---
base_model: starble-dev/Hollow-Tail-V1-12B
language:
- en
license: other
pipeline_tag: text-generation
quantized_by: Reiterate3680
---
Really nice performing merge for me. Try the template from the merge creator or the following:
```
<[start_system]>
System<[END]>
<[start_user]>
User<[END]>
<[start_assistant]>
Model response<[END]>
```

L quants (or more), for fun/testing, probably prefer bartowski or mradermacher's quants if available

Original Model: https://huggingface.co/starble-dev/Hollow-Tail-V1-12B

Made with a modified version of https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script

Q2_K_L, Q4_K_L, Q5_K_L, Q6_K_L, are using Q_8 output tensors and token embeddings. imatrix is done using bartowski's imatrix dataset