Downloads · 30 days
11
17% of all-time downloads
MuXodious/LongCite-llama3.1-8b-absolute-heresy
LongCite-llama3.1-8b-absolute-heresy is a text generation model from MuXodious. Use it when you need the model to write or continue text. It is set up for transformers.
This is a LongCite-llama3.1-8b fine-tune, produced through an extremely scuffed modification on P-E-W's Heretic (v1.1.0) abliteration engine merged with the Magnitude-Preserving Orthogonal Ablation PR.
Downloads · 30 days
11
17% of all-time downloads
All-time downloads
65
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
From the Hugging Face model README
This is a LongCite-llama3.1-8b fine-tune, produced through an extremely scuffed modification on P-E-W's Heretic (v1.1.0) abliteration engine merged with the Magnitude-Preserving Orthogonal Ablation PR.
Note: This model was generated at the request of redaihf. It could be lobotomized, or not. I wouldn't know.
Heretication Results
| Score Metric | Value | Parameter | Value |
|---|---|---|---|
| Refusals | 5/100 | direction_index | 18.83 |
| KL Divergence | 0.0515 | attn.o_proj.max_weight | 1.87 |
| Initial Refusals | 99/100 | attn.o_proj.max_weight_position | 22.79 |
| attn.o_proj.min_weight | 1.59 | ||
| attn.o_proj.min_weight_distance | 16.06 | ||
| mlp.down_proj.max_weight | 1.96 | ||
| mlp.down_proj.max_weight_position | 18.95 | ||
| mlp.down_proj.min_weight | 0.60 | ||
| mlp.down_proj.min_weight_distance | 12.70 |
The Heresy Index weighs the resulting model's corruption by the process (KL Divergence) and its abolition of doctrine (Refusals) for a final verdict in classification.
| Index Entry | Classification | Analysis |
|---|---|---|
| Absolute Heresy | Less than 10/100 Refusals and 0.10 KL Divergence | |
| Tainted Heresy | Around 25-11/100 Refusals and/or -0.20-0.11 KL Divergence | |
| Impotent Heresy | Anything above 25/100 Refusals and 0.21 KL Divergence |
Note: This is an arbitrary classification inspired by Warhammer 40K, having no tangible indication towards the model's performance.
LongCite-llama3.1-8b is trained based on Meta-Llama-3.1-8B, and is capable of generating fine-grained citations in long-context question answering. The model supports a maximum context window of up to 128K tokens.
Environment: transforemrs>=4.43.0.
A simple demo for deployment of the model:
import json
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained('THUDM/LongCite-llama3.1-8b', trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained('THUDM/LongCite-llama3.1-8b', torch_dtype=torch.bfloat16, trust_remote_code=True, device_map='auto')
context = '''
W. Russell Todd, 94, United States Army general (b. 1928). February 13. Tim Aymar, 59, heavy metal singer (Pharaoh) (b. 1963). Marshall \"Eddie\" Conway, 76, Black Panther Party leader (b. 1946). Roger Bonk, 78, football player (North Dakota Fighting Sioux, Winnipeg Blue Bombers) (b. 1944). Conrad Dobler, 72, football player (St. Louis Cardinals, New Orleans Saints, Buffalo Bills) (b. 1950). Brian DuBois, 55, baseball player (Detroit Tigers) (b. 1967). Robert Geddes, 99, architect, dean of the Princeton University School of Architecture (1965–1982) (b. 1923). Tom Luddy, 79, film producer (Barfly, The Secret Garden), co-founder of the Telluride Film Festival (b. 1943). David Singmaster, 84, mathematician (b. 1938).
'''
query = "What was Robert Geddes' profession?"
result = model.query_longcite(context, query, tokenizer=tokenizer, max_input_length=128000, max_new_tokens=1024)
print("Answer:\n{}\n".format(result['answer']))
print("Statement with citations:\n{}\n".format(
json.dumps(result['statements_with_citations'], indent=2, ensure_ascii=False)))
print("Context (divided into sentences):\n{}\n".format(result['splited_context']))
You can also deploy the model with vllm. See the code example in vllm_inference.py.
If you find our work useful, please consider citing LongCite:
@article{zhang2024longcite,
title = {LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA}
author={Jiajie Zhang and Yushi Bai and Xin Lv and Wanjun Gu and Danqing Liu and Minhao Zou and Shulin Cao and Lei Hou and Yuxiao Dong and Ling Feng and Juanzi Li},
journal={arXiv preprint arXiv:2409.02897},
year={2024}
}