tohur's picture
Update README.md
17dabc5 verified
metadata
base_model: tohur/natsumura-storytelling-rp-1.0-llama-3.1-8b
license: llama3.1
datasets:
  - tohur/natsumura-rp-identity-sharegpt
  - tohur/ultrachat_uncensored_sharegpt
  - Nopm/Opus_WritingStruct
  - ResplendentAI/bluemoon
  - tohur/Internal-Knowledge-Map-sharegpt
  - felix-ha/tiny-stories
  - tdh87/Stories
  - tdh87/Just-stories
  - tdh87/Just-stories-2

natsumura-storytelling-rp-1.0-llama-3.1-8b-GGUF

This is my Storytelling/RP model for my Natsumura series of 8b models. This model is finetuned on storytelling and roleplaying datasets so should be a great model to use for character chatbots in applications such as Sillytavern, Agnai, RisuAI and more. And should be a great model to use for fictional writing. Up to a 128k context.

  • Developed by: Tohur

  • License: llama3.1

  • Finetuned from model : meta-llama/Meta-Llama-3.1-8B-Instruct

    This model is based on meta-llama/Meta-Llama-3.1-8B-Instruct, and is governed by Llama 3.1 Community License Natsumura is uncensored, which makes the model compliant.It will be highly compliant with any requests, even unethical ones. You are responsible for any content you create using this model. Please use it responsibly.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by quality.)

Quant Notes
Q2_K
Q3_K_S
Q3_K_M lower quality
Q3_K_L
Q4_0
Q4_K_S fast, recommended
Q4_K_M fast, recommended
Q5_0
Q5_K_S
Q5_K_M
Q6_K very good quality
Q8_0 fast, best quality
f16 16 bpw, overkill

use in ollama

ollama pull Tohur/natsumura-storytelling-rp-llama-3.1

Datasets used:

  • tohur/natsumura-rp-identity-sharegpt
  • tohur/ultrachat_uncensored_sharegpt
  • Nopm/Opus_WritingStruct
  • ResplendentAI/bluemoon
  • tohur/Internal-Knowledge-Map-sharegpt
  • felix-ha/tiny-stories
  • tdh87/Stories
  • tdh87/Just-stories
  • tdh87/Just-stories-2

The following parameters were used in Llama Factory during training:

  • per_device_train_batch_size=2
  • gradient_accumulation_steps=4
  • lr_scheduler_type="cosine"
  • logging_steps=10
  • warmup_ratio=0.1
  • save_steps=1000
  • learning_rate=2e-5
  • num_train_epochs=3.0
  • max_samples=500
  • max_grad_norm=1.0
  • quantization_bit=4
  • loraplus_lr_ratio=16.0
  • fp16=True

Inference

I use the following settings for inference:

"temperature": 1.0,
"repetition_penalty": 1.05,
"top_p": 0.95
"top_k": 40
"min_p": 0.05

Prompt template: llama3

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>