GGUF
Not-For-All-Audiences
nsfw
Inference Endpoints
Edit model card

Description

This repo contains quantized files of Utopia-13B, a merge I have done with the new task_arithmetic merge method from mergekit.

Models and loras used

The sauce

Xwin-LM/Xwin-LM-13B-V0.2
Undi95/Storytelling-v2.1-13B-lora
=> p1

NeverSleep/Nethena-13B
zattio770/120-Days-of-LORA-v2-13B
=> p2

PygmalionAI/pygmalion-2-13b
lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
=> p3



merge_method: task_arithmetic
base_model: TheBloke/Llama-2-13B-fp16
models:
  - model: TheBloke/Llama-2-13B-fp16
  - model: Undi95/newpart1
    parameters:
      weight: 1.0
  - model: Undi95/newpart2
    parameters:
      weight: 0.45
  - model: Undi95/newpart3
    parameters:
      weight: 0.33
dtype: float16

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

If you want to support me, you can here.

Downloads last month
12
GGUF
Model size
13B params
Architecture
llama

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .