Upload folder using huggingface_hub

config.json

@@ -1,53 +1,7 @@
 {
   "architectures": [
-    "Gemma3nForConditionalGeneration"
+    "Lfm2vlForConditionalGeneration"
   ],
-  "audio_config": {
-    "conf_attention_chunk_size": 12,
-    "conf_attention_context_left": 13,
-    "conf_attention_context_right": 0,
-    "conf_attention_logit_cap": 50.0,
-    "conf_conv_kernel_size": 5,
-    "conf_num_attention_heads": 8,
-    "conf_num_hidden_layers": 12,
-    "conf_reduction_factor": 4,
-    "conf_residual_weight": 0.5,
-    "gradient_clipping": 10000000000.0,
-    "hidden_size": 1536,
-    "input_feat_size": 128,
-    "model_type": "gemma3n_audio",
-    "rms_norm_eps": 1e-06,
-    "sscp_conv_channel_size": [
-      128,
-      32
-    ],
-    "sscp_conv_group_norm_eps": 0.001,
-    "sscp_conv_kernel_size": [
-      [
-        3,
-        3
-      ],
-      [
-        3,
-        3
-      ]
-    ],
-    "sscp_conv_stride_size": [
-      [
-        2,
-        2
-      ],
-      [
-        2,
-        2
-      ]
-    ],
-    "torch_dtype": "float32",
-    "vocab_offset": 262272,
-    "vocab_size": 128
-  },
-  "audio_soft_tokens_per_image": 188,
-  "audio_token_id": 262273,
   "boa_token_id": 256000,
   "boi_token": "<start_of_image>",
   "boi_token_id": 64401,
@@ -111,13 +65,13 @@
     "num_hidden_layers": 16,
     "num_key_value_heads": 8,
     "rope_theta": 1000000.0,
-    "torch_dtype": "float32",
+    "torch_dtype": "bfloat16",
     "use_cache": true,
     "use_pos_enc": true,
     "vocab_size": 64403
   },
-  "torch_dtype": "float32",
-  "transformers_version": "4.54.1",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.0",
   "use_cache": true,
   "vision_config": {
     "architecture": "mobilenetv5_300m_enc",
@@ -129,10 +83,10 @@
       "LABEL_1"
     ],
     "model_args": null,
-    "model_type": "gemma3n_vision",
+    "model_type": "lfm2_vision",
     "num_classes": 2,
     "rms_norm_eps": 1e-06,
-    "torch_dtype": "float32",
+    "torch_dtype": "bfloat16",
     "vocab_offset": 262144,
     "vocab_size": 128
   },

generation_config.json

@@ -9,5 +9,5 @@
   "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
-  "transformers_version": "4.54.1"
+  "transformers_version": "4.54.0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b0db5e62e2880b680572af2894587b8c059f7e08199735e420ca2f34ce294fc
+size 2933310216

preprocessor_config.json

@@ -39,7 +39,6 @@
   "preemphasis": 0.97,
   "preemphasis_htk_flavor": true,
   "processor_class": "Lfm2vlProcessor",
-  "feature_extractor_type": "Lfm2vlAudioFeatureExtractor",
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "return_attention_mask": true,

special_tokens_map.json

@@ -1,26 +1,8 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<image_soft_token>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<start_of_image>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<end_of_image>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<image_soft_token>",
+    "<start_of_image>",
+    "<end_of_image>"
   ],
   "bos_token": {
     "content": "<|startoftext|>",

tokenizer_config.json

@@ -4092,6 +4092,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
+  "image_token_id": 64400,
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|pad|>",
@@ -4102,6 +4103,5 @@
   "tokenizer_class": "PreTrainedTokenizerFast",
   "truncation": "do_not_truncate",
   "use_default_system_prompt": false,
-  "use_fast": true,
-  "image_token_id": "64400"
+  "use_fast": true
 }