Fix vocab to 151674 (match upstream Robometer-4B byte-for-byte)

README.md

@@ -5,12 +5,12 @@ license: apache-2.0
 model_name: robometer
 pipeline_tag: robotics
 tags:
+- reward-model
 - lerobot
-- zero-shot
+- qwen3-vl
 - robotics
+- zero-shot
 - robometer
-- qwen3-vl
-- reward-model
 - vision-language
 ---
 

config.json

@@ -51,6 +51,119 @@
     "frame_pooling_attn_temperature": 1.0,
     "progress_loss_type": "discrete",
     "progress_discrete_bins": 10,
+    "vlm_config": {
+        "transformers_version": "5.5.4",
+        "architectures": [
+            "Qwen3VLForConditionalGeneration"
+        ],
+        "output_hidden_states": false,
+        "return_dict": true,
+        "dtype": null,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "problem_type": null,
+        "text_config": {
+            "architectures": null,
+            "output_hidden_states": false,
+            "return_dict": true,
+            "dtype": "bfloat16",
+            "chunk_size_feed_forward": 0,
+            "is_encoder_decoder": false,
+            "id2label": {
+                "0": "LABEL_0",
+                "1": "LABEL_1"
+            },
+            "label2id": {
+                "LABEL_0": 0,
+                "LABEL_1": 1
+            },
+            "problem_type": null,
+            "vocab_size": 151674,
+            "hidden_size": 2560,
+            "intermediate_size": 9728,
+            "num_hidden_layers": 36,
+            "num_attention_heads": 32,
+            "num_key_value_heads": 8,
+            "head_dim": 128,
+            "hidden_act": "silu",
+            "max_position_embeddings": 262144,
+            "initializer_range": 0.02,
+            "rms_norm_eps": 1e-06,
+            "use_cache": true,
+            "rope_parameters": {
+                "mrope_interleaved": true,
+                "mrope_section": [
+                    24,
+                    20,
+                    20
+                ],
+                "rope_type": "default",
+                "rope_theta": 5000000
+            },
+            "attention_bias": false,
+            "attention_dropout": 0.0,
+            "pad_token_id": null,
+            "_name_or_path": "",
+            "bos_token_id": 151643,
+            "eos_token_id": 151645,
+            "model_type": "qwen3_vl_text",
+            "tie_word_embeddings": true,
+            "output_attentions": false
+        },
+        "vision_config": {
+            "architectures": null,
+            "output_hidden_states": false,
+            "return_dict": true,
+            "dtype": null,
+            "chunk_size_feed_forward": 0,
+            "is_encoder_decoder": false,
+            "id2label": {
+                "0": "LABEL_0",
+                "1": "LABEL_1"
+            },
+            "label2id": {
+                "LABEL_0": 0,
+                "LABEL_1": 1
+            },
+            "problem_type": null,
+            "depth": 24,
+            "hidden_size": 1024,
+            "hidden_act": "gelu_pytorch_tanh",
+            "intermediate_size": 4096,
+            "num_heads": 16,
+            "in_channels": 3,
+            "patch_size": 16,
+            "spatial_merge_size": 2,
+            "temporal_patch_size": 2,
+            "out_hidden_size": 2560,
+            "num_position_embeddings": 2304,
+            "deepstack_visual_indexes": [
+                5,
+                11,
+                17
+            ],
+            "initializer_range": 0.02,
+            "_name_or_path": "",
+            "model_type": "qwen3_vl",
+            "output_attentions": false
+        },
+        "image_token_id": 151655,
+        "video_token_id": 151656,
+        "vision_start_token_id": 151652,
+        "vision_end_token_id": 151653,
+        "tie_word_embeddings": true,
+        "_name_or_path": "Qwen/Qwen3-VL-4B-Instruct",
+        "model_type": "qwen3_vl",
+        "output_attentions": false
+    },
     "normalization_mapping": {
         "VISUAL": "IDENTITY",
         "REWARD": "IDENTITY"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37245b849c3b85e757919d6d14b9af7f9342f213b793ebf9b01606e1b4ad7e73
+oid sha256:013709f2ea0b67aa50385b5c5ae61843cf7f2932b8aab7f5e45e0747560d0c14
 size 8894103800