Upload 12 files

README.md

@@ -0,0 +1,41 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- multimodal
+- vision
+- image-text-to-text
+- mlx
+datasets:
+- HuggingFaceM4/OBELICS
+- laion/laion-coco
+- wikipedia
+- facebook/pmd
+- pixparse/idl-wds
+- pixparse/pdfa-eng-wds
+- wendlerc/RenderedText
+- HuggingFaceM4/the_cauldron
+- teknium/OpenHermes-2.5
+- GAIR/lima
+- databricks/databricks-dolly-15k
+- meta-math/MetaMathQA
+- TIGER-Lab/MathInstruct
+- microsoft/orca-math-word-problems-200k
+- camel-ai/math
+- AtlasUnified/atlas-math-sets
+- tiedong/goat
+---
+
+# mlx-community/idefics2-8b-4bit
+This model was converted to MLX format from [`HuggingFaceM4/idefics2-8b`]() using mlx-vllm version **0.0.4**.
+Refer to the [original model card](https://huggingface.co/HuggingFaceM4/idefics2-8b) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model mlx-community/idefics2-8b-4bit --max-tokens 100 --temp 0.0
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<end_of_utterance>": 32002,
+  "<fake_token_around_image>": 32000,
+  "<image>": 32001
+}

config.json

@@ -0,0 +1,34 @@
+{
+    "architectures": [
+        "Idefics2ForConditionalGeneration"
+    ],
+    "image_token_id": 32001,
+    "model_type": "idefics2",
+    "perceiver_config": {
+        "model_type": "idefics2"
+    },
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "text_config": {
+        "max_position_embeddings": 32768,
+        "model_type": "mistral",
+        "pad_token_id": 0,
+        "rms_norm_eps": 1e-05,
+        "vocab_size": 32003
+    },
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "transformers_version": "4.39.0.dev0",
+    "use_cache": true,
+    "vision_config": {
+        "hidden_size": 1152,
+        "image_size": 980,
+        "intermediate_size": 4304,
+        "model_type": "idefics2",
+        "num_attention_heads": 16,
+        "num_hidden_layers": 27,
+        "patch_size": 14
+    }
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3493240ca802ec5979eac2178efcac88337f9c9fd97dac6ea94a6b70ca0b8177
+size 5356662816

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bba7286dac10a6acf4b10c25c78ec2861bcdd33d5a18125636ea63106c623b8
+size 159878808

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "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": "Idefics2ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "Idefics2Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 980,
+    "shortest_edge": 378
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_len": 64,
+  "processor_class": "Idefics2Processor"
+}

special_tokens_map.json

@@ -0,0 +1,53 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<fake_token_around_image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<end_of_utterance>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<fake_token_around_image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<end_of_utterance>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<fake_token_around_image>",
+    "<image>",
+    "<end_of_utterance>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "processor_class": "Idefics2Processor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}