public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-18 04:35:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2026-06-26 16:03:57 +03:00
parent 0279b5386a
commit 0ae02cdb2c
17 changed files with 101 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/llama-quant.cpp
+3 -3
View File
@@ -847,7 +847,7 @@ static void init_quantize_state_counters(quantize_state_impl & qs, std::vector<t
qs.has_tied_embeddings = false;
}
}
qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer();
qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer_all;
}
//
@@ -932,8 +932,8 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
// copy the KV pairs from the input file
gguf_set_kv (ctx_out.get(), ml.metadata);
gguf_set_val_u32(ctx_out.get(), "general.quantization_version", GGML_QNT_VERSION); // TODO: use LLM_KV
gguf_set_val_u32(ctx_out.get(), "general.file_type", ftype); // TODO: use LLM_KV
gguf_set_val_u32(ctx_out.get(), ml.llm_kv(LLM_KV_GENERAL_QUANTIZATION_VERSION).c_str(), GGML_QNT_VERSION);
gguf_set_val_u32(ctx_out.get(), ml.llm_kv(LLM_KV_GENERAL_FILE_TYPE).c_str(), ftype);
// Remove split metadata
gguf_remove_key(ctx_out.get(), ml.llm_kv(LLM_KV_SPLIT_NO).c_str());