Add files using upload-large-folder tool

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/Mistral-Nemo-Base-2407",
+  "_name_or_path": "mistralai/Mistral-Nemo-Base-2407",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -11,7 +11,7 @@
   "hidden_size": 5120,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 1024000,
+  "max_position_embeddings": 131072,
   "model_type": "mistral",
   "num_attention_heads": 32,
   "num_hidden_layers": 40,
@@ -26,7 +26,12 @@
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
+    "llm_int8_skip_modules": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection"
+    ],
     "llm_int8_threshold": 6.0,
     "load_in_4bit": true,
     "load_in_8bit": false,
@@ -37,8 +42,8 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.2",
-  "unsloth_version": "2024.9",
+  "transformers_version": "4.49.0.dev0",
+  "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 131072
 }

generation_config.json

@@ -2,7 +2,7 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "max_length": 1024000,
+  "max_length": 131072,
   "pad_token_id": 10,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.49.0.dev0"
 }

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -8007,7 +8007,8 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "model_max_length": 1000000000000000019884624838656,
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
   "pad_token": "<pad>",
   "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast",