model_card

README.md

@@ -1,5 +1,4 @@
 ---
-library_name: vllm
 language:
 - en
 - fr
@@ -26,14 +25,14 @@ language:
 - hi
 - bn
 license: apache-2.0
+library_name: vllm
 inference: false
 base_model:
 - mistralai/Mistral-Small-3.1-24B-Base-2503
 extra_gated_description: >-
   If you want to learn more about how we process your personal data, please read
   our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
-tags:
-- mistral-common
+pipeline_tag: image-text-to-text
 ---
 
 # Model Card for Mistral-Small-3.1-24B-Instruct-2503
@@ -156,7 +155,7 @@ You cannot perform any web search or access internet to open URLs, links etc. If
 
 # MULTI-MODAL INSTRUCTIONS
 
-You have the ability to read images, but you cannot generate images.
+You have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.
 You cannot read nor transcribe audio files or videos."""
 ```
 

SYSTEM_PROMPT.txt

@@ -15,4 +15,5 @@ You cannot perform any web search or access internet to open URLs, links etc. If
 
 # MULTI-MODAL INSTRUCTIONS
 
-You have the ability to read images, but you cannot generate images. You cannot read nor transcribe audio files or videos.
+You have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.
+You cannot read nor transcribe audio files or videos.

chat_template.json

@@ -1,3 +1,3 @@
 {
-  "chat_template": "{%- set today = strftime_now(\"%Y-%m-%d\") %}\n{%- set default_system_message = \"You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\\nYour knowledge base was last updated on 2023-10-01. The current date is \" + today + \".\\n\\nWhen you're not sure about some information, you say that you don't have the information and don't make 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?\\\")\" %}\n\n{{- bos_token }}\n\n{%- if messages[0]['role'] == 'system' %}\n    {%- if messages[0]['content'] is string %}\n        {%- set system_message = messages[0]['content'] %}\n    {%- else %}\n        {%- set system_message = messages[0]['content'][0]['text'] %}\n    {%- endif %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = default_system_message %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}\n\n{%- for message in loop_messages %}\n    {%- if message['role'] == 'user' %}\n        {%- if message['content'] is string %}\n            {{- '[INST]' + message['content'] + '[/INST]' }}\n        {%- else %}\n            {{- '[INST]' }}\n            {%- for block in message['content'] %}\n                {%- if block['type'] == 'text' %}\n                    {{- block['text'] }}\n                {%- elif block['type'] in ['image', 'image_url'] %}\n                    {{- '[IMG]' }}\n                {%- else %}\n                    {{- raise_exception('Only text and image blocks are supported in message content!') }}\n                {%- endif %}\n            {%- endfor %}\n            {{- '[/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'system' %}\n        {%- if message['content'] is string %}\n            {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}\n        {%- else %}\n            {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {%- if message['content'] is string %}\n            {{- message['content'] + eos_token }}\n        {%- else %}\n            {{- message['content'][0]['text'] + eos_token }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Only user, system and assistant roles are supported!') }}\n    {%- endif %}\n{%- endfor %}"
+  "chat_template": "{%- set today = strftime_now(\"%Y-%m-%d\") %}\n{%- set default_system_message = \"You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\\nYour knowledge base was last updated on 2023-10-01. The current date is \" + today + \".\\n\\nWhen you're not sure about some information, you say that you don't have the information and don't make 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?\\\")\" %}\n\n{{- bos_token }}\n\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = default_system_message %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}\n\n{%- for message in loop_messages %}\n    {%- if message['role'] == 'user' %}\n\t    {%- if message['content'] is string %}\n            {{- '[INST]' + message['content'] + '[/INST]' }}\n\t    {%- else %}\n\t\t    {{- '[INST]' }}\n\t\t    {%- for block in message['content'] %}\n\t\t\t    {%- if block['type'] == 'text' %}\n\t\t\t\t    {{- block['text'] }}\n\t\t\t    {%- elif block['type'] == 'image' or block['type'] == 'image_url' %}\n\t\t\t\t    {{- '[IMG]' }}\n\t\t\t\t{%- else %}\n\t\t\t\t    {{- raise_exception('Only text and image blocks are supported in message content!') }}\n\t\t\t\t{%- endif %}\n\t\t\t{%- endfor %}\n\t\t    {{- '[/INST]' }}\n\t\t{%- endif %}\n    {%- elif message['role'] == 'system' %}\n        {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}\n    {%- elif message['role'] == 'assistant' %}\n        {{- message['content'] + eos_token }}\n    {%- else %}\n        {{- raise_exception('Only user, system and assistant roles are supported!') }}\n    {%- endif %}\n{%- endfor %}"
 }

config.json

@@ -30,7 +30,7 @@
   "vision_config": {
     "attention_dropout": 0.0,
     "head_dim": 64,
-    "hidden_act": "silu",
+    "hidden_act": "gelu",
     "hidden_size": 1024,
     "image_size": 1540,
     "initializer_range": 0.02,

params.json

@@ -8,7 +8,6 @@
     "rope_theta": 1000000000.0,
     "norm_eps": 1e-05,
     "vocab_size": 131072,
-    "max_position_embeddings": 131072,
     "vision_encoder": {
         "hidden_size": 1024,
         "num_channels": 3,