Add tiny processor fixture for testing

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{%- if messages[0][\"role\"] == \"system\" %}{%- set system_message = messages[0][\"content\"] %}{%- set loop_messages = messages[1:] %}\n{%- else %}{%- set loop_messages = messages %}{%- endif %}{{- bos_token }}{%- for message in loop_messages %}{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}{%- endif %}{%- if message[\"role\"] == \"user\" %}{%- if loop.last and system_message is defined %}{{- \"[INST]\" + system_message + \"\n\n\" }}{%- else %}{{ \"[INST]\" }}{%- endif %}{%- endif %}{%- if message[\"content\"] is not string %}{%- for chunk in message[\"content\"] %}{%- if chunk[\"type\"] == \"text\" %}{%- if \"content\" in chunk %}{{- chunk[\"content\"] }}{%- elif \"text\" in chunk %}{{- chunk[\"text\"] }}{%- endif %}{%- elif chunk[\"type\"] == \"image\" %}{{- \"[IMG]\" }}{%- else %}{{- raise_exception(\"Unrecognized content type!\") }}{%- endif %}{%- endfor %}{%- else %}{{- message[\"content\"] }}{%- endif %}{%- if message[\"role\"] == \"user\" %}{{- \"[/INST]\" }}{%- elif message[\"role\"] == \"assistant\" %}{{- eos_token}}{%- else %}{{- raise_exception(\"Only user and assistant roles are supported, with the exception of an initial optional system message!\") }}{%- endif %}{%- endfor %}"
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_commit_hash": null,
+  "_name_or_path": "../pixtral",
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_seq_length": 1,
+  "image_token_index": 10,
+  "model_type": "llava",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "hidden_size": 5120,
+    "head_dim": 128,
+    "intermediate_size": 14336,
+    "is_composition": true,
+    "max_position_embeddings": 1024000,
+    "model_type": "mistral",
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sliding_window": null,
+    "vocab_size": 131072
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": null,
+  "vision_config": {
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "image_size": 1024,
+    "is_composition": true,
+    "model_type": "pixtral",
+    "patch_size": 16,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false
+  },
+  "vision_feature_layer": -1,
+  "vision_feature_select_strategy": "full",
+  "vocab_size": 1500
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "PixtralImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "patch_size": {
+    "height": 16,
+    "width": 16
+  },
+  "processor_class": "PixtralProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1024
+  }
+}

processor_config.json

@@ -0,0 +1,7 @@
+{
+  "image_break_token": "[IMG_BREAK]",
+  "image_end_token": "[IMG_END]",
+  "image_token": "[IMG]",
+  "patch_size": 16,
+  "processor_class": "PixtralProcessor"
+}