Upload README.md

README.md

@@ -0,0 +1,60 @@
+---
+base_model:
+- Qwen2.5-32B-Instruct
+- EVA-UNIT-01/EVA-Qwen2.5-32B-v0.0
+license: apache-2.0
+license_name: qwen
+license_link: https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/LICENSE
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+- merge
+- roleplay
+- not-for-all-audiences
+library_name: transformers
+---
+
+# EVA-Instruct-32B
+
+della_linear merge done at a 40/60 split using EVA-Qwen2.5-32B-v0.0 and Qwen2.5-32B-Instruct. Seems pretty good on creative ventures so far.
+
+Big thanks to the Qwen and EVA-UNIT-01 teams for the models used!
+
+EXL2 quant:
+
+https://huggingface.co/ParasiticRogue/EVA-Instruct-32B-exl2-4.0
+
+## Settings
+
+Temperature @ 0.7
+
+Min-P @ 0.02
+
+Smoothing Factor @ 0.3
+
+DRY Multiplier (plus standard DRY settings) @ 0.8
+
+Skip Special Tokens @ On
+
+Everything else @ Off
+
+### Prompt Format: ChatML
+
+```
+<|im_start|>system
+System prompt<|im_end|>
+<|im_start|>user
+User prompt<|im_end|>
+<|im_start|>assistant
+Bot response
+```
+
+### Models Merged
+
+The following models were included in the merge:
+
+https://huggingface.co/Qwen2.5-32B-Instruct
+
+https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.0