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

PR clean up

Browse source
This commit is contained in:
Michael Podvitskiy 2024-02-29 18:01:14 +01:00
parent afa9d0953b
commit e0504d536c
2 changed files with 1 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

16
llama.cpp
View file

@ -3072,6 +3072,7 @@ static void llm_load_hparams(
// get general kv
ml.get_key(LLM_KV_GENERAL_NAME, model.name, false);
// get hparams kv
ml.get_key(LLM_KV_VOCAB_SIZE, hparams.n_vocab, false) || ml.get_arr_n(LLM_KV_TOKENIZER_LIST, hparams.n_vocab);
ml.get_key(LLM_KV_CONTEXT_LENGTH, hparams.n_ctx_train);
ml.get_key(LLM_KV_EMBEDDING_LENGTH, hparams.n_embd);
@ -12520,14 +12521,6 @@ int32_t llama_n_embd(const struct llama_model * model) {
return model->hparams.n_embd;
}
int32_t llama_n_layers(const struct llama_model * model) {
return model->hparams.n_layer;
}
int32_t llama_n_heads(const struct llama_model * model) {
return model->hparams.n_head;
}
float llama_rope_freq_scale_train(const struct llama_model * model) {
return model->hparams.rope_freq_scale_train;
}
@ -13185,13 +13178,6 @@ void llama_set_n_threads(struct llama_context * ctx, uint32_t n_threads, uint32_
ctx->cparams.n_threads_batch = n_threads_batch;
}
void llama_get_n_threads(struct llama_context * ctx, uint32_t * n_threads, uint32_t * n_threads_batch) {
GGML_ASSERT(n_threads);
GGML_ASSERT(n_threads_batch);
*n_threads = ctx->cparams.n_threads;
*n_threads_batch = ctx->cparams.n_threads_batch;
}
void llama_set_abort_callback(struct llama_context * ctx, bool (*abort_callback)(void * data), void * abort_callback_data) {
ctx->abort_callback = abort_callback;
ctx->abort_callback_data = abort_callback_data;

4
llama.h
View file

@ -384,8 +384,6 @@ extern "C" {
LLAMA_API int32_t llama_n_vocab (const struct llama_model * model);
LLAMA_API int32_t llama_n_ctx_train(const struct llama_model * model);
LLAMA_API int32_t llama_n_embd (const struct llama_model * model);
LLAMA_API int32_t llama_n_layers (const struct llama_model * model);
LLAMA_API int32_t llama_n_heads (const struct llama_model * model);
// Get the model's RoPE frequency scaling factor
LLAMA_API float llama_rope_freq_scale_train(const struct llama_model * model);
@ -643,8 +641,6 @@ extern "C" {
// n_threads is the number of threads used for generation (single token)
// n_threads_batch is the number of threads used for prompt and batch processing (multiple tokens)
LLAMA_API void llama_set_n_threads(struct llama_context * ctx, uint32_t n_threads, uint32_t n_threads_batch);
// Get the number of threads used for decoding
LLAMA_API void llama_get_n_threads(struct llama_context * ctx, uint32_t * n_threads, uint32_t * n_threads_batch);
// Set abort callback
LLAMA_API void llama_set_abort_callback(struct llama_context * ctx, ggml_abort_callback abort_callback, void * abort_callback_data);