From 956d652314e8b94dae0ceab7533c2ff0f6adbe0f Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Wed, 5 Jun 2024 23:22:58 +0200 Subject: [PATCH] models(gallery): add nyun (#2496) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 2017e792..df3644c3 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -951,6 +951,23 @@ - filename: Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf sha256: 694c55b5215d03e59626cd4292076eaf31610ef27ba04737166766baa75d889f uri: huggingface://MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3-32k-GGUF/Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf +- !!merge <<: *llama3 + url: "github:mudler/LocalAI/gallery/chatml.yaml@master" + name: "nyun-llama3-62b" + description: | + 12% Fewer Parameters: nyun-llama3-62B comprises approximately 12% fewer parameters than the popular Llama-3-70B. + Intact Performance: Despite having fewer parameters, our model performs at par if not better, and occasionally outperforms, the Llama-3-70B. + No Fine-Tuning Required: This model undergoes no fine-tuning, showcasing the raw potential of our optimization techniques. + urls: + - https://huggingface.co/nyunai/nyun-llama3-62B + - https://huggingface.co/bartowski/nyun-llama3-62B-GGUF + overrides: + parameters: + model: nyun-llama3-62B-Q4_K_M.gguf + files: + - filename: nyun-llama3-62B-Q4_K_M.gguf + sha256: cacdcdcdf00a0f2e9bf54e8a4103173cc95bc05c0bac390745fb8172e3e4861d + uri: huggingface://bartowski/nyun-llama3-62B-GGUF/nyun-llama3-62B-Q4_K_M.gguf - url: "github:mudler/LocalAI/gallery/chatml.yaml@master" name: "mahou-1.2-llama3-8b" license: llama3