Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) pygmalion-1.3b - GGUF - Model creator: https://huggingface.co/PygmalionAI/ - Original model: https://huggingface.co/PygmalionAI/pygmalion-1.3b/ | Name | Quant method | Size | | ---- | ---- | ---- | | [pygmalion-1.3b.Q2_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q2_K.gguf) | Q2_K | 0.53GB | | [pygmalion-1.3b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ3_XS.gguf) | IQ3_XS | 0.59GB | | [pygmalion-1.3b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ3_S.gguf) | IQ3_S | 0.61GB | | [pygmalion-1.3b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K_S.gguf) | Q3_K_S | 0.61GB | | [pygmalion-1.3b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ3_M.gguf) | IQ3_M | 0.66GB | | [pygmalion-1.3b.Q3_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K.gguf) | Q3_K | 0.71GB | | [pygmalion-1.3b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K_M.gguf) | Q3_K_M | 0.71GB | | [pygmalion-1.3b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K_L.gguf) | Q3_K_L | 0.77GB | | [pygmalion-1.3b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ4_XS.gguf) | IQ4_XS | 0.74GB | | [pygmalion-1.3b.Q4_0.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_0.gguf) | Q4_0 | 0.77GB | | [pygmalion-1.3b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ4_NL.gguf) | IQ4_NL | 0.78GB | | [pygmalion-1.3b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_K_S.gguf) | Q4_K_S | 0.78GB | | [pygmalion-1.3b.Q4_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_K.gguf) | Q4_K | 0.85GB | | [pygmalion-1.3b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_K_M.gguf) | Q4_K_M | 0.85GB | | [pygmalion-1.3b.Q4_1.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_1.gguf) | Q4_1 | 0.85GB | | [pygmalion-1.3b.Q5_0.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_0.gguf) | Q5_0 | 0.92GB | | [pygmalion-1.3b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_K_S.gguf) | Q5_K_S | 0.92GB | | [pygmalion-1.3b.Q5_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_K.gguf) | Q5_K | 0.98GB | | [pygmalion-1.3b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_K_M.gguf) | Q5_K_M | 0.98GB | | [pygmalion-1.3b.Q5_1.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_1.gguf) | Q5_1 | 1.0GB | | [pygmalion-1.3b.Q6_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q6_K.gguf) | Q6_K | 1.08GB | | [pygmalion-1.3b.Q8_0.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q8_0.gguf) | Q8_0 | 1.4GB | Original model description: --- license: agpl-3.0 language: - en thumbnail: tags: - text generation - conversational inference: false --- # Pygmalion 1.3B ## Model description Pymalion 1.3B is a proof-of-concept dialogue model based on EleutherAI's [pythia-1.3b-deduped](https://huggingface.co/EleutherAI/pythia-1.3b-deduped). **Warning:** This model is **NOT** suitable for use by minors. It **will** output X-rated content under certain circumstances. ## Training data The fine-tuning dataset consisted of 56MB of dialogue data gathered from multiple sources, which includes both real _and_ partially machine-generated conversations. ## Training procedure Fine-tuning was done using [ColossalAI](https://github.com/hpcaitech/ColossalAI) (specifically, with a slightly modified version of their [OPT fine-tune example](https://github.com/hpcaitech/ColossalAI/blob/78509124d32b63b7fc36f6508e0576a326d51422/examples/language/opt/run_clm.py)) for around 11.4 million tokens over 5440 steps on a single 24GB GPU. The run took just under 21 hours. ## Intended use ### The easy way We provide a notebook with a Gradio UI for playing around with the model without having to manually format inputs. This notebook can be found [here](https://github.com/PygmalionAI/gradio-ui/blob/master/notebooks/GPU.ipynb). ### The manual way The model can be used as a regular text generation model, but it'll perform best if the input prompt adheres to the following format: ``` [CHARACTER]'s Persona: [A few sentences about the character you want the model to play] [DIALOGUE HISTORY] You: [Your input message here] [CHARACTER]: ``` Where `[CHARACTER] `is, as you can probably guess, the name of the character you want the model to portray, and `[DIALOGUE HISTORY]` is chat history so the model can have some conversational context to draw from. Ideally it'll be pairs of messages like: ``` [CHARACTER]: [some dialogue here] You: [your response to the dialogue above] ``` Apart from chat history, you can also just add example conversations in `[DIALOGUE HISTORY]` to show how the character should speak - ideally at the beginning, so it doesn't get confused as to what's conversation history vs. character definition. ## Known issues - The model can get stuck repeating certain phrases, or sometimes even entire sentences. - We believe this is due to that behavior being present in the training data itself, and plan to investigate and adjust accordingly for future versions.