Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 14:20:31 +01:00
Code Issues Packages Projects Releases Wiki Activity

Add Qwen2MoE 57B-A14B model identifier (#8158)

Browse Source 
* Add Qwen2MoE 57B-A14B

* Add Qwen2MoE 57B-A14B
This commit is contained in:
Sigbjørn Skjæret 2024-06-27 16:27:41 +02:00 committed by GitHub
parent 85a267daaa
commit 6030c61281
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama.cpp
View File

@ -2038,6 +2038,7 @@ enum e_model {
MODEL_8x22B,
MODEL_16x12B,
MODEL_10B_128x3_66B,
MODEL_57B_A14B,
};
static const size_t kiB = 1024;
@ -4267,6 +4268,7 @@ static const char * llama_model_type_name(e_model type) {
case MODEL_8x22B: return "8x22B";
case MODEL_16x12B: return "16x12B";
case MODEL_10B_128x3_66B: return "10B+128x3.66B";
case MODEL_57B_A14B: return "57B.A14B";
default: return "?B";
}
}
@ -4588,6 +4590,7 @@ static void llm_load_hparams(
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
switch (hparams.n_layer) {
case 24: model.type = e_model::MODEL_A2_7B; break;
case 28: model.type = e_model::MODEL_57B_A14B; break;
default: model.type = e_model::MODEL_UNKNOWN;
}
} break;