dea929f8ca
* 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 |
||
|---|---|---|
| .. | ||
| prompt | ||
| 20B_tokenizer.json | ||
| chat_with_bot.py | ||
| convert_pytorch_to_ggml.py | ||
| convert_pytorch_to_ggml.test.py | ||
| generate_completions.py | ||
| measure_pexplexity.py | ||
| merge_lora_into_ggml.py | ||
| quantize.py | ||
| requirements.txt | ||
| rwkv_cpp_model.py | ||
| rwkv_cpp_shared_library.py | ||
| sampling.py | ||