runanywhere/LFM2.5-2.6B_ANE

Card: list the three bundles and which one targets a phone

Add lut8_g32_c6: phone-safe 6-chunk 8-bit bundle (every graph under the iOS 500 MB tier)

Add lut8_g32 bundle (8-bit weight-only, fp16 compute)

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload lfm2_5_2_6b_lmhead.iodesc.json with huggingface_hub

Upload lfm2_5_2_6b_decode_chunk3.iodesc.json with huggingface_hub

Upload lfm2_5_2_6b_decode_chunk2.iodesc.json with huggingface_hub

Upload lfm2_5_2_6b_decode_chunk1.iodesc.json with huggingface_hub

Upload lfm2_5_2_6b_decode_chunk0.iodesc.json with huggingface_hub

Upload tokenizer.json with huggingface_hub

Upload lfm2_5_2_6b_embed_f16.bin with huggingface_hub

Upload lfm2-5-2-6b.json with huggingface_hub

Upload README.md with huggingface_hub

initial commit