]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
Add missing inference support for GPTNeoXForCausalLM (Pythia and GPT-NeoX base models...
authorfairydreaming <redacted>
Thu, 23 May 2024 09:49:53 +0000 (11:49 +0200)
committerGitHub <redacted>
Thu, 23 May 2024 09:49:53 +0000 (11:49 +0200)
commit9b82476ee9e73065a759f8bcc4cf27ec7ab2ed8c
treed4881d12bc7e60750f90e642e3fabbdf4029fc53
parenta61a94e543e3c6877c087e80fca27a0313ce5fd5
Add missing inference support for GPTNeoXForCausalLM (Pythia and GPT-NeoX base models) (#7461)

* convert-hf : add conversion of bloom-style qkv tensor to gpt-style qkv (code borrowed from BloomModel)

* llama : add inference support for LLM_ARCH_GPTNEOX

* llama : add model types for every Pythia variant and GPT-NeoX

Co-authored-by: Stanisław Szymczyk <redacted>
convert-hf-to-gguf.py
llama.cpp