46 lines
1.3 KiB
JSON
46 lines
1.3 KiB
JSON
|
{
|
||
|
|
"timestamp": 1774921447,
|
||
|
|
"model": "Qwen/Qwen3-VL-Embedding-2B",
|
||
|
|
"output_dir": "/home/szymon/source/repos/Qwen3-VL-Embedding-2B-quant/artifacts/checkpoints/qwen3_vl_embedding_2b_awq_v1",
|
||
|
|
"quant_mode": "awq",
|
||
|
|
"quantizer_impl": "llmcompressor",
|
||
|
|
"modelopt_cfg": null,
|
||
|
|
"llmcompressor_scheme": "W4A16_ASYM",
|
||
|
|
"llmcompressor_pipeline": "layer_sequential",
|
||
|
|
"llmcompressor_sequential_targets": [
|
||
|
|
"Qwen3VLTextDecoderLayer"
|
||
|
|
],
|
||
|
|
"vllm_quantization_backend": "compressed-tensors",
|
||
|
|
"vllm_dtype": null,
|
||
|
|
"manifest": "/home/szymon/source/repos/Qwen3-VL-Embedding-2B-quant/data/calibration/master/manifests/calibration_manifest.jsonl",
|
||
|
|
"num_calib_samples": 876,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"device": "cuda",
|
||
|
|
"disable_globs": [
|
||
|
|
"*visual*",
|
||
|
|
"*vision*"
|
||
|
|
],
|
||
|
|
"skipped_image_rows": 124,
|
||
|
|
"elapsed_s": 936.56,
|
||
|
|
"copied_remote_files": [
|
||
|
|
"added_tokens.json",
|
||
|
|
"chat_template.jinja",
|
||
|
|
"config.json",
|
||
|
|
"merges.txt",
|
||
|
|
"preprocessor_config.json",
|
||
|
|
"special_tokens_map.json",
|
||
|
|
"tokenizer.json",
|
||
|
|
"tokenizer_config.json",
|
||
|
|
"video_preprocessor_config.json",
|
||
|
|
"vocab.json"
|
||
|
|
],
|
||
|
|
"export_checks": {
|
||
|
|
"config_json": true,
|
||
|
|
"weights": true,
|
||
|
|
"tokenizer_config_json": true,
|
||
|
|
"tokenizer_json_or_vocab": true,
|
||
|
|
"chat_template": true,
|
||
|
|
"processor_definition": true,
|
||
|
|
"compressed_tensors_config": true
|
||
|
|
}
|
||
|
|
}
|