|
|
|
--- |
|
|
|
license: apache-2.0 |
|
datasets: |
|
- arcee-ai/EvolKit-20k |
|
base_model: |
|
- Qwen/Qwen2.5-1.5B |
|
|
|
--- |
|
|
|
[](https://hf.co/QuantFactory) |
|
|
|
|
|
# QuantFactory/EVA-D-Qwen2.5-1.5B-v0.0-GGUF |
|
This is quantized version of [EVA-UNIT-01/EVA-D-Qwen2.5-1.5B-v0.0](https://huggingface.co/EVA-UNIT-01/EVA-D-Qwen2.5-1.5B-v0.0) created using llama.cpp |
|
|
|
# Original Model Card |
|
|
|
# EVA-D Qwen2.5-1.5B v0.0 |
|
|
|
<p> |
|
An experimental online logit distillation of EVA-Qwen2.5-14B-v0.1 into Qwen2.5-1.5B. Should work as a RP/storywriting specialist, but don't expect superb performance from it, due to it's small size. All in all, it was a fun experiment to do.<br> |
|
</p> |
|
|
|
<p>Note: using quantized KV cache with Qwen2.5 <b>is not recommended</b> and can lead to degraded output quality. On the other hand, Qwen's KV cache is already light enough, so using f16 for it shouldn't be problematic.</p> |
|
|
|
<p> |
|
<p>Prompt format is ChatML.</p><br> |
|
<h3>Recommended sampler values:</h3> |
|
<ul> |
|
<li>Temperature: 1</li> |
|
<li>Min-P: 0.02</li> |
|
</ul> |
|
|
|
<h3>Recommended SillyTavern presets (via CalamitousFelicitousness):</h3> |
|
|
|
- [Context](https://huggingface.co/EVA-UNIT-01/EVA-Yi-1.5-9B-32K-V1/blob/main/%5BChatML%5D%20Roleplay-v1.9%20Context.json) |
|
- [Instruct and System Prompt](https://huggingface.co/EVA-UNIT-01/EVA-Yi-1.5-9B-32K-V1/blob/main/%5BChatML%5D%20Roleplay-v1.9%20Instruct.json) |
|
</p> |
|
|
|
<p> |
|
<br> |
|
<h3> |
|
Distillation data: |
|
</h3> |
|
<ul> |
|
<li>Arcee.AI's <a href=https://huggingface.co/datasets/arcee-ai/EvolKit-20k>EvolKit-20k</a> dataset, which is specifically made for knowledge distillation purposes.</li> |
|
</ul> |
|
<h3> |
|
Training time and hardware: |
|
</h3> |
|
<ul><li>1.8 hours on 8xA100 SXM, provided by Garg</li></ul><br> |
|
</p> |
|
<p>Model was trained by Kearm and Auri.</p> |
|
<h4>Special thanks:</h4><ul> |
|
<li><b>to Garg for generously providing 8xA100 SXM node for this experiment!</b></li> |
|
<li>to Arcee.AI for creating DistillKit and EvolKit-20k dataset, which were used to create this model.</li> |
|
<li>and to Allura-org for support and feedback on EVA models.</li></ul> |
|
|
