EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

model : add Granite Hybrid types (#16635)

Browse Source 
add Granite 4 models mapping their embedding dimensions to the # of
parameters.

Information taken from https://huggingface.co/ibm-granite/granite-4.0-h-tiny

Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
This commit is contained in:
Giuseppe Scrivano
2025-10-19 23:54:31 +02:00
committed by GitHub
parent 4f73d0a951
commit 0398752dd4
2 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/llama-model.cpp
View File

@@ -114,6 +114,7 @@ const char * llm_type_name(llm_type type) {
case LLM_TYPE_17B_16E: return "17Bx16E (Scout)"; case LLM_TYPE_17B_16E: return "17Bx16E (Scout)";
case LLM_TYPE_17B_128E: return "17Bx128E (Maverick)"; case LLM_TYPE_17B_128E: return "17Bx128E (Maverick)";
case LLM_TYPE_A13B: return "A13B"; case LLM_TYPE_A13B: return "A13B";
case LLM_TYPE_7B_A1B: return "7B.A1B";
case LLM_TYPE_8B_A1B: return "8B.A1B"; case LLM_TYPE_8B_A1B: return "8B.A1B";
case LLM_TYPE_21B_A3B: return "21B.A3B"; case LLM_TYPE_21B_A3B: return "21B.A3B";
case LLM_TYPE_30B_A3B: return "30B.A3B"; case LLM_TYPE_30B_A3B: return "30B.A3B";
@@ -1843,8 +1844,10 @@ void llama_model::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
switch (hparams.n_layer) { switch (hparams.n_embd) {
// TODO: Add llm type label (not sure this is useful) case 1536: type = LLM_TYPE_7B_A1B; break;
case 2048: case 2560: type = LLM_TYPE_3B; break;
case 4096: type = LLM_TYPE_32B; break;
default: type = LLM_TYPE_UNKNOWN; default: type = LLM_TYPE_UNKNOWN;
} }

1
src/llama-model.h
View File

@@ -107,6 +107,7 @@ enum llm_type {
LLM_TYPE_17B_16E, // llama4 Scout LLM_TYPE_17B_16E, // llama4 Scout
LLM_TYPE_17B_128E, // llama4 Maverick LLM_TYPE_17B_128E, // llama4 Maverick
LLM_TYPE_A13B, LLM_TYPE_A13B,
LLM_TYPE_7B_A1B,
LLM_TYPE_8B_A1B, // lfm2moe LLM_TYPE_8B_A1B, // lfm2moe
LLM_TYPE_21B_A3B, // Ernie MoE small LLM_TYPE_21B_A3B, // Ernie MoE small
LLM_TYPE_30B_A3B, LLM_TYPE_30B_A3B,