first commit

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": 1280,
+    "intermediate_size": 6848,
+    "kv_lora_rank": null,
+    "lm_head": true,
+    "max_position_embeddings": 4096,
+    "model_type": "deepseek_v2",
+    "moe_intermediate_size": 896,
+    "n_group": 1,
+    "n_routed_experts": 64,
+    "n_shared_experts": 2,
+    "num_attention_heads": 10,
+    "num_experts_per_tok": 6,
+    "num_hidden_layers": 12,
+    "num_key_value_heads": 10,
+    "q_lora_rank": null,
+    "qk_nope_head_dim": 0,
+    "qk_rope_head_dim": 0,
+    "rm_head": false,
+    "topk_group": 1,
+    "topk_method": "greedy",
+    "torch_dtype": "bfloat16",
+    "use_mla": false,
+    "v_head_dim": 0,
+    "vocab_size": 129280
+  },
+  "model_type": "deepseek_vl_v2",
+  "projector_config": {
+    "model_type": "mlp_projector",
+    "n_embed": 1280
+  },
+  "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
+  }
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "image-to-text", "allow_remote": true}