Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- N8Programs/CreativeGPT
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+

|
| 11 |
+
|
| 12 |
+
# Model Card for Coxcomb
|
| 13 |
+
|
| 14 |
+
A creative writing model, using the superb [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2) as a base, finetuned on GPT-4 outputs to a diverse variety of prompts. It in no way competes with GPT-4 - it's quality of writing is below it, and it is primarily meant to be run in offline, local environments.
|
| 15 |
+
On creative writing benchmarks, it is consistently ranked higher than most other models - [it scores 72.37](https://eqbench.com/creative_writing.html), beating goliath-120b, yi chat, and mistral-large.
|
| 16 |
+
It is designed for **single-shot interactions**. You ask it to write a story, and it does. It is NOT designed for chat purposes, roleplay, or follow-up questions.
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
Trained w/ a 40M parameter lora on [N8Programs/CreativeGPT](https://huggingface.co/datasets/N8Programs/CreativeGPT) for 3 epochs. Overfit slightly (for much better benchmark results).
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
### Model Description
|
| 24 |
+
|
| 25 |
+
- **Developed by:** N8Programs
|
| 26 |
+
- **Model type:** Mistral
|
| 27 |
+
- **Language(s) (NLP):** English
|
| 28 |
+
- **License:** Apache 2.0
|
| 29 |
+
- **Finetuned from model:** [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2)
|
| 30 |
+
|
| 31 |
+
## Uses
|
| 32 |
+
|
| 33 |
+
Bot trained on NSFW (sexual or violent) content but will generate it when asked - it has not been trained with refusals. If you wish to ADD refusal behavior in, further tuning or filtering will be neccessary.
|
| 34 |
+
|
| 35 |
+
### Direct Use
|
| 36 |
+
|
| 37 |
+
GGUFs available at [Coxcomb-GGUF](https://huggingface.co/N8Programs/Coxcomb-GGUF)
|
| 38 |
+
Should work with transformers (not officially tested).
|
| 39 |
+
|
| 40 |
+
## Bias, Risks, and Limitations
|
| 41 |
+
|
| 42 |
+
Tends to generate stories with happy, trite endings. Most LLMs do this. It's very hard to get them not to.
|
| 43 |
+
|
| 44 |
+
## Training Details
|
| 45 |
+
|
| 46 |
+
Trained on a single M3 Max in roughly 12 hours.
|