From f2942cc0e196a50cf76c8bffecb0fdd75d18128c Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Tue, 20 May 2025 10:28:27 +0200 Subject: [PATCH] chore(model gallery): add thedrummer_valkyrie-49b-v1 (#5410) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 2a8bb2c3..8443a8b0 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -2568,6 +2568,39 @@ - filename: L3.3-Genetic-Lemonade-Sunset-70B.Q4_K_M.gguf sha256: 743c11180c0c9168c0fe31a97f9d2efe0dd749c2797d749821fcb1d6932c19f7 uri: huggingface://mradermacher/L3.3-Genetic-Lemonade-Sunset-70B-GGUF/L3.3-Genetic-Lemonade-Sunset-70B.Q4_K_M.gguf +- !!merge <<: *llama33 + name: "thedrummer_valkyrie-49b-v1" + icon: https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/8I-AvB0bFSoEcxlLU7dtY.png + urls: + - https://huggingface.co/TheDrummer/Valkyrie-49B-v1 + - https://huggingface.co/bartowski/TheDrummer_Valkyrie-49B-v1-GGUF + description: | + it swears unprompted 10/10 model + + ... characters work well, groups work well, scenarios also work really well so great model overall + + This is pretty exciting though. GLM-4 already had me on the verge of deleting all of my other 32b and lower models. I got to test this more but I think this model at Q3m is the death blow lol + + Smart Nemotron 49b learned how to roleplay + + Even without thinking it rock solid at 4qm. + + Without thinking is like 40-70b level. With thinking is 100+b level + + This model would have been AGI if it were named properly with a name like "Bob". Alas, it was not. + + I think this model is nice. It follows prompts very well. I didn't really note any major issues or repetition + + Yeah this is good. I think its clearly smart enough, close to the other L3.3 70b models. It follows directions and formatting very well. I asked it to create the intro message, my first response was formatted differently, and it immediately followed my format on the second message. I also have max tokens at 2k cause I like the model to finish it's thought. But I started trimming the models responses when I felt the last bit was unnecessary and it started replying closer to that length. It's pretty much uncensored. + + Nemotron is my favorite model, and I think you fixed it!! + overrides: + parameters: + model: TheDrummer_Valkyrie-49B-v1-Q4_K_M.gguf + files: + - filename: TheDrummer_Valkyrie-49B-v1-Q4_K_M.gguf + sha256: f50be1eef41e0da2cb59e4b238f4f178ee1000833270b337f97f91572c31b752 + uri: huggingface://bartowski/TheDrummer_Valkyrie-49B-v1-GGUF/TheDrummer_Valkyrie-49B-v1-Q4_K_M.gguf - &rwkv url: "github:mudler/LocalAI/gallery/rwkv.yaml@master" name: "rwkv-6-world-7b"