vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into compilade/bitnet-ternary

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-08-11 15:52:29 -04:00
commit d911cd1f13
138 changed files with 7065 additions and 1937 deletions
Download patch file Download diff file Expand all files Collapse all files

5
include/llama.h
View file

@ -347,7 +347,7 @@ extern "C" {
int32_t nthread; // number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
enum llama_ftype ftype; // quantize to this llama_ftype
enum ggml_type output_tensor_type; // output tensor type
enum ggml_type token_embedding_type; // itoken embeddings tensor type
enum ggml_type token_embedding_type; // token embeddings tensor type
bool allow_requantize; // allow quantizing non-f32/f16 tensors
bool quantize_output_tensor; // quantize output.weight
bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
@ -506,6 +506,9 @@ extern "C" {
// Returns true if the model contains an encoder that requires llama_encode() call
LLAMA_API bool llama_model_has_encoder(const struct llama_model * model);
// Returns true if the model contains a decoder that requires llama_decode() call
LLAMA_API bool llama_model_has_decoder(const struct llama_model * model);
// For encoder-decoder models, this function returns id of the token that must be provided
// to the decoder to start generating output sequence. For other models, it returns -1.
LLAMA_API llama_token llama_model_decoder_start_token(const struct llama_model * model);