vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix: fix linting and editor

Browse source
This commit is contained in:
Joan Martinez 2024-04-22 17:42:48 +02:00
parent c1c0f4d883
commit 64cd4b1339
2 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
convert-hf-to-gguf.py
View file

@ -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

2
llama.cpp
View file

@ -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});