fix convert.py for codellama, add llama 34B to the list of recognized models (#2768)

diff --git a/convert.py b/convert.py
index 8d34d5f291ddb68dbc5561e86d1a2ce14af2248d..d3776a4dad925b8f06e20584187a8f1abd338a52 100755 (executable)
--- a/convert.py
+++ b/convert.py
@@ -191,7 +191,7 @@ class Params:
     def loadOriginalParamsJson(model: 'LazyModel', config_path: 'Path') -> 'Params':
         config = json.load(open(config_path))
 
-        n_vocab    = config["vocab_size"]
+        n_vocab    = config["vocab_size"] if "vocab_size" in config else -1
         n_embd     = config["dim"]
         n_layer    = config["n_layers"]
         n_mult     = config["multiple_of"]

diff --git a/llama.cpp b/llama.cpp
index f5526e302e145af13c601daff92817f28d8d156e..7ee6bcdae6acae01dc84a6fbd0e88273619cb002 100644 (file)
--- a/llama.cpp
+++ b/llama.cpp
@@ -827,6 +827,7 @@ enum e_model {
     MODEL_7B,
     MODEL_13B,
     MODEL_30B,
+    MODEL_34B,
     MODEL_40B,
     MODEL_65B,
     MODEL_70B,
@@ -1518,6 +1519,7 @@ 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_40B: return "40B";
         case MODEL_65B: return "65B";
         case MODEL_70B: return "70B";
@@ -1590,6 +1592,7 @@ static void llm_load_hparams(
                     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 = hparams.n_head == hparams.n_head_kv ? e_model::MODEL_65B : e_model::MODEL_70B; break;
                     default: model.type = e_model::MODEL_UNKNOWN;