baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge pull request #411 from jmorganca/mxyng/34b

Browse source 
patch llama.cpp for 34B
This commit is contained in:
Michael Yang 2023-08-25 11:59:05 -07:00 committed by GitHub
commit dad63f0821
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
llm/llama.cpp
View file

@ -105,6 +105,7 @@ enum e_model {
MODEL_7B,
MODEL_13B,
MODEL_30B,
MODEL_34B,
MODEL_65B,
MODEL_70B,
};
@ -1053,6 +1054,7 @@ static const char *llama_model_type_name(e_model type) {
case MODEL_7B: return "7B";
case MODEL_13B: return "13B";
case MODEL_30B: return "30B";
case MODEL_34B: return "34B";
case MODEL_65B: return "65B";
case MODEL_70B: return "70B";
default: LLAMA_ASSERT(false);
@ -1100,6 +1102,7 @@ static void llama_model_load_internal(
case 26: model.type = e_model::MODEL_3B; break;
case 32: model.type = e_model::MODEL_7B; break;
case 40: model.type = e_model::MODEL_13B; break;
case 48: model.type = e_model::MODEL_34B; break;
case 60: model.type = e_model::MODEL_30B; break;
case 80: model.type = e_model::MODEL_65B; break;
default: