remove unused keys

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "microsoft/Magma-8B",
   "architectures": [
     "MagmaForCausalLM"
   ],
@@ -8,7 +7,7 @@
   "auto_map": {
     "AutoConfig": "microsoft/Magma-8B--configuration_magma.MagmaConfig",
     "AutoModelForCausalLM": "microsoft/Magma-8B--modeling_magma.MagmaForCausalLM"
-  },  
+  },
   "hidden_act": "silu",
   "hidden_size": 4096,
   "image_token_id": 128257,
@@ -33,89 +32,36 @@
   "spatial_quant_size": 256,
   "text_config": {
     "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
-    "add_cross_attention": false,
     "architectures": [
       "LlamaForCausalLM"
     ],
     "attention_bias": false,
     "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
     "bos_token_id": 128000,
-    "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": 128009,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
+    "head_dim": 128,
     "hidden_act": "silu",
     "hidden_size": 4096,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "initializer_range": 0.02,
     "intermediate_size": 14336,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
     "max_position_embeddings": 8192,
-    "min_length": 0,
     "mlp_bias": false,
     "model_type": "llama",
-    "no_repeat_ngram_size": 0,
     "num_attention_heads": 32,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_hidden_layers": 32,
     "num_key_value_heads": 8,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
     "pad_token_id": 128256,
-    "prefix": null,
     "pretraining_tp": 1,
-    "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": null,
     "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": 128261
   },
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.1",
+  "transformers_version": "4.52.0.dev0",
   "use_cache": false,
   "vision_config": {
     "attention_bias": false,
@@ -138,9 +84,10 @@
     "mm_projector_type": "mlp2x_gelu",
     "mm_use_im_patch_token": false,
     "mm_use_im_start_end": false,
+    "mm_use_row_seperator": true,
     "mm_vision_select_feature": "patch",
     "mm_vision_select_layer": -2,
-    "mm_use_row_seperator": true,
+    "model_type": "magma_vision",
     "num_attention_heads": 32,
     "num_hidden_layers": 32,
     "num_key_value_heads": 8,
@@ -153,7 +100,6 @@
     "tokenizer_model_max_length": 4096,
     "tokenizer_padding_side": "right",
     "torch_dtype": "bfloat16",
-    "transformers_version": "4.36.2",
     "tune_mm_mlp_adapter": false,
     "tune_vision_tokenizer": "all",
     "use_cache": true,

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 128000,
   "eos_token_id": 128009,
   "pad_token_id": 128256,
-  "transformers_version": "4.44.1"
+  "transformers_version": "4.52.0.dev0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf018c291b927b63801b3d036b96f553a351f085852db2b4c62025323e6e2bee
-size 4983726904
+oid sha256:1a66e191d251086f7d69a9429369335d1a1fdab095a1c092663ee68b3c1617c9
+size 4977422784

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 17812436736
+    "total_size": 17806132992
   },
   "weight_map": {
     "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
@@ -299,9 +299,6 @@
     "multi_modal_projector.proj.2.bias": "model-00001-of-00004.safetensors",
     "multi_modal_projector.proj.2.weight": "model-00001-of-00004.safetensors",
     "multi_modal_projector.row_seperator": "model-00001-of-00004.safetensors",
-    "vision_tower.clip_vision_model.head.proj.weight": "model-00001-of-00004.safetensors",
-    "vision_tower.clip_vision_model.trunk.head.norm.bias": "model-00001-of-00004.safetensors",
-    "vision_tower.clip_vision_model.trunk.head.norm.weight": "model-00001-of-00004.safetensors",
     "vision_tower.clip_vision_model.trunk.stages.0.blocks.0.conv_dw.bias": "model-00001-of-00004.safetensors",
     "vision_tower.clip_vision_model.trunk.stages.0.blocks.0.conv_dw.weight": "model-00001-of-00004.safetensors",
     "vision_tower.clip_vision_model.trunk.stages.0.blocks.0.gamma": "model-00001-of-00004.safetensors",