summaryrefslogtreecommitdiff
path: root/llama.h
diff options
context:
space:
mode:
authorGeorgi Gerganov <ggerganov@gmail.com>2023-08-23 23:08:04 +0300
committerGitHub <noreply@github.com>2023-08-23 23:08:04 +0300
commitcf658adc832badaaa2ca119fe86070e5a830f8f6 (patch)
treee314db2fb18676067ddbc5cde0cf7f73c417af29 /llama.h
parenta192860cfec89a38d59a943623bf595b1fe4495b (diff)
llm : add Falcon support (#2717)
* llama : refactor GGUF constants into static maps * llama : check if model architecture is known * llama : refactor llama_model_load_internal() * gguf : add KV constant maps * llm : read arch-specific KVs * convert : add dummy scores + types * falcon : load tensor data (CPU only) * llama : fix loading progress bar * llama : add arch member to llama_model * falcon : CPU inference working * falcon : support non-40B models * falcon : minor * llama : minor updates ggml-ci * convert-falcon-hf-to-gguf.py : fix special token mapping * llama.cpp : llama default UNK token = id 0 * llama.cpp : fix bpe tokenizer * llama.cpp : fix the fix of bpe tokenizer * ggml : pass eps to ggml_norm * metal : implement RoPE (mode = 2) + avoid ggml_repeat * ggml : ggml_repeat always creates new tensor * falcon : copy-paste self-attention from LLaMA * metal : print extra compute pipeline info * falcon : minor changes (still chasing the Metal problem) * llama.cpp : fix linefeed token * metal : fix GELU kernel numerical stability by using precise::tanh * metal : temporary workaround for the concurrency optimization bug * falcon : add CUDA offloading (#2739) * llama : better model naming and size reporting * llama : prep new tokenizer support * llama : advanced BPE tokenizer based on ggllm.cpp imlpementation * llama : remove oboslete comment ggml-ci * common : remove obsolete BPE API + disable test-tokenizer-1 * llama : revert BPE special-case in llama_byte_to_token() * cuda : add TODOs for RoPE NeoX implementation * llama : default special tokens based on vocab type * perplexity : add log for start of tokenization --------- Co-authored-by: klosax <131523366+klosax@users.noreply.github.com> Co-authored-by: slaren <slarengh@gmail.com>
Diffstat (limited to 'llama.h')
-rw-r--r--llama.h15
1 files changed, 2 insertions, 13 deletions
diff --git a/llama.h b/llama.h
index 7ce478d5..4e7638c0 100644
--- a/llama.h
+++ b/llama.h
@@ -247,6 +247,8 @@ extern "C" {
LLAMA_API int llama_n_ctx (const struct llama_context * ctx);
LLAMA_API int llama_n_embd (const struct llama_context * ctx);
+ LLAMA_API enum llama_vocab_type llama_vocab_type(const struct llama_context * ctx);
+
LLAMA_API int llama_model_n_vocab(const struct llama_model * model);
LLAMA_API int llama_model_n_ctx (const struct llama_model * model);
LLAMA_API int llama_model_n_embd (const struct llama_model * model);
@@ -368,13 +370,6 @@ extern "C" {
int n_max_tokens,
bool add_bos);
- LLAMA_API int llama_tokenize_bpe(
- struct llama_context * ctx,
- const char * text,
- llama_token * tokens,
- int n_max_tokens,
- bool add_bos);
-
LLAMA_API int llama_tokenize_with_model(
const struct llama_model * model,
const char * text,
@@ -390,12 +385,6 @@ extern "C" {
char * buf,
int length);
- LLAMA_API int llama_token_to_str_bpe(
- const struct llama_context * ctx,
- llama_token token,
- char * buf,
- int length);
-
LLAMA_API int llama_token_to_str_with_model(
const struct llama_model * model,
llama_token token,