From 32540ac6196c74ad73157b42fc12a1ad50986a77 Mon Sep 17 00:00:00 2001 From: ubergarm Date: Fri, 17 Oct 2025 00:52:31 -0400 Subject: [PATCH] Ling-1T convert fixup (#837) * Conditionally write moe_shared_expert_intermediate_size Ling-1T config.json does *not* have `moe_shared_expert_intermediate_size`. Ling-flash-2.0a *does* have it. This small patch just makes the gguf_writer conditionally detect as needed. * Fix Ling-1T missing moe_shared_expert_intermediate_size Thanks CISC for the proper patch to include the needed values! --- convert_hf_to_gguf.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py index 6b21c05f..c4aabbff 100644 --- a/convert_hf_to_gguf.py +++ b/convert_hf_to_gguf.py @@ -4494,7 +4494,7 @@ class BailingMoeV2Model(Model): self.gguf_writer.add_leading_dense_block_count(hparams["first_k_dense_replace"]) self.gguf_writer.add_vocab_size(hparams["vocab_size"]) self.gguf_writer.add_expert_feed_forward_length(hparams["moe_intermediate_size"]) - self.gguf_writer.add_expert_shared_feed_forward_length(hparams["moe_shared_expert_intermediate_size"]) + self.gguf_writer.add_expert_shared_feed_forward_length(hparams.get("moe_shared_expert_intermediate_size", hparams["moe_intermediate_size"] * hparams["num_shared_experts"])) self.gguf_writer.add_expert_weights_scale(hparams["routed_scaling_factor"]) self.gguf_writer.add_expert_count(hparams["num_experts"]) self.gguf_writer.add_expert_shared_count(hparams["num_shared_experts"])