| .. |
|
prompt
|
punish repetitions & break if END_OF_TEXT & decouple prompts from chat script (#37)
|
2023-04-30 18:50:05 +05:00 |
|
20B_tokenizer.json
|
Add text generation and chat scripts
|
2023-04-02 15:03:31 +04:00 |
|
chat_with_bot.py
|
Add support for the world tokenizer (#86)
|
2023-06-08 16:37:18 +05:00 |
|
convert_pytorch_to_ggml.py
|
Various improvements & upgrade ggml (#75)
|
2023-05-27 16:02:24 +05:00 |
|
convert_pytorch_to_ggml.test.py
|
Various improvements & upgrade ggml (#75)
|
2023-05-27 16:02:24 +05:00 |
|
generate_completions.py
|
Add support for the world tokenizer (#86)
|
2023-06-08 16:37:18 +05:00 |
|
measure_pexplexity.py
|
Add support for the world tokenizer (#86)
|
2023-06-08 16:37:18 +05:00 |
|
merge_lora_into_ggml.py
|
Various improvements & upgrade ggml (#75)
|
2023-05-27 16:02:24 +05:00 |
|
quantize.py
|
Various improvements & upgrade ggml (#75)
|
2023-05-27 16:02:24 +05:00 |
|
requirements.txt
|
Add text generation and chat scripts
|
2023-04-02 15:03:31 +04:00 |
|
rwkv_cpp_model.py
|
Fix pytorch storage warnings, fixes #80 (#88)
|
2023-06-03 15:09:51 +05:00 |
|
rwkv_cpp_shared_library.py
|
File parsing and memory usage optimization (#74)
|
2023-05-31 16:31:19 +05:00 |
|
rwkv_tokenizer.py
|
Fix bug in world tokenizer (#93)
|
2023-06-11 11:46:54 +05:00 |
|
rwkv_tokenizer_test.py
|
Add support for the world tokenizer (#86)
|
2023-06-08 16:37:18 +05:00 |
|
rwkv_vocab_v20230424.txt
|
Add support for the world tokenizer (#86)
|
2023-06-08 16:37:18 +05:00 |
|
sampling.py
|
Add text generation and chat scripts
|
2023-04-02 15:03:31 +04:00 |
b88ae59604