Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-12 05:17:21 +01:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
slaren 2023-08-24 17:44:11 +02:00 committed by GitHub
parent ef955fbd23
commit fea95c682d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
convert.py
View File

@ -191,7 +191,7 @@ class Params:
def loadOriginalParamsJson(model: 'LazyModel', config_path: 'Path') -> 'Params': def loadOriginalParamsJson(model: 'LazyModel', config_path: 'Path') -> 'Params':
config = json.load(open(config_path)) 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_embd = config["dim"]
n_layer = config["n_layers"] n_layer = config["n_layers"]
n_mult = config["multiple_of"] n_mult = config["multiple_of"]

3
llama.cpp
View File

@ -827,6 +827,7 @@ enum e_model {
MODEL_7B, MODEL_7B,
MODEL_13B, MODEL_13B,
MODEL_30B, MODEL_30B,
MODEL_34B,
MODEL_40B, MODEL_40B,
MODEL_65B, MODEL_65B,
MODEL_70B, MODEL_70B,
@ -1518,6 +1519,7 @@ 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_40B: return "40B"; case MODEL_40B: return "40B";
case MODEL_65B: return "65B"; case MODEL_65B: return "65B";
case MODEL_70B: return "70B"; case MODEL_70B: return "70B";
@ -1590,6 +1592,7 @@ static void llm_load_hparams(
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 = 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;