System Info
transformers version: 4.45.0.dev0- Platform: Linux-5.10.134-16.101.al8.x86_64-x86_64-with-glibc2.35
- Python version: 3.10.14
- Huggingface_hub version: 0.23.4
- Safetensors version: 0.4.3
- Accelerate version: 0.32.1
- Accelerate config: not found
- PyTorch version (GPU?): 2.4.0+cu121 (True)
- Tensorflow version (GPU?): not installed (NA)
- Flax version (CPU?/GPU?/TPU?): not installed (NA)
- Jax version: not installed
- JaxLib version: not installed
- Using distributed or parallel set-up in script?:
- Using GPU in script?:
- GPU type: NVIDIA L20Y
Who can help?
@amyeroberts @qubvel
Information
Tasks
Reproduction
- Download the
config.json from Qwen2-VL-7B-Instruct HF main repo to /tmp/Qwen2-VL-7B-Instruct/config.json.
- The downloaded config file content should be:
{
"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
}
- Install the latest
transformers version via pip install git+https://github.com/huggingface/transformers@main
- Run the following script:
from transformers import AutoConfig
config = AutoConfig.from_pretrained('/tmp/Qwen2-VL-7B-Instruct/')
print(config)
- The result is:
Unrecognized keys in `rope_scaling` for 'rope_type'='default': {'mrope_section'}
Qwen2VLConfig {
"_name_or_path": "/tmp/Qwen2-VL-7B-Instruct/",
"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": "4.45.0.dev0",
"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
}
It prints a warning message, and the output rope_scaling.type and rope_scaling.rope_type are set to default, but mrope is expected.
Expected behavior
This bug seems to be introduced in a recent version of transformers.
When I switch to a old version by git+https://github.com/huggingface/transformers@21fac7abba2a37fae86106f87fcf9974fd1e3830, the output is correct:
Qwen2VLConfig {
"_name_or_path": "/tmp/Qwen2-VL-7B-Instruct/",
"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
],
"type": "mrope"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.45.0.dev0",
"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
}
System Info
transformersversion: 4.45.0.dev0Who can help?
@amyeroberts @qubvel
Information
Tasks
examplesfolder (such as GLUE/SQuAD, ...)Reproduction
config.jsonfrom Qwen2-VL-7B-Instruct HF main repo to/tmp/Qwen2-VL-7B-Instruct/config.json.{ "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 }transformersversion viapip install git+https://github.com/huggingface/transformers@mainIt prints a warning message, and the output
rope_scaling.typeandrope_scaling.rope_typeare set todefault, butmropeis expected.Expected behavior
This bug seems to be introduced in a recent version of transformers.
When I switch to a old version by
git+https://github.com/huggingface/transformers@21fac7abba2a37fae86106f87fcf9974fd1e3830, the output is correct: