diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 0498c11734..fd2b3044c0 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -2471,6 +2471,7 @@ class FastLlamaModel: disable_log_stats = disable_log_stats, use_bitsandbytes = load_in_4bit, unsloth_vllm_standby = unsloth_vllm_standby, + revision = revision, fp8_mode = fp8_mode, ) for allowed_arg in allowed_args: diff --git a/unsloth/models/loader.py b/unsloth/models/loader.py index bd15ed5281..3155cd0d09 100644 --- a/unsloth/models/loader.py +++ b/unsloth/models/loader.py @@ -553,6 +553,7 @@ class FastLanguageModel(FastLlamaModel): model_config = AutoConfig.from_pretrained( model_name, token = token, + revision = revision, trust_remote_code = trust_remote_code, ) @@ -1304,6 +1305,7 @@ class FastModel(FastBaseModel): model_config = AutoConfig.from_pretrained( model_name, token = token, + revision = revision, trust_remote_code = trust_remote_code, )