Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-02 19:11:16 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/gguf-publish.yml
#	CODEOWNERS
#	examples/sycl/test.sh
#	pyproject.toml
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/README.md
This commit is contained in:
Concedo
2026-05-08 14:48:57 +08:00
parent 20e479a7ca 803627f121
commit eb30b29d69
43 changed files with 2427 additions and 576 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+2 -1
View File
@@ -415,7 +415,7 @@ static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params
case LLM_ARCH_STEP35:
return new llama_model_step35(params);
default:
GGML_ABORT("unimplemented model class");
throw std::runtime_error(std::string("unsupported model architecture: '") + llm_arch_name(arch) + "'");
}
}
@@ -1802,6 +1802,7 @@ void llama_model::print_info() const {
LLAMA_LOG_INFO("%s: f_max_alibi_bias = %.1e\n", __func__, hparams.f_max_alibi_bias);
LLAMA_LOG_INFO("%s: f_logit_scale = %.1e\n", __func__, hparams.f_logit_scale);
LLAMA_LOG_INFO("%s: f_attn_scale = %.1e\n", __func__, hparams.f_attention_scale);
LLAMA_LOG_INFO("%s: f_attn_value_scale = %.4f\n", __func__, hparams.f_attn_value_scale);
LLAMA_LOG_INFO("%s: n_ff = %s\n", __func__, print_f([&](uint32_t il) { return hparams.n_ff(il); }, hparams.n_layer).c_str());
LLAMA_LOG_INFO("%s: n_expert = %u\n", __func__, hparams.n_expert);
LLAMA_LOG_INFO("%s: n_expert_used = %u\n", __func__, hparams.n_expert_used);