chore(model gallery): add qwen2.5-32b-rp-ink

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-12-31 11:15:23 +01:00
parent 639526d207
commit f0fb53dc35

View file

@ -2490,6 +2490,22 @@
- filename: Teleut-7b-RP-Q4_K_M.gguf
sha256: 74d9a0974c48f16677da8891ac76ed89ed04f246275b9ca8316d25e1e86ce89f
uri: huggingface://bartowski/Teleut-7b-RP-GGUF/Teleut-7b-RP-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "qwen2.5-32b-rp-ink"
icon: https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/1_Zt_OvEW183lmrgidQw8.png
urls:
- https://huggingface.co/allura-org/Qwen2.5-32b-RP-Ink
- https://huggingface.co/bartowski/Qwen2.5-32b-RP-Ink-GGUF
description: |
A roleplay-focused LoRA finetune of Qwen 2.5 32b Instruct. Methodology and hyperparams inspired by SorcererLM and Slush.
Yet another model in the Ink series, following in the footsteps of the Nemo one
overrides:
parameters:
model: Qwen2.5-32b-RP-Ink-Q4_K_M.gguf
files:
- filename: Qwen2.5-32b-RP-Ink-Q4_K_M.gguf
sha256: 7a0693d50aa40ba4fd43b4988851e67443e758ae34881f448e2812e5fcc25468
uri: huggingface://bartowski/Qwen2.5-32b-RP-Ink-GGUF/Qwen2.5-32b-RP-Ink-Q4_K_M.gguf
- &smollm
## SmolLM
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"