Upload folder using huggingface_hub

config.json

@@ -1,32 +1,13 @@
 {
   "_commit_hash": null,
-  "_name_or_path": "mistralai/Pixtral-12B",
+  "_name_or_path": "../pixtral",
   "architectures": [
     "LlavaForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 5120,
-  "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 1024000,
-  "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-05,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.0.dev0",
-  "use_cache": false,
-  "vocab_size": 131073,
+  "ignore_index": -100,
   "image_seq_length": 1,
   "image_token_index": 10,
+  "model_type": "llava",
   "projector_hidden_act": "gelu",
   "text_config": {
     "hidden_size": 5120,
@@ -34,7 +15,7 @@
     "intermediate_size": 14336,
     "is_composition": true,
     "max_position_embeddings": 1024000,
-    "model_type": "llava",
+    "model_type": "mistral",
     "num_hidden_layers": 40,
     "num_key_value_heads": 8,
     "rms_norm_eps": 1e-05,
@@ -42,16 +23,18 @@
     "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": "llava",
+    "model_type": "pixtral",
     "patch_size": 16,
     "rope_theta": 10000.0,
     "tie_word_embeddings": false
   },
   "vision_feature_layer": -1,
   "vision_feature_select_strategy": "full"
-}
+}

special_tokens_map.json

@@ -13,13 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -95,7 +95,7 @@
     },
     {
       "id": 10,
-      "content": "<pad>",
+      "content": "[IMG]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -104,7 +104,7 @@
     },
     {
       "id": 11,
-      "content": "[PREFIX]",
+      "content": "<pad>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -113,7 +113,7 @@
     },
     {
       "id": 12,
-      "content": "[MIDDLE]",
+      "content": "[IMG_BREAK]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -122,7 +122,7 @@
     },
     {
       "id": 13,
-      "content": "[SUFFIX]",
+      "content": "[IMG_END]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -131,7 +131,7 @@
     },
     {
       "id": 14,
-      "content": "<SPECIAL_14>",
+      "content": "[PREFIX]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -140,7 +140,7 @@
     },
     {
       "id": 15,
-      "content": "<SPECIAL_15>",
+      "content": "[MIDDLE]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -149,7 +149,7 @@
     },
     {
       "id": 16,
-      "content": "<SPECIAL_16>",
+      "content": "[SUFFIX]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -9002,15 +9002,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 131072,
-      "content": "[PAD]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,
@@ -9020,7 +9011,7 @@
       {
         "type": "Split",
         "pattern": {
-          "Regex": "[^\\r\\n\\p{L}\\p{N}]?[\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}\\p{M}]*[\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}]+|[^\\r\\n\\p{L}\\p{N}]?[\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}\\p{M}]+[\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}]*|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n/]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
+          "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
         },
         "behavior": "Isolated",
         "invert": false
@@ -9034,67 +9025,10 @@
     ]
   },
   "post_processor": {
-    "type": "TemplateProcessing",
-    "single": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      }
-    ],
-    "pair": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 1
-        }
-      },
-      {
-        "Sequence": {
-          "id": "B",
-          "type_id": 1
-        }
-      }
-    ],
-    "special_tokens": {
-      "</s>": {
-        "id": "</s>",
-        "ids": [
-          2
-        ],
-        "tokens": [
-          "</s>"
-        ]
-      },
-      "<s>": {
-        "id": "<s>",
-        "ids": [
-          1
-        ],
-        "tokens": [
-          "<s>"
-        ]
-      }
-    }
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": false,
+    "use_regex": true
   },
   "decoder": {
     "type": "ByteLevel",
@@ -9122,13 +9056,13 @@
       "[TOOL_RESULTS]": 7,
       "[/TOOL_RESULTS]": 8,
       "[TOOL_CALLS]": 9,
-      "<pad>": 10,
-      "[PREFIX]": 11,
-      "[MIDDLE]": 12,
-      "[SUFFIX]": 13,
-      "<SPECIAL_14>": 14,
-      "<SPECIAL_15>": 15,
-      "<SPECIAL_16>": 16,
+      "[IMG]": 10,
+      "<pad>": 11,
+      "[IMG_BREAK]": 12,
+      "[IMG_END]": 13,
+      "[PREFIX]": 14,
+      "[MIDDLE]": 15,
+      "[SUFFIX]": 16,
       "<SPECIAL_17>": 17,
       "<SPECIAL_18>": 18,
       "<SPECIAL_19>": 19,

tokenizer_config.json

@@ -1,7 +1,4 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -84,7 +81,7 @@
       "special": true
     },
     "10": {
-      "content": "<pad>",
+      "content": "[IMG]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -92,7 +89,7 @@
       "special": true
     },
     "11": {
-      "content": "[PREFIX]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -100,7 +97,7 @@
       "special": true
     },
     "12": {
-      "content": "[MIDDLE]",
+      "content": "[IMG_BREAK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -108,7 +105,7 @@
       "special": true
     },
     "13": {
-      "content": "[SUFFIX]",
+      "content": "[IMG_END]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -116,7 +113,7 @@
       "special": true
     },
     "14": {
-      "content": "<SPECIAL_14>",
+      "content": "[PREFIX]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -124,7 +121,7 @@
       "special": true
     },
     "15": {
-      "content": "<SPECIAL_15>",
+      "content": "[MIDDLE]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -132,7 +129,7 @@
       "special": true
     },
     "16": {
-      "content": "<SPECIAL_16>",
+      "content": "[SUFFIX]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -8002,22 +7999,17 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "131072": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
+  "processor_class": "PixtralProcessor",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<unk>"
 }