diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py index c7885f85e..9be6e17e2 100755 --- a/convert_hf_to_gguf.py +++ b/convert_hf_to_gguf.py @@ -3128,6 +3128,7 @@ class JinaBertV2Model(BertModel): return super().modify_tensors(data_torch, name, bid) + @Model.register("OpenELMForCausalLM") class OpenELMModel(Model): model_arch = gguf.MODEL_ARCH.OPENELM diff --git a/examples/server/tests/features/rerank.feature b/examples/server/tests/features/rerank.feature new file mode 100644 index 000000000..e6981673d --- /dev/null +++ b/examples/server/tests/features/rerank.feature @@ -0,0 +1,39 @@ +@llama.cpp +@rerank +Feature: llama.cpp server + + Background: Server startup + Given a server listening on localhost:8080 + And a model url https://huggingface.co/ggml-org/models/resolve/main/jina-reranker-v1-tiny-en/ggml-model-f16.gguf + And a model file jina-reranker-v1-tiny-en.gguf + And a model alias jina-reranker-v1-tiny-en + And 42 as server seed + And 2 slots + And 128 as batch size + And 128 as ubatch size + And 512 KV cache size + And embeddings extraction + Then the server is starting + Then the server is healthy + +# TODO: implement some tests +# https://github.com/ggerganov/llama.cpp/pull/9510 +# Scenario: Rerank +# Given a prompt: +# """ +# What is panda? +# """ +# And a prompt: +# """ +# Hi. +# """ +# And a prompt: +# """ +# It's a bear. +# """ +# And a prompt: +# """ +# The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China. +# """ +# When reranking request +# Then reranking results are returned