From 64cd4b133945f875a1ae0014fdfd86bc0d5ce881 Mon Sep 17 00:00:00 2001 From: Joan Martinez Date: Mon, 22 Apr 2024 17:42:48 +0200 Subject: [PATCH] fix: fix linting and editor --- convert-hf-to-gguf.py | 1 + llama.cpp | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/convert-hf-to-gguf.py b/convert-hf-to-gguf.py index c1b6888bc..23e1606ed 100755 --- a/convert-hf-to-gguf.py +++ b/convert-hf-to-gguf.py @@ -2714,6 +2714,7 @@ class OlmoModel(Model): self.gguf_writer.add_tensor(new_name, data) + @Model.register("JinaBertModel") class JinaBertModel(BertModel): model_arch = gguf.MODEL_ARCH.JINA_BERT diff --git a/llama.cpp b/llama.cpp index a257e46e3..309f4eecc 100644 --- a/llama.cpp +++ b/llama.cpp @@ -5124,7 +5124,7 @@ static bool llm_load_tensors( auto & layer = model.layers[i]; // JinaBertLayer - layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); + layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd}); layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i), {n_embd}); layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa});