This commit is contained in:
Daniel Han 2025-05-02 03:09:52 -07:00
commit 2a231c7ba4

View file

@ -70,6 +70,7 @@ LLAMA_WEIGHTS = (
LLAMA_LAYERNORMS = (
"input_layernorm", "post_attention_layernorm",
"pre_feedforward_layernorm", "post_feedforward_layernorm",
"self_attn.q_norm", "self_attn.k_norm",
)
# https://github.com/ggerganov/llama.cpp/blob/master/examples/quantize/quantize.cpp#L19