Upload folder using huggingface_hub

README.md

@@ -0,0 +1,21 @@
+---
+license: other
+license_name: deepseek
+license_link: LICENSE
+pipeline_tag: image-text-to-text
+tags:
+- mlx
+---
+
+# mlx-community/deepseek-vl-7b-chat-8bit
+This model was converted to MLX format from [`deepseek-ai/deepseek-vl-7b-chat`]() using mlx-vlm version **0.0.11**.
+Refer to the [original model card](https://huggingface.co/deepseek-ai/deepseek-vl-7b-chat) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model mlx-community/deepseek-vl-7b-chat-8bit --max-tokens 100 --temp 0.0
+```

config.json

@@ -0,0 +1,75 @@
+{
+    "aligner_config": {
+        "cls": "MlpProjector",
+        "model_type": "aligner",
+        "params": {
+            "depth": 2,
+            "input_dim": 1024,
+            "n_embed": 4096,
+            "projector_type": "low_high_hybrid_split_mlp_gelu"
+        }
+    },
+    "architectures": [
+        "MultiModalityCausalLM"
+    ],
+    "language_config": {
+        "max_position_embeddings": 16384,
+        "model_type": "llama",
+        "num_hidden_layers": 30,
+        "torch_dtype": "float16",
+        "vocab_size": 102400
+    },
+    "model_type": "multi_modality",
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "torch_dtype": "float16",
+    "transformers_version": "4.38.2",
+    "vision_config": {
+        "cls": "HybridVisionTower",
+        "model_type": "vision",
+        "params": {
+            "concat_type": "tuple",
+            "freeze_high": true,
+            "freeze_low": true,
+            "high_res_cfg": {
+                "ckpt_path": "",
+                "image_size": 1024,
+                "model_name": "sam_b_downsample",
+                "output_dim": 1024,
+                "pixel_mean": [
+                    0.48145466,
+                    0.4578275,
+                    0.40821073
+                ],
+                "pixel_std": [
+                    0.26862954,
+                    0.26130258,
+                    0.27577711
+                ],
+                "select_feature": "same",
+                "select_layer": -1
+            },
+            "low_res_cfg": {
+                "ckpt_path": "",
+                "image_size": 384,
+                "model_name": "siglip_large_patch16_384",
+                "output_dim": 1024,
+                "pixel_mean": [
+                    0.5,
+                    0.5,
+                    0.5
+                ],
+                "pixel_std": [
+                    0.5,
+                    0.5,
+                    0.5
+                ],
+                "select_feature": "same",
+                "select_layer": -1
+            }
+        },
+        "intermediate_size": 4096
+    }
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d703cda4adb5d7f9583b7b39eb2bb6a684dfdf5730761610f19774aa27a0aef
+size 5364486329

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a42b61379cd443d612ba5643eb64ae3f15b27e9e4cba2842ee2b0ed9120271
+size 2451263766

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<image_placeholder>"
+  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,148 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100009": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100015": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<image>"
+  ],
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": null,
+  "processor_class": "VLChatProcessor",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}