metadata
base_model: NyxKrage/Chronomaid-Storytelling-13b
inference: false
license: llama2
model_creator: Carsten Kragelund
model_name: Chronomaid Storytelling 13B
model_type: llama
prompt_template: >
Below is an instruction that describes a task. Write a response that
appropriately completes the request.
### Instruction:
{prompt}
### Response:
quantized_by: LogicismTV
Chronomaid Storytelling 13B - ExLlama V2
Original model: Chronomaid Storytelling 13B
Description
This is an EXL2 quantization of the NyxKrage's Chronomaid Storytelling 13B model.
Prompt template: Alpaca
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
Quantizations
Bits Per Weight | Size |
---|---|
main (2.4bpw) | 3.98 GB |
3bpw | 4.86 GB |
3.5bpw | 5.60 GB |
4bpw | 6.34 GB |
4.5bpw | 7.08 GB |
5bpw | 7.82 GB |
6bpw | 9.29 GB |
8bpw | 12.2 GB |
Original model card: Carsten Kragelund's Chronomaid Storytelling 13B
Chronomaid-Storytelling-13b
Merge including Noromaid-13b-v0.1.1, and Chronos-13b-v2 with the Storytelling-v1-Lora applied afterwards
Inteded for primarily RP, and will do ERP, narrator-character and group-chats without much trouble in my testing.
Prompt Format
Tested with Alpaca, the Noromaid preset's will probably also work (check the Noromaid model card for SillyTavern presets)
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
Sampler Settings
Tested at
temp
1.3min p
0.05 and 0.15temp
1.7,min p
0.08 and 0.15
Quantized Models
The model has been kindly quantized in GGUF, AWQ, and GPTQ by TheBloke
Find them in the Chronomaid-Storytelling-13b Collection
Thanks ❤️
To Undi & Ikari for Noromaid and Elinas for Chronos
Support Undi and Elinas on Kofi