Epos-8B

Epos-8B is a fine-tuned version of the base model Llama-3.1-8B from Meta, optimized for storytelling, dialogue generation, and creative writing. The model specializes in generating rich narratives, immersive prose, and dynamic character interactions, making it ideal for creative tasks.

---

Model Details

Model Description

Epos-8B is an 8 billion parameter language model fine-tuned for storytelling and narrative tasks.

• Developed by: P0x0
• Funded by: P0x0
• Shared by: P0x0
• Model type: Transformer-based Language Model
• Language(s) (NLP): Primarily English
• License: Apache 2.0
• Finetuned from model: meta-llama/Llama-3.1-8B

Model Sources

• Repository: Epos-8B on Hugging Face
• GGUF: GGUF by mradermache
• imatrix GGUF:imatrix quants by mradermacher

---

Uses

Direct Use

Epos-8B is ideal for:

• Storytelling: Generate detailed, immersive, and engaging narratives.
• Dialogue Creation: Create realistic and dynamic character interactions for stories or games.

How to Get Started with the Model

To run the quantized version of the model, you can use KoboldCPP, which allows you to run quantized GGUF models locally.

Steps:

1. Download KoboldCPP.
2. Follow the setup instructions provided in the repository.
3. Download the GGUF variant of Epos-8B from Epos-8B-GGUF.
4. Load the model in KoboldCPP and start generating!

Alternatively, integrate the model directly into your code with the following snippet:

from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("P0x0/Epos-8B")
model = AutoModelForCausalLM.from_pretrained("P0x0/Epos-8B")

input_text = "Once upon a time in a distant land..."
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))