Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 model.onnx.data filter=lfs diff=lfs merge=lfs -text
 projection/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+multi_modal_projector/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+vision_encoder/model.onnx.data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,25 @@
----
-license: apache-2.0
----
+# DistilViT2 for Transformers.js
+
+This model is compatible with transformers.js image-to-text pipeline.
+
+## Usage
+
+```javascript
+import { pipeline } from '@huggingface/transformers';
+
+const captioner = await pipeline('image-to-text', 'tarekziade/distilvit2');
+const result = await captioner('path/to/image.jpg');
+console.log(result);
+```
+
+## Architecture
+
+- Vision: SigLIP-base-patch16-224 (frozen during training)
+- Projector: Trained linear/MLP projection (768 → 576)
+- Text: SmolLM-135M with merged LoRA adapters
+
+## Training
+
+- Dataset: Flickr30k, COCO
+- Task: Image captioning
+- Trainable parameters: 2.2M (1% of total)

config.json

@@ -1,174 +1,23 @@
 {
+  "model_type": "llava",
   "architectures": [
     "PrefixConditioningVLM"
   ],
-  "freeze_vision_encoder": true,
-  "lora_alpha": 16,
-  "lora_dropout": 0.1,
-  "lora_r": 16,
-  "lora_target_modules": null,
-  "max_length": 30,
-  "mlp_hidden_dim": 2048,
-  "model_type": "prefix_conditioning_vlm",
-  "projection_dim": 512,
-  "projection_type": "linear",
-  "text_config": {
-    "_name_or_path": "HuggingFaceTB/SmolLM-135M",
-    "add_cross_attention": false,
-    "architectures": [
-      "LlamaForCausalLM"
-    ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 0,
-    "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": 0,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "head_dim": 64,
-    "hidden_act": "silu",
-    "hidden_size": 576,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
-    "intermediate_size": 1536,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 2048,
-    "min_length": 0,
-    "mlp_bias": false,
-    "model_type": "llama",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 9,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 30,
-    "num_key_value_heads": 3,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "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": 10000.0,
-    "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": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": "float32",
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 49152
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.53.3",
   "vision_config": {
-    "_name_or_path": "google/siglip-base-patch16-224",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "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_pytorch_tanh",
+    "model_type": "siglip_vision_model",
     "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "image_size": 224,
-    "intermediate_size": 3072,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-06,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "siglip_vision_model",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_channels": 3,
-    "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "patch_size": 16,
-    "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,
-    "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": "float32",
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false
+    "patch_size": 16
+  },
+  "text_config": {
+    "model_type": "gpt2",
+    "vocab_size": 49152,
+    "n_positions": 2048,
+    "n_embd": 576,
+    "n_layer": 30,
+    "n_head": 9
   },
-  "vision_unfreeze_layers": 0
-}
+  "projector_hidden_size": 512,
+  "vision_feature_select_strategy": "full",
+  "vision_feature_layer": -1
+}

multi_modal_projector/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52cbc298ed3ff4a9fd20e63080f6e722a57136240508d0ac294005ee583ecfe4
+size 580

multi_modal_projector/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58cbfbfc1d88bca785733cdec608c08da434ad60f4c4bd2e2982f6c10dd54d8f
+size 1835008

special_tokens_map.json

@@ -32,13 +32,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

text_model/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "use_cache": true,
+  "vocab_size": 49152
+}

text_model/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.53.3"
+}

text_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce16e82eb17e4d75ac020086b09dbd796140317c83d639606feb3b9b4dbc307
+size 545494928

vision_encoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dea7354fafd5a7dd96e08b1a3fd632e09185ff100a5d914974be30eb0877133
+size 111186

vision_encoder/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbafa23edb2db76ee79def6879ea1717481380341b526890c8188363a298f84
+size 371589120