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-small-6bit
+This model was converted to MLX format from [`prince-canuma/deepseek-vl2-small`]() using mlx-vlm version **0.1.5**.
+Refer to the [original model card](https://huggingface.co/prince-canuma/deepseek-vl2-small) 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-small-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 +1,146 @@
+{
+    "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"
+        },
+        "first_k_dense_replace": 1,
+        "hidden_size": 2048,
+        "intermediate_size": 10944,
+        "lm_head": true,
+        "max_position_embeddings": 4096,
+        "model_type": "deepseek_v2",
+        "moe_intermediate_size": 1408,
+        "n_group": 1,
+        "n_routed_experts": 64,
+        "n_shared_experts": 2,
+        "num_attention_heads": 16,
+        "num_experts_per_tok": 6,
+        "num_hidden_layers": 27,
+        "num_key_value_heads": 16,
+        "q_lora_rank": null,
+        "rm_head": false,
+        "topk_group": 1,
+        "topk_method": "greedy",
+        "torch_dtype": "bfloat16"
+    },
+    "model_type": "deepseek_vl_v2",
+    "projector_config": {
+        "model_type": "mlp_projector"
+    },
+    "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-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a759f955eeb9f3de44d4f8301bb5ae3ed35753e437508144cafb0514aa13228b
+size 5340637305

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0572961dd240850b087701a2302c526f0d418fe8971c950e508965fc14a7f5
+size 5367313527

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e9b137b4a2292ac59592219ac8ff25439e4922d3a52715585f4e9a1de4e5ef
+size 2584128337

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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜▁pad▁｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "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": "<｜▁pad▁｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100003": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100004": {
+      "content": "<|ref|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100005": {
+      "content": "<|/ref|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100006": {
+      "content": "<|det|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100007": {
+      "content": "<|/det|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100008": {
+      "content": "<|grounding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100009": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100010": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|User|>",
+    "<|Assistant|>"
+  ],
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{%- set found_item = false -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set found_item = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{%- if not found_item -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{{'### Response:\\n'}}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 100000000,
+  "pad_token": "<｜▁pad▁｜>",
+  "processor_class": "DeepseekVLV2Processor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}