Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,25 @@
+---
+library_name: transformers
+license: gemma
+pipeline_tag: image-text-to-text
+extra_gated_heading: Access PaliGemma on Hugging Face
+extra_gated_prompt: To access PaliGemma on Hugging Face, you’re required to review
+  and agree to Google’s usage license. 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
+tags:
+- mlx
+---
+
+# abalogh/paligemma2-3b-pt-896-4bit
+This model was converted to MLX format from [`google/paligemma2-3b-pt-896`]() using mlx-vlm version **0.1.4**.
+Refer to the [original model card](https://huggingface.co/google/paligemma2-3b-pt-896) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model abalogh/paligemma2-3b-pt-896-4bit --max-tokens 100 --temp 0.0
+```

config.json

@@ -0,0 +1,58 @@
+{
+    "_vocab_size": 257152,
+    "architectures": [
+        "PaliGemmaForConditionalGeneration"
+    ],
+    "bos_token_id": 2,
+    "eos_token_id": 1,
+    "image_token_index": 257152,
+    "model_type": "paligemma",
+    "num_hidden_layers": 26,
+    "pad_token_id": 0,
+    "projection_dim": 2304,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "text_config": {
+        "architectures": [
+            "Gemma2ForCausalLM"
+        ],
+        "attn_logit_softcapping": 50.0,
+        "cache_implementation": "hybrid",
+        "eos_token_id": [
+            1,
+            107
+        ],
+        "final_logit_softcapping": 30.0,
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 2304,
+        "intermediate_size": 9216,
+        "model_type": "gemma2",
+        "num_attention_heads": 8,
+        "num_hidden_layers": 26,
+        "num_image_tokens": 4096,
+        "num_key_value_heads": 4,
+        "query_pre_attn_scalar": 256,
+        "sliding_window": 4096,
+        "torch_dtype": "bfloat16",
+        "vocab_size": 257216
+    },
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.47.0.dev0",
+    "vision_config": {
+        "hidden_size": 1152,
+        "image_size": 896,
+        "intermediate_size": 4352,
+        "model_type": "siglip_vision_model",
+        "num_attention_heads": 16,
+        "num_hidden_layers": 27,
+        "num_image_tokens": 4096,
+        "num_positions": 256,
+        "patch_size": 14,
+        "projection_dim": 2304,
+        "torch_dtype": "bfloat16",
+        "vision_use_head": false
+    }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e7387855598171722b32ea55927258738b05a8987f828c7c231d2d4eb44d3a
+size 1711895397

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_seq_length": 4096,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "PaliGemmaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172fab587d68c56b63eb3620057c62dfd15e503079ff7fce584692e3fd5bf4da
+size 34600820