83 lines
2.5 KiB
Markdown
83 lines
2.5 KiB
Markdown
---
|
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
|
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 (fixed)
|
|
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](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/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.
|
|
|
|
# Quantized GGUF
|
|
|
|
All GGUF models are available here: [natsumura-storytelling-rp-1.0-llama-3.1-8b-GGUF](https://huggingface.co/tohur/natsumura-storytelling-rp-1.0-llama-3.1-8b-GGUF)
|
|
|
|
# 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](https://github.com/hiyouga/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|>
|
|
``` |