models(gallery): add nyun (#2496)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-06-05 23:22:58 +02:00 committed by GitHub
parent 9ce2b4d71f
commit 956d652314
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -951,6 +951,23 @@
- filename: Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf - filename: Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf
sha256: 694c55b5215d03e59626cd4292076eaf31610ef27ba04737166766baa75d889f 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 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" - url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
name: "mahou-1.2-llama3-8b" name: "mahou-1.2-llama3-8b"
license: llama3 license: llama3