Upload folder using huggingface_hub

config.json

@@ -1,10 +1,12 @@
 {
-  "_name_or_path": "meta-llama/Llama-3.2-90B-Vision",
   "architectures": [
     "MllamaForConditionalGeneration"
   ],
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
   "image_token_index": 128256,
   "model_type": "mllama",
+  "pad_token_id": 128004,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
@@ -14,22 +16,18 @@
     "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,
     "quant_method": "bitsandbytes"
   },
   "text_config": {
-    "_attn_implementation_autoset": false,
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 128000,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
     "cross_attention_layers": [
       3,
       8,
@@ -52,54 +50,16 @@
       93,
       98
     ],
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
     "dropout": 0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 128001,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
     "hidden_act": "silu",
     "hidden_size": 8192,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "initializer_range": 0.02,
     "intermediate_size": 28672,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
     "max_position_embeddings": 131072,
-    "min_length": 0,
     "model_type": "mllama_text_model",
-    "no_repeat_ngram_size": 0,
     "num_attention_heads": 64,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_hidden_layers": 100,
     "num_key_value_heads": 8,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 128004,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
     "rms_norm_eps": 1e-05,
     "rope_scaling": {
       "factor": 8.0,
@@ -109,53 +69,17 @@
       "rope_type": "llama3"
     },
     "rope_theta": 500000.0,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": false,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
     "torch_dtype": "bfloat16",
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
     "use_cache": true,
     "vocab_size": 128256
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.52.4",
   "unsloth_fixed": true,
   "vision_config": {
-    "_attn_implementation_autoset": false,
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
     "attention_heads": 16,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
     "hidden_act": "gelu",
     "hidden_size": 1280,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "image_size": 560,
     "initializer_range": 0.02,
     "intermediate_layers_indices": [
@@ -166,38 +90,13 @@
       30
     ],
     "intermediate_size": 5120,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
     "max_num_tiles": 4,
-    "min_length": 0,
     "model_type": "mllama_vision_model",
-    "no_repeat_ngram_size": 0,
     "norm_eps": 1e-05,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_channels": 3,
     "num_global_layers": 8,
     "num_hidden_layers": 32,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
     "patch_size": 14,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
     "supported_aspect_ratios": [
       [
         1,
@@ -232,19 +131,7 @@
         1
       ]
     ],
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
     "torch_dtype": "bfloat16",
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
     "vision_output_dim": 7680
   }
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 128000,
   "eos_token_id": 128001,
   "pad_token_id": 128004,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.52.4"
 }

model-00010-of-00010.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc77a781427aa2512d631f8100a21891f67ef8bf44eaba1fc97a9460f48c4f82
-size 4263159969
+oid sha256:3038a5ec5cd083f93f3ccd8e840828979d2bb9c6f9450d73c5720dea77c01dc1
+size 4356531589

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 48939476902
+    "total_size": 49032849082
   },
   "weight_map": {
     "language_model.lm_head.weight": "model-00010-of-00010.safetensors",
@@ -4488,11 +4488,6 @@
     "language_model.model.norm.weight": "model-00010-of-00010.safetensors",
     "multi_modal_projector.bias": "model-00010-of-00010.safetensors",
     "multi_modal_projector.weight": "model-00010-of-00010.safetensors",
-    "multi_modal_projector.weight.absmax": "model-00010-of-00010.safetensors",
-    "multi_modal_projector.weight.nested_absmax": "model-00010-of-00010.safetensors",
-    "multi_modal_projector.weight.nested_quant_map": "model-00010-of-00010.safetensors",
-    "multi_modal_projector.weight.quant_map": "model-00010-of-00010.safetensors",
-    "multi_modal_projector.weight.quant_state.bitsandbytes__nf4": "model-00010-of-00010.safetensors",
     "vision_model.class_embedding": "model-00001-of-00010.safetensors",
     "vision_model.gated_positional_embedding.embedding": "model-00001-of-00010.safetensors",
     "vision_model.gated_positional_embedding.gate": "model-00001-of-00010.safetensors",

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_bos_token": true,
   "added_tokens_decoder": {
     "128000": {
       "content": "<|begin_of_text|>",
@@ -2060,6 +2061,7 @@
   "bos_token": "<|begin_of_text|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"
@@ -2068,6 +2070,6 @@
   "pad_token": "<|finetune_right_pad_id|>",
   "padding_side": "left",
   "processor_class": "MllamaProcessor",
-  "tokenizer_class": "PreTrainedTokenizerFast",
+  "tokenizer_class": "PreTrainedTokenizer",
   "unk_token": null
-}
+}