diff options
| author | Howard Su <howard0su@gmail.com> | 2023-06-28 10:13:02 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-06-28 20:13:02 +0300 |
| commit | b922bc351b69770cec2d35d2aa50fa052b95ca93 (patch) | |
| tree | ab14ba0af7274ddc5822fb5d110a7d0c953daa43 /prompts/chat-with-vicuna-v1.txt | |
| parent | 7f9753fa1263c4eded9a3de19778562f0e1093d7 (diff) | |
llama : remove shards weight file support (#2000)
* Remove multiple shards
* Remove multiple file loaders
* Remove llama_load_tensor_shard class
* Simplify load logic
* Remove dead code guess_n_parts function
* Remove vocab_only from constructor of llama_model_loader
* Remove alignment_prevents_mmap which is not more needed.
* Remove useless check
Diffstat (limited to 'prompts/chat-with-vicuna-v1.txt')
0 files changed, 0 insertions, 0 deletions