diff options
| author | Pedro Cuenca <pedro@huggingface.co> | 2024-04-21 13:50:41 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-21 14:50:41 +0300 |
| commit | b97bc3966e852adb626c90be64fd48282800f504 (patch) | |
| tree | 178656d15821205889fa03ec603c7327facbb265 /examples/batched.swift/Sources/main.swift | |
| parent | b8109bc0139f15a5b321909f47510b89dca47ffc (diff) | |
llama : support Llama 3 HF conversion (#6745)
* Support Llama 3 conversion
The tokenizer is BPE.
* style
* Accept suggestion
Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com>
* llama : add llama_token_is_eog()
ggml-ci
* llama : auto-detect more EOT tokens when missing in KV data
* convert : replacing EOS token is a hack
* llama : fix codegemma EOT token + add TODOs
* llama : fix model type string for 8B model
---------
Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'examples/batched.swift/Sources/main.swift')
| -rw-r--r-- | examples/batched.swift/Sources/main.swift | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/examples/batched.swift/Sources/main.swift b/examples/batched.swift/Sources/main.swift index d75c503d..5764acb6 100644 --- a/examples/batched.swift/Sources/main.swift +++ b/examples/batched.swift/Sources/main.swift @@ -153,7 +153,7 @@ while n_cur <= n_len { // const llama_token new_token_id = llama_sample_token_greedy(ctx, &candidates_p); // is it an end of stream? -> mark the stream as finished - if new_token_id == llama_token_eos(model) || n_cur == n_len { + if llama_token_is_eog(model, new_token_id) || n_cur == n_len { i_batch[i] = -1 // print("") if n_parallel > 1 { |