.28.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.29.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.29.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.29.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.29.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.29.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.29.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.29.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.30.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.30.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.30.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.30.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.30.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.30.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.30.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.31.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.31.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.31.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.31.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.31.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.31.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.31.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.32.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.32.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.32.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.32.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.32.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.32.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.32.self_attn.v_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.33.mlp.down_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.33.mlp.gate_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.33.mlp.up_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.33.self_attn.k_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.33.self_attn.o_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.33.self_attn.q_proj.weight_scale_inv": "model.safetensors",
-    "model.layers.33.self_attn.v_proj.weight_scale_inv": "model.safetensors"
+    "model.layers.33.self_attn.v_proj.weight": "model.safetensors"
   }
 }

tokenizer_config.json

@@ -1004,7 +1004,10 @@
     "<SPECIAL_999>"
   ],
   "model_max_length": 1000000000000000019884624838656,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
   "pad_token": "<pad>",
+  "unk_token": "<unk>",
   "processor_class": "PixtralProcessor",
   "tokenizer_class": "TokenizersBackend"
 }