lfm3-omni:2b-mxfp8

12 9 minutes ago

LFM3-17B is a tri-hybrid for local agents and specialized applications.

vision tools audio 2b
... /
json
dd756829f85a ยท 2.4kB
{
"audio_markers": true,
"audio_out_token": "<|audio_out|>",
"audio_token": "<|audio|>",
"audio_tokenizer_subfolder": "audio_tokenizer",
"feature_extractor": {
"encoder_stride": 8,
"feature_extractor_type": "Lfm3OmniFeatureExtractor",
"feature_size": 128,
"hop_length": 160,
"log_floor": -12.0,
"n_fft": 400,
"normalization_divisor": 4.0,
"normalization_offset": 4.0,
"padding_side": "right",
"padding_value": 0.0,
"return_attention_mask": true,
"sampling_rate": 16000,
"win_length": 400,
"auto_map": {
"AutoFeatureExtractor": "feature_extraction_lfm3_omni.Lfm3OmniFeatureExtractor"
}
},
"image_processor": {
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.5,
0.5,
0.5
],
"image_processor_type": "Lfm3VlImageProcessor",
"image_std": [
0.5,
0.5,
0.5
],
"merge_size": 2,
"patch_size": 16,
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 2097152,
"shortest_edge": 65536
},
"temporal_patch_size": 2,
"auto_map": {
"AutoImageProcessor": "image_processing_lfm3_vl.Lfm3VlImageProcessor"
}
},
"image_token": "<|image|>",
"processor_class": "Lfm3OmniProcessor",
"video_processor": {
"cap_pixels_per_frame": false,
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"do_sample_frames": true,
"fps": 2.0,
"image_mean": [
0.5,
0.5,
0.5
],
"image_std": [
0.5,
0.5,
0.5
],
"max_frames": 384,
"max_video_tokens": 768,
"merge_size": 2,
"min_frames": 4,
"patch_size": 16,
"resample": 3,
"rescale_factor": 0.00392156862745098,
"return_metadata": false,
"size": {
"longest_edge": 25165824,
"shortest_edge": 4096
},
"temporal_patch_size": 2,
"video_processor_type": "Lfm3VlVideoProcessor",
"auto_map": {
"AutoVideoProcessor": "video_processing_lfm3_vl.Lfm3VlVideoProcessor"
}
},
"video_token": "<|video|>",
"vision_end_token": "<|vision_end|>",
"vision_markers": true,
"vision_start_token": "<|vision_start|>",
"auto_map": {
"AutoProcessor": "processing_lfm3_omni.Lfm3OmniProcessor"
}
}