Georgi Gerganov
56ba00b923
sampling : hide prev behind API and apply #3661
...
ggml-ci
2023-10-20 18:53:27 +03:00
Georgi Gerganov
7e2b5fb1dd
sampling : add llama_sampling_print helper
2023-10-20 18:02:50 +03:00
Georgi Gerganov
b526561583
sampling : rename penalty params + reduce size of "prev" vector
2023-10-20 17:47:13 +03:00
Georgi Gerganov
6e6587656f
llama : combine repetition, frequency and presence penalties in 1 call
2023-10-20 17:05:46 +03:00
Georgi Gerganov
cd1e937821
sampling : refactor init to use llama_sampling_params
2023-10-20 14:58:20 +03:00
Georgi Gerganov
0e89203b51
speculative : add tree-based sampling example ( #3624 )
...
* sampling : one sequence per sampling context
ggml-ci
* speculative : add tree-based sampling support
ggml-ci
* speculative : reuse the n_parallel CLI param
* speculative : refactor sampling
* examples : fix build after sampling refactoring
ggml-ci
* batched : fix n_seq_id
* sampling : fix malloc
ggml-ci
* swift : fix build
ggml-ci
* swift : try to fix build
ggml-ci
* prompts : add assistant.txt
* common : add llama_batch_add() and llama_batch_clear() helpers
* speculative : minor refactor
ggml-ci
* minor : comments + rename
ggml-ci
* speculative : fix off-by-one for n_drafted
* speculative : fix the n_drafted fix + p constants
2023-10-18 16:21:57 +03:00
Kerfuffle
70c29da118
common : fix mirostat state when using multiple sequences ( #3543 )
...
* Fix mirostat state when using multiple sequences
* Fix mirostat by completely refactoring sampling!
* Try to fix zig build.
* Export function to fetch/create default sampler states
Code formatting cleanups and add some comments
Silence a warning about id not being used when logging is disabled
* Apply some renaming suggestions.
Fix comments that were out of sync with the pull.
* Use more consistant naming convention for sampling contexts
2023-10-11 22:35:46 +03:00
