Upload Qwen2VLForConditionalGeneration

config.json

@@ -1 +1,47 @@
-{"architectures": ["Qwen2VLForConditionalGeneration"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "vision_start_token_id": 151652, "vision_end_token_id": 151653, "vision_token_id": 151654, "image_token_id": 151655, "video_token_id": 151656, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen2_vl", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.41.2", "use_cache": true, "use_sliding_window": false, "vision_config": {"depth": 32, "embed_dim": 1280, "mlp_ratio": 4, "num_heads": 16, "in_chans": 3, "hidden_size": 3584, "patch_size": 14, "spatial_merge_size": 2, "spatial_patch_size": 14, "temporal_patch_size": 2}, "rope_scaling": {"type": "mrope", "mrope_section": [16, 24, 24]}, "vocab_size": 152064}
+{
+  "_name_or_path": "chakra-labs/pango-7b-sft-checkpoints",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b2bc09b616be132f295650b9d719d7723dc567021adf0cb3b06c29ad8bc08c
+oid sha256:4123346318ded0478e0076e5e70d3fe55a13696114dc63c86bac98d001e25e9d
 size 4966659944

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1f19321021453a7f4ce0bac6078771951dc4d12afdb54ad20434e08523dfda7
+oid sha256:f22be2de6f063a6d54cd2a32cc98ca6c0a905df51fee75738879558f297a29bf
 size 4991495816

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae5daba3d3bbf8ab20f9835eac37f5d9e17e6e5ec194ccff5f4b4df9b081681
+oid sha256:463cf07047133f92d49308ae5bfadfdf250429a52633ea8b04b69d398fcb1b66
 size 4932751040

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0252b097f1433c11182c187fc20af263b87ce78100a6093023a253016376db8
+oid sha256:06c57eb09735888155f626f3276938e7699d29b2b3624fbef052fb3aafd6cc18
 size 1691924384