Skip to content

GitLab

Unverified Commit dad63f08 authored by Michael Yang's avatar Michael Yang Committed by GitHub
Browse files

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

patch llama.cpp for 34B
parents de0bdd7f 7a378f8b
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 0 deletions
llm/llama.cpp
View file @ dad63f08
...@@ -105,6 +105,7 @@ enum e_model { ...@@ -105,6 +105,7 @@ enum e_model {
MODEL_7B, MODEL_7B,
MODEL_13B, MODEL_13B,
MODEL_30B, MODEL_30B,
MODEL_34B,
MODEL_65B, MODEL_65B,
MODEL_70B, MODEL_70B,
}; };
...@@ -1053,6 +1054,7 @@ static const char *llama_model_type_name(e_model type) { ...@@ -1053,6 +1054,7 @@ static const char *llama_model_type_name(e_model type) {
case MODEL_7B: return "7B"; case MODEL_7B: return "7B";
case MODEL_13B: return "13B"; case MODEL_13B: return "13B";
case MODEL_30B: return "30B"; case MODEL_30B: return "30B";
case MODEL_34B: return "34B";
case MODEL_65B: return "65B"; case MODEL_65B: return "65B";
case MODEL_70B: return "70B"; case MODEL_70B: return "70B";
default: LLAMA_ASSERT(false); default: LLAMA_ASSERT(false);
...@@ -1100,6 +1102,7 @@ static void llama_model_load_internal( ...@@ -1100,6 +1102,7 @@ static void llama_model_load_internal(
case 26: model.type = e_model::MODEL_3B; break; case 26: model.type = e_model::MODEL_3B; break;
case 32: model.type = e_model::MODEL_7B; break; case 32: model.type = e_model::MODEL_7B; break;
case 40: model.type = e_model::MODEL_13B; 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 60: model.type = e_model::MODEL_30B; break;
case 80: model.type = e_model::MODEL_65B; break; case 80: model.type = e_model::MODEL_65B; break;
default: default:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment