Upload folder using huggingface_hub

README.md

@@ -0,0 +1,22 @@
+---
+license: other
+license_name: deepseek
+license_link: https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- mlx
+---
+
+# mlx-community/deepseek-vl2-6bit
+This model was converted to MLX format from [`prince-canuma/deepseek-vl2`]() using mlx-vlm version **0.1.5**.
+Refer to the [original model card](https://huggingface.co/prince-canuma/deepseek-vl2) 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-vl2-6bit --max-tokens 100 --temp 0.0
+```

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}<|User|>:{% elif message['role'] == 'assistant' %}<|Assistant|>{% endif %} {{message['content']}}\n\n{% endfor %}{% if add_generation_prompt %}<|Assistant|>:{% endif %}"
+}

config.json

@@ -0,0 +1,150 @@
+{
+    "candidate_resolutions": [
+        [
+            384,
+            384
+        ],
+        [
+            384,
+            768
+        ],
+        [
+            768,
+            384
+        ],
+        [
+            384,
+            1152
+        ],
+        [
+            1152,
+            384
+        ],
+        [
+            384,
+            1536
+        ],
+        [
+            1536,
+            384
+        ],
+        [
+            768,
+            768
+        ],
+        [
+            384,
+            1920
+        ],
+        [
+            1920,
+            384
+        ],
+        [
+            384,
+            2304
+        ],
+        [
+            2304,
+            384
+        ],
+        [
+            768,
+            1152
+        ],
+        [
+            1152,
+            768
+        ],
+        [
+            384,
+            2688
+        ],
+        [
+            2688,
+            384
+        ],
+        [
+            384,
+            3072
+        ],
+        [
+            3072,
+            384
+        ],
+        [
+            768,
+            1536
+        ],
+        [
+            1536,
+            768
+        ],
+        [
+            384,
+            3456
+        ],
+        [
+            3456,
+            384
+        ],
+        [
+            1152,
+            1152
+        ]
+    ],
+    "global_view_pos": "head",
+    "language_config": {
+        "architectures": [
+            "DeepseekV2ForCausalLM"
+        ],
+        "auto_map": {
+            "AutoConfig": "configuration_deepseek.DeepseekV2Config",
+            "AutoModel": "modeling_deepseek.DeepseekV2Model",
+            "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
+        },
+        "bos_token_id": 0,
+        "eos_token_id": 1,
+        "first_k_dense_replace": 1,
+        "hidden_size": 2560,
+        "intermediate_size": 12288,
+        "lm_head": false,
+        "max_position_embeddings": 4096,
+        "model_type": "deepseek_v2",
+        "moe_intermediate_size": 1536,
+        "n_group": 1,
+        "n_routed_experts": 72,
+        "n_shared_experts": 2,
+        "norm_topk_prob": true,
+        "num_experts_per_tok": 6,
+        "q_lora_rank": null,
+        "rm_head": false,
+        "routed_scaling_factor": 2.0,
+        "scoring_func": "sigmoid",
+        "topk_group": 1,
+        "topk_method": "noaux_tc",
+        "torch_dtype": "bfloat16",
+        "vocab_size": 129280
+    },
+    "model_type": "deepseek_vl_v2",
+    "projector_config": {
+        "model_type": "mlp_projector",
+        "n_embed": 2560
+    },
+    "quantization": {
+        "group_size": 64,
+        "bits": 6
+    },
+    "tile_tag": "2D",
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.38.2",
+    "vision_config": {
+        "layers": 27,
+        "mlp_ratio": 3.7362,
+        "model_name": "siglip_so400m_patch14_384",
+        "model_type": "vision",
+        "patch_size": 14,
+        "width": 1152,
+        "skip_vision_non_divisible": true
+    }
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b48ed3efe938fa81fc52934bd77d5f4394795fc12902b39a7128250e53373cf
+size 5325873457

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9bfea22afb16fbed400ce9a26b9004563a74846720906fc374afd5e98fd2105
+size 5361210089

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:868d5262cac9c2933d47c43f39b223dd1fcc0f2bbb6ddf0593a8d1ce71eaadf2
+size 5166568395

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98021c7380851caa065d734dc8402c588ad33ab80b1dc5749dc18c2f2f6b1efb
+size 5361210173

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d32445ebe9dad1f3d02b71acbed467aaf81f0ac73787e3d303d58e65f7aa252
+size 1286668913

processor_config.json

@@ -0,0 +1,116 @@
+{
+  "add_special_token": false,
+  "candidate_resolutions": [
+    [
+      384,
+      384
+    ],
+    [
+      384,
+      768
+    ],
+    [
+      768,
+      384
+    ],
+    [
+      384,
+      1152
+    ],
+    [
+      1152,
+      384
+    ],
+    [
+      384,
+      1536
+    ],
+    [
+      1536,
+      384
+    ],
+    [
+      768,
+      768
+    ],
+    [
+      384,
+      1920
+    ],
+    [
+      1920,
+      384
+    ],
+    [
+      384,
+      2304
+    ],
+    [
+      2304,
+      384
+    ],
+    [
+      768,
+      1152
+    ],
+    [
+      1152,
+      768
+    ],
+    [
+      384,
+      2688
+    ],
+    [
+      2688,
+      384
+    ],
+    [
+      384,
+      3072
+    ],
+    [
+      3072,
+      384
+    ],
+    [
+      768,
+      1536
+    ],
+    [
+      1536,
+      768
+    ],
+    [
+      384,
+      3456
+    ],
+    [
+      3456,
+      384
+    ],
+    [
+      1152,
+      1152
+    ]
+  ],
+  "downsample_ratio": 2,
+  "ignore_id": -100,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_token": "<image>",
+  "mask_prompt": false,
+  "normalize": true,
+  "pad_token": "<\uff5c\u2581pad\u2581\uff5c>",
+  "patch_size": 14,
+  "processor_class": "DeepseekVLV2Processor",
+  "sft_format": "deepseek"
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜▁pad▁｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}