thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

model : add LFM2-ColBert-350M (#18607)

Browse source 
* model : add LFM2-ColBert-350M

* llama_model_n_embd_out() - returns `hparams.n_embd_out` if set and fallbacks to `hparams.n_embd`
This commit is contained in:
Tarek Dakhran 2026-01-05 19:52:56 +01:00 • committed by GitHub
parent df17a4c94f
commit 73d284a250
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
16 changed files with 118 additions and 60 deletions
Download patch file Download diff file Expand all files Collapse all files

1
include/llama.h
View file

@ -535,6 +535,7 @@ extern "C" {
LLAMA_API int32_t llama_model_n_ctx_train(const struct llama_model * model);
LLAMA_API int32_t llama_model_n_embd (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_embd_inp (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_embd_out (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_layer (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_head (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_head_kv (const struct llama_model * model);