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

BUG: generates gibberish/repeating tokens after a while

Browse source
This commit is contained in:
Leon Ericsson 2023-12-15 14:14:17 +01:00
parent 0ec5fdb5ce
commit 1665ad8bf1
2 changed files with 33 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

6
common/common.h
View file

@ -75,10 +75,10 @@ struct gpt_params {
// // sampling parameters
struct llama_sampling_params sparams;
std::string model = "models/7B/ggml-model-q4_0.gguf"; // model path
std::string model = "models/7B/ggml-model-f16.gguf"; // model path
std::string model_draft = ""; // draft model for speculative decoding
std::string model_alias = "unknown"; // model alias
std::string prompt = "Hello my name is";
std::string prompt = "";
std::string prompt_file = ""; // store the external prompt file name
std::string path_prompt_cache = ""; // path to file for saving/loading prompt eval state
std::string input_prefix = ""; // string to prefix user inputs with
@ -228,4 +228,4 @@ void dump_non_result_info_yaml(
void dump_kv_cache_view(const llama_kv_cache_view & view, int row_size = 80);
// Dump the KV cache view showing individual sequences in each cell (long output).
void dump_kv_cache_view_seqs(const llama_kv_cache_view & view, int row_size = 40);
void dump_kv_cache_view_seqs(const llama_kv_cache_view & view, int row_size = 40);