* Use types from typing for better compatibility with older Python versions * Split last double end of line token as per BlinkDL's suggestion * Fix MSVC warnings * Drop Q4_2 support * Update ggml * Bump file format version for quantization changes * Apply suggestions |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| expected_logits.bin | ||
| test_ggml_basics.c | ||
| test_tiny_rwkv.c | ||
| tiny-rwkv-660K-FP16.bin | ||
| tiny-rwkv-660K-FP32.bin | ||