llama: rwkv6: Add quantization tensor exclusion

Signed-off-by: Molly Sophia <[email protected]>

src/llama.cpp

@@ -16547,6 +16547,9 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
         quantize &= name.find("ssm_x.weight")      == std::string::npos;
         quantize &= name.find("ssm_dt.weight")     == std::string::npos;
 
+        // do not quantize RWKV's time_mix_first tensors
+        quantize &= name.find("time_mix_first.weight") == std::string::npos;
+
         // do not quantize relative position bias (T5)
         quantize &= name.find("attn_rel_b.weight") == std::string::npos;