models(gallery): add eva-qwen2.5-14b-v0.2 (#4099)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-11-09 09:01:15 +01:00 committed by GitHub
parent e8431d62a2
commit 7f0093b2c9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -860,6 +860,25 @@
- filename: LLENN-v0.75-Qwen2.5-72b.i1-Q4_K_M.gguf - filename: LLENN-v0.75-Qwen2.5-72b.i1-Q4_K_M.gguf
sha256: 38990136bb48fc9422b0e477bed6d9c40c00c270806d3bd3f58e426badfa0d4d sha256: 38990136bb48fc9422b0e477bed6d9c40c00c270806d3bd3f58e426badfa0d4d
uri: huggingface://mradermacher/LLENN-v0.75-Qwen2.5-72b-i1-GGUF/LLENN-v0.75-Qwen2.5-72b.i1-Q4_K_M.gguf uri: huggingface://mradermacher/LLENN-v0.75-Qwen2.5-72b-i1-GGUF/LLENN-v0.75-Qwen2.5-72b.i1-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "eva-qwen2.5-14b-v0.2"
urls:
- https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
- https://huggingface.co/bartowski/EVA-Qwen2.5-14B-v0.2-GGUF
description: |
A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-14B on mixture of synthetic and natural data.
It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and "flavor" of the resulting model.
Version notes for 0.2: Now using the refined dataset from 32B 0.2. Major improvements in coherence, instruction following and long-context comprehension over 14B v0.1.
Prompt format is ChatML.
overrides:
parameters:
model: EVA-Qwen2.5-14B-v0.2-Q4_K_M.gguf
files:
- filename: EVA-Qwen2.5-14B-v0.2-Q4_K_M.gguf
sha256: 5d79bc8bf486c48c6430621a5bc5d3032227532dae436a27aa23aaf3e618e009
uri: huggingface://bartowski/EVA-Qwen2.5-14B-v0.2-GGUF/EVA-Qwen2.5-14B-v0.2-Q4_K_M.gguf
- &archfunct - &archfunct
license: apache-2.0 license: apache-2.0
tags: tags: