-
Use min/max dynamic shape bounds for forward inputs/outputs
-
Backfill constant metadata method values in config.json from .pte
-
Add stub root config.json for HF download counter
-
Add spec-compliant config.json files
-
Add spec-compliant config.json files
-
Remove old-layout metadata orphaned by MODEL_SPEC.md restructure
-
Restructure to MODEL_SPEC.md convention
-
Upload qwen2_5_3b_8da4w.pte
-
Upload qwen2_5_1_5b_8da4w.pte
-
Upload qwen2_5_0_5b_8da4w.pte
-
Fix invalid JSON in config.json
Add missing quotes around model_type key to make the JSON valid and parseable.
-
Update README.md
-
Update README.md
-
Update qwen-2.5-0.5B/quantized/config.json
-
Update qwen-2.5-0.5B/original/config.json
-
Update qwen-2.5-1.5B/quantized/config.json
-
Update qwen-2.5-1.5B/original/config.json
-
Update qwen-2.5-3B/original/config.json
-
Update qwen-2.5-3B/quantized/config.json
-
Upload qwen2_5_3b_8da4w.pte
-
Upload qwen2_5_3b_bf16.pte
-
Upload qwen2_5_1_5b_8da4w.pte
-
Upload qwen2_5_1_5b_bf16.pte
-
Upload qwen2_5_0_5b_8da4w.pte
-
Upload qwen2_5_0_5b_bf16.pte
-
Create qwen-2.5-3B/quantized/config.json
-
Create qwen-2.5-3B/original/config.json
-
Create qwen-2.5-1.5B/quantized/config.json
-
Create qwen-2.5-0.5B/quantized/config.json
-
Create qwen-2.5-1.5B/original/config.json
-
Create quantized/config.json
-
Create qwen-2.5-0.5B/original/config.json
-
Delete original/qwen2_5_bf16.pte
-
Delete original/config.json
-
Create config.json
-
Update README.md
-
Update README.md
-
Update README.md
-
Update original/config.json
-
Upload qwen2_5_bf16.pte
-
Create original/config.json
-
Upload 2 files
-
initial commit