Oct 14 26 days ago 17:44 docs: update model card, context lengths, and config specs Oct 12 28 days ago 12:56 update models Sep 7 13:55 Apply the model card standard 12:56 Apply the model card standard 09:40 Add MLX int4 variants for 0.5B, 1.5B and 3B Sep 3 14:49 Stop restating quantized, and drop the unused default quantized duplicated precisions.json, which is authoritative for the
quantized/non-quantized partition. default expressed a per-repository
recommendation nothing consumed: the library resolves its own per-platform
default. Both are gone from the schema. 12:21 Correct the published metadata Adds library_name to the model card. Aug 31 15:59 Re-export 3b 8da4w with the right stop token, and correct the configs (#1 ) - Re-export 3b 8da4w with the right stop token, and correct the configs (9d35f56e3d4835f67e5f1ff280e8233bd7d914a9) Jun 22 09:43 Use min/max dynamic shape bounds for forward inputs/outputs 08:39 Backfill constant metadata method values in config.json from .pte May 14 08:35 Add stub root config.json for HF download counter May 13 19:38 Add spec-compliant config.json files 13:54 Add spec-compliant config.json files 13:24 Remove old-layout metadata orphaned by MODEL_SPEC.md restructure 13:11 Restructure to MODEL_SPEC.md convention Apr 9 23:57 Upload qwen2_5_3b_8da4w.pte 23:55 Upload qwen2_5_1_5b_8da4w.pte 23:55 Upload qwen2_5_0_5b_8da4w.pte Jan 28 11:30 Fix invalid JSON in config.json Add missing quotes around model_type key to make the JSON valid and parseable. May 8, 2025 12:56 Update README.md May 2, 2025 09:17 Update README.md Apr 29, 2025 15:14 Update qwen-2.5-0.5B/quantized/config.json 15:14 Update qwen-2.5-0.5B/original/config.json 15:13 Update qwen-2.5-1.5B/quantized/config.json 15:13 Update qwen-2.5-1.5B/original/config.json 15:13 Update qwen-2.5-3B/original/config.json 15:13 Update qwen-2.5-3B/quantized/config.json 15:12 Upload qwen2_5_3b_8da4w.pte 15:11 Upload qwen2_5_3b_bf16.pte 15:09 Upload qwen2_5_1_5b_8da4w.pte 15:08 Upload qwen2_5_1_5b_bf16.pte 15:07 Upload qwen2_5_0_5b_8da4w.pte 15:07 Upload qwen2_5_0_5b_bf16.pte 15:05 Create qwen-2.5-3B/quantized/config.json 15:04 Create qwen-2.5-3B/original/config.json 15:04 Create qwen-2.5-1.5B/quantized/config.json 15:04 Create qwen-2.5-0.5B/quantized/config.json 15:03 Create qwen-2.5-1.5B/original/config.json 15:03 Create quantized/config.json 15:03 Create qwen-2.5-0.5B/original/config.json 15:02 Delete original/qwen2_5_bf16.pte 15:02 Delete original/config.json 14:53 Create config.json 14:52 Update README.md 14:51 Update README.md Apr 24, 2025 14:33 Update README.md 14:26 Update original/config.json 14:24 Upload qwen2_5_bf16.pte 14:19 Create original/config.json 14:19 Upload 2 files 
