happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

model : make minicpm embedding_scale, residual_scale and logit_scale optional with legacy defaults (#16273) 

* minicpm: make GGUF scaling keys optional with legacy defaults

Older MiniCPM GGUFs do not include the scaling metadata keys (minicpm.embedding_scale, minicpm.residual_scale, minicpm.logit_scale). The loader currently treats these as required, so quantization fails with:

    key not found in model: minicpm.embedding_scale

This change restores backward compatibility by treating these keys as optional in the loader and using the older MiniCPM scaling values:

    embedding_scale = 12.0f
    residual_scale  = 1.4f / sqrt(n_layer)
    logit_scale     = 256.0f / n_embd

When the GGUF provides the keys, their values override the defaults; otherwise the legacy defaults are used. Newer GGUFs that already include these keys are unaffected.

Fixes: #16192
Signed-off-by: Vinkal Chudgar <vinkal.chudgar@gmail.com>

* Update src/llama-model.cpp

Committed as suggested. Thanks!

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Signed-off-by: Vinkal Chudgar <vinkal.chudgar@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Vinkal 2025-09-27 02:58:29 +05:30 committed by GitHub
parent 624207e676
commit 72b24d96c6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/llama-model.cpp
View File

@ -675,10 +675,17 @@ void llama_model::load_hparams(llama_model_loader & ml) {
} break;
case LLM_ARCH_MINICPM:
{
// Backward-compatible defaults for older MiniCPM GGUFs
hparams.f_embedding_scale = 12.0f;
hparams.f_residual_scale = 1.4f / sqrtf(float(hparams.n_layer));
hparams.f_logit_scale = hparams.n_embd ? (256.0f / float(hparams.n_embd)) : 1.0f;
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
ml.get_key(LLM_KV_EMBEDDING_SCALE, hparams.f_embedding_scale);
ml.get_key(LLM_KV_RESIDUAL_SCALE, hparams.f_residual_scale);
ml.get_key(LLM_KV_LOGIT_SCALE, hparams.f_logit_scale);
// Optional KV reads, override defaults if present in newer GGUF exports
ml.get_key(LLM_KV_EMBEDDING_SCALE, hparams.f_embedding_scale, /*required=*/false);
ml.get_key(LLM_KV_RESIDUAL_SCALE, hparams.f_residual_scale, /*required=*/false);
ml.get_key(LLM_KV_LOGIT_SCALE, hparams.f_logit_scale, /*required=*/false);
// MiniCPM uses rope by default, unlike Granite which uses it as a switch
hparams.rope_finetuned = true;