Upload folder using huggingface_hub

README.md

@@ -2,15 +2,15 @@
 license: other
 license_name: health-ai-developer-foundations
 license_link: https://developers.google.com/health-ai-developer-foundations/terms
-library_name: mlx
-pipeline_tag: text-generation
+library_name: transformers
+pipeline_tag: image-text-to-text
 extra_gated_heading: Access MedGemma on Hugging Face
 extra_gated_prompt: To access MedGemma on Hugging Face, you're required to review
   and agree to [Health AI Developer Foundation's terms of use](https://developers.google.com/health-ai-developer-foundations/terms).
   To do this, please ensure you're logged in to Hugging Face and click below. Requests
   are processed immediately.
 extra_gated_button_content: Acknowledge license
-base_model: google/medgemma-4b-it
+base_model: google/medgemma-4b-pt
 tags:
 - medical
 - radiology
@@ -23,29 +23,14 @@ tags:
 ---
 
 # mlx-community/medgemma-4b-it-bf16
-
-This model [mlx-community/medgemma-4b-it-bf16](https://huggingface.co/mlx-community/medgemma-4b-it-bf16) was
-converted to MLX format from [google/medgemma-4b-it](https://huggingface.co/google/medgemma-4b-it)
-using mlx-lm version **0.24.1**.
-
+This model was converted to MLX format from [`google/medgemma-4b-it`]() using mlx-vlm version **0.1.26**.
+Refer to the [original model card](https://huggingface.co/google/medgemma-4b-it) for more details on the model.
 ## Use with mlx
 
 ```bash
-pip install mlx-lm
+pip install -U mlx-vlm
 ```
 
-```python
-from mlx_lm import load, generate
-
-model, tokenizer = load("mlx-community/medgemma-4b-it-bf16")
-
-prompt = "hello"
-
-if tokenizer.chat_template is not None:
-    messages = [{"role": "user", "content": prompt}]
-    prompt = tokenizer.apply_chat_template(
-        messages, add_generation_prompt=True
-    )
-
-response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```bash
+python -m mlx_vlm.generate --model mlx-community/medgemma-4b-it-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
 ```

config.json

@@ -1,47 +1,235 @@
 {
+    "add_cross_attention": false,
     "architectures": [
         "Gemma3ForConditionalGeneration"
     ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
     "boi_token_index": 255999,
+    "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,
     "eoi_token_index": 256000,
     "eos_token_id": [
         1,
         106
     ],
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
     "image_token_index": 262144,
     "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
     "mm_tokens_per_image": 256,
     "model_type": "gemma3",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 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": {},
+    "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,
     "text_config": {
-        "attention_bias": false,
-        "attention_dropout": 0.0,
-        "attn_logit_softcapping": null,
-        "cache_implementation": "hybrid",
-        "final_logit_softcapping": null,
-        "head_dim": 256,
-        "hidden_activation": "gelu_pytorch_tanh",
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": "bfloat16",
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": 2,
+        "pad_token_id": 0,
+        "eos_token_id": 1,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "model_type": "gemma3_text",
+        "vocab_size": 262208,
+        "max_position_embeddings": 131072,
         "hidden_size": 2560,
-        "initializer_range": 0.02,
         "intermediate_size": 10240,
-        "max_position_embeddings": 131072,
-        "model_type": "gemma3_text",
-        "num_attention_heads": 8,
         "num_hidden_layers": 34,
+        "num_attention_heads": 8,
+        "head_dim": 256,
         "num_key_value_heads": 4,
-        "query_pre_attn_scalar": 256,
+        "initializer_range": 0.02,
         "rms_norm_eps": 1e-06,
+        "use_cache": true,
+        "rope_theta": 1000000,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "query_pre_attn_scalar": 256,
+        "sliding_window": 1024,
+        "final_logit_softcapping": null,
+        "attn_logit_softcapping": null,
+        "cache_implementation": "hybrid",
         "rope_local_base_freq": 10000,
+        "sliding_window_pattern": 6,
         "rope_scaling": {
             "factor": 8.0,
             "rope_type": "linear"
-        },
-        "rope_theta": 1000000,
-        "sliding_window": 1024,
-        "sliding_window_pattern": 6,
-        "torch_dtype": "bfloat16",
-        "use_cache": true,
-        "vocab_size": 262208
+        }
     },
-    "torch_dtype": "bfloat16",
-    "transformers_version": "4.52.0.dev0"
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.52.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vision_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": "bfloat16",
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "model_type": "siglip_vision_model",
+        "vision_use_head": false,
+        "hidden_size": 1152,
+        "intermediate_size": 4304,
+        "num_hidden_layers": 27,
+        "num_attention_heads": 16,
+        "num_channels": 3,
+        "patch_size": 14,
+        "image_size": 896,
+        "attention_dropout": 0.0,
+        "layer_norm_eps": 1e-06,
+        "hidden_act": "gelu_pytorch_tanh"
+    }
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af6a5f148e1b27fd04b7c9bffba42e264edb2ff4c23ddd08be587342748847ab
-size 5338068786
+oid sha256:10de905eb103e7f174d1219fd2fe706234fed4f958a6ebe4ebef8cc3aea01682
+size 5332884576

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:678d26f73e86683347cfbf3609694846f78c3e16907ac8be6c19aa21ca939512
-size 3765020765
+oid sha256:122cd3312cc3b5449bce2df491ffe388b9e85ab89d0e65142e55a1e5e1e33c4a
+size 4609898146

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}