What are the hardware requirements for Todd Proxy LoRA 7B?

Todd Proxy LoRA 7B requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Todd Proxy LoRA 7B and how large is it?

Todd Proxy LoRA 7B is developed by autobots, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Todd Proxy LoRA 7B?

Todd Proxy LoRA 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Todd Proxy LoRA 7B by autobots — VRAM 0.1GB

Name: Todd Proxy LoRA 7B
Author: autobots

Todd Proxy LoRA 7B is an open-source language model by autobots. Features: 7b LLM, VRAM: 0.1GB, LLM Explorer Score: 0.07.

Adapter Finetuned Lora Region:us

Model Card on HF 🤗: https://huggingface.co/autobots/Todd_Proxy_LoRA_7b

Todd Proxy LoRA 7B Parameters and Internals

Additional Notes

Significant changes in interaction. V1 indicated overfitting with increase in 'master' terminology, V2 improvement noted in model strength with dedicated training set and settings adjustments.

Training Details

Data Sources:

100k dumped messages from 'chan' todd proxy

Methodology:

Trained for 3 epochs on 4-bit precision. Overfitting after 3, ideally should have been 2 epochs. V2 version trained at higher rank and longer context (512) on unique data with removed content warnings.

Context Length:

512

Model Architecture:

llama-7b architecture with 4-bit and FP16 testing.

Release Notes

Version:

Notes:

Trained with non-deduped dataset causing overfitting, more dependence on 'master' terminology.

Version:

Notes:

Trained on higher rank, longer context with unique data, excluding content-related issues, resulting in stronger model performance.

LLM Name	Todd Proxy LoRA 7b
Repository 🤗	https://huggingface.co/autobots/Todd_Proxy_LoRA_7b
Model Size	7b
Required VRAM	0.1 GB
Updated	2026-07-18
Maintainer	autobots
Model Files	0.1 GB
Model Architecture	Adapter
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	q_proj\|v_proj
LoRA Alpha	64
LoRA Dropout	0.05
R Param	32

Rank the Todd Proxy LoRA 7B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the Todd Proxy LoRA 7B

Model	Likes	Downloads	VRAM
LLaMA 7B 2bit	5	10	2 GB
Llama 7B 8bit	0	14	7 GB
LLaMA 7B 4bit 32g	1	11	4 GB
Llama 7B 4bit Act	2	11	3 GB
Llama 7B 4bit	12	68	3 GB

Best Alternatives to Todd Proxy LoRA 7B

Best Alternatives	Context / RAM	Downloads	Likes
K2 Horizon 7B Uno	0K / 1.4 GB	10105	16
...x H3 Prompt Rewriter LoRA Omni	0K / 1.3 GB	27	32
Antcoder Planner 7B	0K / 0.3 GB	37	1
Vilaw Llm DPO	0K / 0.2 GB	17	2
DeepMath R1 Distill Qwen 7B	0K / 0.1 GB	13	1
Zduhac Cyber 7B V2	0K / 0 GB	8	1
Llama2 7B Qlora Guanaco	0K / 0.1 GB	11	1
Qwen Megumin	0K / 0.1 GB	11	1
Mistral 7B Instruct Vi Alpaca	0K / 0.4 GB	5	0
Vietnamese Amr Baseline 7B	0K / 0 GB	13	0

Note: green Score (e.g. "73.2") means that the model is better than autobots/Todd_Proxy_LoRA_7b.