common : by default, move the penalties at the end of the sampling chain
ggml-ci
This commit is contained in:
parent
9847a375f3
commit
97261aa216
2 changed files with 12 additions and 9 deletions
|
@ -146,6 +146,7 @@ struct common_params_sampling {
|
||||||
COMMON_SAMPLER_TYPE_MIN_P,
|
COMMON_SAMPLER_TYPE_MIN_P,
|
||||||
COMMON_SAMPLER_TYPE_XTC,
|
COMMON_SAMPLER_TYPE_XTC,
|
||||||
COMMON_SAMPLER_TYPE_TEMPERATURE,
|
COMMON_SAMPLER_TYPE_TEMPERATURE,
|
||||||
|
COMMON_SAMPLER_TYPE_PENALTIES,
|
||||||
};
|
};
|
||||||
|
|
||||||
std::string grammar; // optional BNF-like grammar to constrain sampling
|
std::string grammar; // optional BNF-like grammar to constrain sampling
|
||||||
|
@ -194,9 +195,11 @@ struct common_params {
|
||||||
|
|
||||||
// offload params
|
// offload params
|
||||||
std::vector<ggml_backend_dev_t> devices; // devices to use for offloading
|
std::vector<ggml_backend_dev_t> devices; // devices to use for offloading
|
||||||
|
|
||||||
int32_t n_gpu_layers = -1; // number of layers to store in VRAM (-1 - use default)
|
int32_t n_gpu_layers = -1; // number of layers to store in VRAM (-1 - use default)
|
||||||
int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors
|
int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors
|
||||||
float tensor_split[128] = {0}; // how split tensors should be distributed across GPUs
|
float tensor_split[128] = {0}; // how split tensors should be distributed across GPUs
|
||||||
|
|
||||||
enum llama_split_mode split_mode = LLAMA_SPLIT_MODE_LAYER; // how to split the model across GPUs
|
enum llama_split_mode split_mode = LLAMA_SPLIT_MODE_LAYER; // how to split the model across GPUs
|
||||||
|
|
||||||
struct cpu_params cpuparams;
|
struct cpu_params cpuparams;
|
||||||
|
|
|
@ -166,9 +166,9 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, co
|
||||||
switch (cnstr) {
|
switch (cnstr) {
|
||||||
case COMMON_SAMPLER_TYPE_DRY:
|
case COMMON_SAMPLER_TYPE_DRY:
|
||||||
{
|
{
|
||||||
std::vector<const char*> c_breakers;
|
std::vector<const char *> c_breakers;
|
||||||
c_breakers.reserve(params.dry_sequence_breakers.size());
|
c_breakers.reserve(params.dry_sequence_breakers.size());
|
||||||
for (const auto& str : params.dry_sequence_breakers) {
|
for (const auto & str : params.dry_sequence_breakers) {
|
||||||
c_breakers.push_back(str.c_str());
|
c_breakers.push_back(str.c_str());
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue