[Model] Mistral3 example and test

examples/multimodal_vision/mistral3_chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{%- set default_system_message = \"You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI\" %}\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 %}"
+}

examples/multimodal_vision/mistral3_example.py

@@ -0,0 +1,89 @@
+import json
+import os
+
+import requests
+import torch
+from PIL import Image
+from transformers import AutoProcessor, Mistral3ForConditionalGeneration
+
+from llmcompressor import oneshot
+from llmcompressor.modifiers.quantization import GPTQModifier
+
+# Load model.
+model_id = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
+model = Mistral3ForConditionalGeneration.from_pretrained(
+    model_id, device_map="auto", torch_dtype="auto"
+)
+processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
+
+# Use a custom calibration chat template, rather than the overly-verbose default
+file_path = os.path.join(os.path.dirname(__file__), "mistral3_chat_template.json")
+with open(file_path, "r") as file:
+    processor.chat_template = json.load(file)["chat_template"]
+
+# Oneshot arguments
+DATASET_ID = "flickr30k"
+DATASET_SPLIT = "test"
+NUM_CALIBRATION_SAMPLES = 512
+MAX_SEQUENCE_LENGTH = 2048
+
+
+# Define a oneshot data collator for multimodal inputs.
+def data_collator(batch):
+    assert len(batch) == 1
+    return {
+        key: torch.tensor(value)
+        if key != "pixel_values"
+        else torch.tensor(value, dtype=model.dtype)
+        for key, value in batch[0].items()
+    }
+
+
+# Recipe
+recipe = [
+    GPTQModifier(
+        targets="Linear",
+        scheme="W4A16",
+        sequential_targets=["MistralDecoderLayer"],
+        ignore=["re:.*lm_head", "re:vision_tower.*", "re:multi_modal_projector.*"],
+    ),
+]
+
+# Perform oneshot
+oneshot(
+    model=model,
+    tokenizer=model_id,
+    dataset=DATASET_ID,
+    splits={"calibration": f"{DATASET_SPLIT}[:{NUM_CALIBRATION_SAMPLES}]"},
+    recipe=recipe,
+    max_seq_length=MAX_SEQUENCE_LENGTH,
+    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
+    trust_remote_code_model=True,
+    data_collator=data_collator,
+)
+
+# Confirm generations of the quantized model look sane.
+print("========== SAMPLE GENERATION ==============")
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "text", "text": "Please describe the animal in this image\n"},
+            {"type": "image"},
+        ],
+    },
+]
+prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
+image_url = "http://images.cocodataset.org/train2017/000000231895.jpg"
+raw_image = Image.open(requests.get(image_url, stream=True).raw)
+
+inputs = processor(images=raw_image, text=prompt, return_tensors="pt").to("cuda")
+inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)  # fix dtype
+output = model.generate(**inputs, max_new_tokens=100)
+print(processor.decode(output[0], skip_special_tokens=True))
+print("==========================================")
+
+# Save to disk compressed.
+SAVE_DIR = model_id.split("/")[1] + "-W4A16-G128"
+model.save_pretrained(SAVE_DIR, save_compressed=True)
+processor.save_pretrained(SAVE_DIR)

tests/llmcompressor/transformers/tracing/test_models.py

@@ -7,6 +7,7 @@
     Idefics3ForConditionalGeneration,
     Llama4ForConditionalGeneration,
     LlavaForConditionalGeneration,
+    Mistral3ForConditionalGeneration,
     MllamaForConditionalGeneration,
     Qwen2_5_VLForConditionalGeneration,
     Qwen2VLForConditionalGeneration,
@@ -86,6 +87,13 @@
             "vision",
             ["torchvision"],
         ),
+        (
+            "mistralai/Mistral-Small-3.1-24B-Instruct-2503",
+            Mistral3ForConditionalGeneration,
+            ["MistralDecoderLayer"],
+            "vision",
+            [],
+        ),
         (
             "google/gemma-3-4b-it",
             Gemma3ForConditionalGeneration,