* Support multiple chat templates - step 1
As a first step, allow user to to select template from metadata with chat_format parameter in the form of `chat_template.name`.
* register chat templates to self.chat_formats instead of globally
* Don't expose internal chat handlers yet
---------
Co-authored-by: Andrei <abetlen@gmail.com>
* Proper fill-in-middle support
Use prefix/middle/suffix tokens when metadata is present in GGUF, like f.ex. in [this](https://huggingface.co/CISCai/CodeQwen1.5-7B-Chat-SOTA-GGUF) one.
* fall back to internal prefix/middle/suffix id
In some cases llama.cpp will make a guess at fim tokens, use them if there's no metadata.
* typo--
* don't insert special tokens that are not there in suffix
Note: add_bos is misnamed, it's actually add_special and can cause several special tokens to be added to the token list (the special parameter is actually parse_special).
* don't add/parse any special tokens when using fim
I've left original behavior when no fim tokens are found, but this should perhaps be re-evaluated.
* don't append suffix to prompt_tokens unless fim tokens are detected
* make sure we only do this for fim
---------
Co-authored-by: Andrei <abetlen@gmail.com>
* State load/save changes
- Only store up to `n_tokens` logits instead of full `(n_ctx, n_vocab)`
sized array.
- Difference between ~350MB and ~1500MB for example prompt with ~300
tokens (makes sense lol)
- Auto-formatting changes
* Back out formatting changes
* Add logprobs return in ChatCompletionResponse
* Fix duplicate field
* Set default to false
* Simplify check
* Add server example
---------
Co-authored-by: Andrei Betlen <abetlen@gmail.com>
* switch to llama_get_embeddings_seq
* Remove duplicate definition of llama_get_embeddings_seq
Co-authored-by: Andrei <abetlen@gmail.com>
---------
Co-authored-by: Andrei <abetlen@gmail.com>
* fix sample_idx off-by-one error
* self._scores is indexed differently, only modify the index within self._input_ids
---------
Co-authored-by: Andrew Lapp <andrew@rew.la>
Co-authored-by: Andrei <abetlen@gmail.com>
* Add draft model param to llama class, implement basic prompt lookup decoding draft model
* Use samplingcontext for sampling
* Use 1d array
* Use draft model for sampling
* Fix dumb mistake
* Allow for later extensions to the LlamaDraftModel api
* Cleanup
* Adaptive candidate prediction
* Update implementation to match hf transformers
* Tuning
* Fix bug where last token was not used for ngram prediction
* Remove heuristic for num_pred_tokens (no benefit)
* fix: n_candidates bug.
* Add draft_model_num_pred_tokens server setting
* Cleanup
* Update README
