Code relesae

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tekken.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,125 @@
+---
+license: apache-2.0
+---
+
+# Pixtral-12B-0910
+
+> [!WARNING]
+> We still need to validate official evaluations with the below usage example.
+
+
+...TODO
+
+## Usage
+
+We recommend using Pixtral with the [vLLM library](https://github.com/vllm-project/vllm).
+
+**Important**: Make sure you have installed vLLM from source - more specifically make sure you have installed [this commit (TODO)]( ).
+Also make sure you have `mistral_common >= 1.4.0` installed:
+
+```
+pip install --upgrade mistral_common
+```
+
+**_Simple Example_**
+
+```py
+from vllm import LLM
+from vllm.sampling_params import SamplingParams
+
+model_name = "mistralai/Pixtral-12B-2409"
+
+sampling_params = SamplingParams(max_tokens=8192)
+
+llm = LLM(model=model_name, tokenizer_mode="mistral")
+
+prompt = "Describe this image in one sentence."
+image_url = "https://picsum.photos/id/237/200/300"
+
+messages = [
+    {
+        "role": "user",
+        "content": [{"type": "text", "text": prompt}, {"type": "image_url", "image_url": {"url": image_url}}]
+    },
+]
+
+outputs = vllm_model.model.chat(messages, sampling_params=sampling_params)
+
+print(outputs[0].outputs[0].text)
+```
+
+**_Advanced Example_**
+
+You can also pass multiple images per message and/or pass multi-turn conversations
+
+```py
+from vllm import LLM
+from vllm.sampling_params import SamplingParams
+
+model_name = "mistralai/Pixtral-12B-2409"
+max_img_per_msg = 5
+max_tokens_per_img = 4096
+
+sampling_params = SamplingParams(max_tokens=8192, temperature=0.7)
+llm = LLM(model=model_name, tokenizer_mode="mistral", limit_mm_per_prompt={"image": max_img_per_msg}, max_num_batched_tokens=max_img_per_msg * max_tokens_per_img)
+
+prompt = "Describe the following image."
+
+url_1 = "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png"
+url_2 = "https://picsum.photos/seed/picsum/200/300"
+url_3 = "https://picsum.photos/id/32/512/512"
+
+messages = [
+    {
+        "role": "user",
+        "content": [{"type": "text", "text": prompt}, {"type": "image_url", "image_url": {"url": url_1}}, {"type": "image_url", "image_url": {"url": url_2}}],
+    },
+    {
+        "role": "assistant",
+        "content": "The images shows nature.",
+    },
+    {
+        "role": "user",
+        "content": "More details please and answer only in French!."
+    },
+    {
+        "role": "user",
+        "content": [{"type": "image_url", "image_url": {"url": url_3}}],
+    }
+]
+
+outputs = llm.chat(messages=messages, sampling_params=sampling_params)
+print(outputs[0].outputs[0].text)
+```
+
+**_Server_**
+
+You can also use pixtral in a server/client setting. 
+
+1. Spin up a server:
+
+```
+vllm serve mistralai/Pixtral-12B-2409 --tokenizer_mode mistral --limit_mm_per_prompt 'image=4' --max_num_batched_tokens 16384
+```
+
+2. And ping the client:
+
+```
+curl --location 'http://<your-node-url>:8000/v1/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer token' \
+--data '{
+    "model": "mistralai/Pixtral-12B-2409",
+    "messages": [
+      {
+        "role": "user",
+        "content": [
+            {"type" : "text", "text": "Describe this image in detail please."},
+            {"type": "image_url", "image_url": {"url": "https://s3.amazonaws.com/cms.ipressroom.com/338/files/201808/5b894ee1a138352221103195_A680%7Ejogging-edit/A680%7Ejogging-edit_hero.jpg"}},
+            {"type" : "text", "text": "and this one as well. Answer in French."},
+            {"type": "image_url", "image_url": {"url": "https://www.wolframcloud.com/obj/resourcesystem/images/a0e/a0ee3983-46c6-4c92-b85d-059044639928/6af8cfb971db031b.png"}}
+        ]
+      }
+    ]
+  }'
+```

consolidated.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4816a81eef8c05103d7b6df82bf27d3d59f6066e8f1e4245568aaa39326cf4b4
+size 25365548952

params.json

@@ -0,0 +1,22 @@
+{
+  "dim": 5120,
+  "n_layers": 40,
+  "head_dim": 128,
+  "hidden_dim": 14336,
+  "n_heads": 32,
+  "n_kv_heads": 8,
+  "rope_theta": 1000000000.0,
+  "norm_eps": 1e-05,
+  "vocab_size": 131072,
+  "vision_encoder": {
+    "hidden_size": 1024,
+    "num_channels": 3,
+    "image_size": 1024,
+    "patch_size": 16,
+    "rope_theta": 10000.0,
+    "intermediate_size": 4096,
+    "num_hidden_layers": 24,
+    "num_attention_heads": 16,
+    "image_token_id": 10
+  }
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386b1f98fba69b38c3de512a4eb602dc69a95dae0e54e6ce048ea3e29a2627a8
+size 19280967