model : support Rnj-1 (#17811)
* add support for rnj1 * refactor gemma3 to support rnj-1 * address review comments
This commit is contained in:
+17
-6
@@ -1264,18 +1264,25 @@ void llama_model::load_hparams(llama_model_loader & ml) {
|
||||
} break;
|
||||
case LLM_ARCH_GEMMA3:
|
||||
{
|
||||
hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;
|
||||
hparams.set_swa_pattern(6);
|
||||
const bool found_swa = ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa, false);
|
||||
if (found_swa && hparams.n_swa > 0) {
|
||||
hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;
|
||||
hparams.set_swa_pattern(6);
|
||||
|
||||
hparams.rope_freq_base_train_swa = 10000.0f;
|
||||
hparams.rope_freq_scale_train_swa = 1.0f;
|
||||
hparams.rope_freq_base_train_swa = 10000.0f;
|
||||
hparams.rope_freq_scale_train_swa = 1.0f;
|
||||
} else {
|
||||
hparams.swa_type = LLAMA_SWA_TYPE_NONE;
|
||||
}
|
||||
|
||||
ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa);
|
||||
hparams.f_final_logit_softcapping = 0.0f;
|
||||
ml.get_key(LLM_KV_FINAL_LOGIT_SOFTCAPPING, hparams.f_final_logit_softcapping, false);
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
|
||||
|
||||
switch (hparams.n_layer) {
|
||||
case 18: type = LLM_TYPE_270M; break;
|
||||
case 26: type = LLM_TYPE_1B; break;
|
||||
case 32: type = LLM_TYPE_8B; break; // Rnj-1
|
||||
case 34: type = LLM_TYPE_4B; break;
|
||||
case 48: type = LLM_TYPE_12B; break;
|
||||
case 62: type = LLM_TYPE_27B; break;
|
||||
@@ -7304,7 +7311,11 @@ ggml_cgraph * llama_model::build_graph(const llm_graph_params & params) const {
|
||||
} break;
|
||||
case LLM_ARCH_GEMMA3:
|
||||
{
|
||||
llm = std::make_unique<llm_build_gemma3_iswa>(*this, params);
|
||||
if (hparams.swa_type == LLAMA_SWA_TYPE_STANDARD) {
|
||||
llm = std::make_unique<llm_build_gemma3<true>>(*this, params);
|
||||
} else {
|
||||
llm = std::make_unique<llm_build_gemma3<false>>(*this, params);
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_GEMMA3N:
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user