Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


ValueLlama-3-8B - GGUF
- Model creator: https://huggingface.co/Value4AI/
- Original model: https://huggingface.co/Value4AI/ValueLlama-3-8B/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [ValueLlama-3-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q2_K.gguf) | Q2_K | 2.96GB |
| [ValueLlama-3-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
| [ValueLlama-3-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.IQ3_S.gguf) | IQ3_S | 3.43GB |
| [ValueLlama-3-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
| [ValueLlama-3-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.IQ3_M.gguf) | IQ3_M | 3.52GB |
| [ValueLlama-3-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q3_K.gguf) | Q3_K | 3.74GB |
| [ValueLlama-3-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
| [ValueLlama-3-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
| [ValueLlama-3-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
| [ValueLlama-3-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q4_0.gguf) | Q4_0 | 4.34GB |
| [ValueLlama-3-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
| [ValueLlama-3-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
| [ValueLlama-3-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q4_K.gguf) | Q4_K | 4.58GB |
| [ValueLlama-3-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
| [ValueLlama-3-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q4_1.gguf) | Q4_1 | 4.78GB |
| [ValueLlama-3-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q5_0.gguf) | Q5_0 | 5.21GB |
| [ValueLlama-3-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
| [ValueLlama-3-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q5_K.gguf) | Q5_K | 5.34GB |
| [ValueLlama-3-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
| [ValueLlama-3-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q5_1.gguf) | Q5_1 | 5.65GB |
| [ValueLlama-3-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q6_K.gguf) | Q6_K | 6.14GB |
| [ValueLlama-3-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Value4AI_-_ValueLlama-3-8B-gguf/blob/main/ValueLlama-3-8B.Q8_0.gguf) | Q8_0 | 7.95GB |




Original model description:
---
library_name: transformers
tags:
- llama-factory
license: llama3
datasets:
- allenai/ValuePrism
- Value4AI/ValueBench
language:
- en
---

# Model Card for ValueLlama


## Model Description


ValueLlama is designed for perception-level value measurement in an open-ended value space, which includes two tasks: (1) Relevance classification determines whether a perception is relevant to a value; and (2) Valence classification determines whether a perception supports, opposes, or remains neutral (context-dependent) towards a value. Both tasks are formulated as generating a label given a value and a perception.

- **Model type:** Language model
- **Language(s) (NLP):** en
- **Finetuned from model:** [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)

## Paper


For more information, please refer to our paper: [*Measuring Human and AI Values based on Generative Psychometrics with Large Language Models*](https://arxiv.org/abs/2409.12106).

## Uses

It is intended for use in **research** to measure human/AI values and conduct related analyses.

See our codebase for more details: [https://github.com/Value4AI/gpv](https://github.com/Value4AI/gpv).


## BibTeX:

If you find this model helpful, we would appreciate it if you cite our paper:

```bibtex
@misc{ye2024gpv,
      title={Measuring Human and AI Values based on Generative Psychometrics with Large Language Models}, 
      author={Haoran Ye and Yuhang Xie and Yuanyi Ren and Hanjun Fang and Xin Zhang and Guojie Song},
      year={2024},
      eprint={2409.12106},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2409.12106}, 
}
```