Upload folder using huggingface_hub

README.md

@@ -0,0 +1,42 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags: [medical, vqa, vision-language, healthcare, morocco, lora, smolvlm]
+base_model: HuggingFaceTB/SmolVLM-256M-Instruct
+datasets: [flaviagiammarino/vqa-rad]
+language: [en]
+---
+
+# doctoria-rally-ai 🩺
+
+Fine-tuned medical Vision-Language Model for **SahhaAI** — offline, private
+wound-care & medical VQA for disconnected clinics in Morocco.
+
+- **Base:** `HuggingFaceTB/SmolVLM-256M-Instruct` (SmolVLM)
+- **Method:** LoRA fine-tune (PyTorch + PEFT, trained locally on Apple Silicon / MPS)
+- **Data:** [VQA-RAD](https://huggingface.co/datasets/flaviagiammarino/vqa-rad) (radiology VQA, CC0)
+- **Runs:** in-browser (WebGPU via transformers.js) and locally — data stays on device
+
+## Benchmark (VQA-RAD test)
+
+- Closed-ended accuracy: **0.439**
+- Open-ended token-F1: **0.228**
+- Speed: **19.0 tok/s** on Apple Silicon (MPS)
+- See repo `finetune/BENCHMARK.md` for base-vs-fine-tuned analysis.
+
+## Use
+```python
+from transformers import AutoProcessor, AutoModelForImageTextToText
+from PIL import Image
+m = AutoModelForImageTextToText.from_pretrained("doctoria/doctoria-rally-ai")
+p = AutoProcessor.from_pretrained("doctoria/doctoria-rally-ai")
+msgs = [{"role":"user","content":[{"type":"image"},{"type":"text","text":"Assess this wound."}]}]
+text = p.apply_chat_template(msgs, add_generation_prompt=True)
+inp = p(text=text, images=[[Image.open("wound.jpg")]], return_tensors="pt")
+print(p.batch_decode(m.generate(**inp, max_new_tokens=128), skip_special_tokens=True)[0])
+```
+
+⚠ **Decision support, not a diagnosis.** A trained health worker stays in the loop.
+
+— Author: **Jad Tounsi El Azzouzi** · part of SahhaAI · Apache-2.0

chat_template.jinja

@@ -0,0 +1,2 @@
+<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
+{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}

config.json

@@ -0,0 +1,194 @@
+{
+  "architectures": [
+    "Idefics3ForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "image_token_id": 49190,
+  "model_type": "idefics3",
+  "pad_token_id": 128002,
+  "scale_factor": 4,
+  "text_config": {
+    "_attn_implementation_autoset": false,
+    "_flash_attn_2_enabled": true,
+    "_name_or_path": "None",
+    "add_cross_attention": false,
+    "architectures": [
+      "VLlama3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dtype": "float32",
+    "eos_token_id": 2,
+    "finetuning_task": null,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 576,
+    "initializer_range": 0.041666666666666664,
+    "intermediate_size": 1536,
+    "is_decoder": false,
+    "is_llama_config": true,
+    "max_position_embeddings": 8192,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "neftune_noise_alpha": 0.0,
+    "num_attention_heads": 9,
+    "num_hidden_layers": 30,
+    "num_key_value_heads": 3,
+    "pad_token_id": 2,
+    "perceiver_config": {
+      "_attn_implementation_autoset": false,
+      "_name_or_path": "",
+      "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": "silu",
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "vllama3",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_key_value_heads": 1,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "qk_layer_norms_perceiver": false,
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "resampler_depth": 6,
+      "resampler_head_dim": 96,
+      "resampler_n_heads": 16,
+      "resampler_n_latents": 64,
+      "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": null,
+      "torchscript": false,
+      "transformers_version": "4.46.0",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "pixel_shuffle_factor": 4,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "pruned_heads": {},
+    "qk_layer_norms": false,
+    "rms_norm_eps": 1e-05,
+    "rope_interleaved": false,
+    "rope_parameters": {
+      "rope_theta": 100000,
+      "rope_type": "default"
+    },
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "transformers.js_config": {
+      "kv_cache_dtype": {
+        "fp16": "float16",
+        "q4f16": "float16"
+      }
+    },
+    "use_bfloat16": false,
+    "use_cache": true,
+    "use_resampler": false,
+    "vocab_size": 49280
+  },
+  "tie_word_embeddings": false,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "5.12.1",
+  "use_cache": true,
+  "vision_config": {
+    "_attn_implementation_autoset": false,
+    "add_cross_attention": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dtype": "float32",
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 512,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "layer_norm_eps": 1e-06,
+    "max_image_size": {
+      "longest_edge": 512
+    },
+    "model_type": "idefics3_vision",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "pruned_heads": {},
+    "sep_token_id": null,
+    "size": {
+      "longest_edge": 2048
+    },
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_base_siglip": true,
+    "use_bfloat16": false
+  },
+  "vocab_size": 49280
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 49279,
+  "pad_token_id": 2,
+  "transformers_version": "5.12.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48242fb6a93fc68a661415d1015b0e184307d33862ff5f97e55319c9af82bc7
+size 1025998224

processor_config.json

@@ -0,0 +1,31 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_image_splitting": true,
+    "do_normalize": true,
+    "do_pad": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Idefics3ImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_image_size": {
+      "longest_edge": 512
+    },
+    "resample": 1,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 2048
+    }
+  },
+  "image_seq_len": 64,
+  "processor_class": "Idefics3Processor"
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<end_of_utterance>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<fake_token_around_image>",
+    "<image>",
+    "<end_of_utterance>"
+  ],
+  "is_local": false,
+  "legacy": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "processor_class": "Idefics3Processor",
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "left",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}