Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 13:58:46 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama : add model types for mixtral (#6589)

Browse Source
This commit is contained in:
slaren 2024-04-10 17:24:14 +02:00 committed by GitHub
parent 65c64dc36f
commit 4f407a0a35
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 21 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
llama.cpp
View File

@ -1705,6 +1705,8 @@ enum e_model {
MODEL_MEDIUM, MODEL_MEDIUM,
MODEL_LARGE, MODEL_LARGE,
MODEL_XL, MODEL_XL,
MODEL_8x7B,
MODEL_8x22B,
}; };
static const size_t kiB = 1024; static const size_t kiB = 1024;
@ -3558,6 +3560,8 @@ static const char * llama_model_type_name(e_model type) {
case MODEL_MEDIUM: return "0.4B"; case MODEL_MEDIUM: return "0.4B";
case MODEL_LARGE: return "0.8B"; case MODEL_LARGE: return "0.8B";
case MODEL_XL: return "1.5B"; case MODEL_XL: return "1.5B";
case MODEL_8x7B: return "8x7B";
case MODEL_8x22B: return "8x22B";
default: return "?B"; default: return "?B";
} }
} }
@ -3672,6 +3676,13 @@ static void llm_load_hparams(
{ {
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);
if (hparams.n_expert == 8) {
switch (hparams.n_layer) {
case 32: model.type = e_model::MODEL_8x7B; break;
case 56: model.type = e_model::MODEL_8x22B; break;
default: model.type = e_model::MODEL_UNKNOWN;
}
} else {
switch (hparams.n_layer) { switch (hparams.n_layer) {
case 22: model.type = e_model::MODEL_1B; break; case 22: model.type = e_model::MODEL_1B; break;
case 26: model.type = e_model::MODEL_3B; break; case 26: model.type = e_model::MODEL_3B; break;
@ -3682,6 +3693,7 @@ static void llm_load_hparams(
case 80: model.type = hparams.n_head == hparams.n_head_kv ? e_model::MODEL_65B : e_model::MODEL_70B; break; case 80: model.type = hparams.n_head == hparams.n_head_kv ? e_model::MODEL_65B : e_model::MODEL_70B; break;
default: model.type = e_model::MODEL_UNKNOWN; default: model.type = e_model::MODEL_UNKNOWN;
} }
}
} break; } break;
case LLM_ARCH_MINICPM: case LLM_ARCH_MINICPM:
{ {