LLM EXPLORER 63,407 MODELS INDEXED

Zephyr Finetuned Legal by Feluda

By Feluda · 2 downloads
HF Repo ↗ Copy URL

Zephyr Finetuned Legal is an open-source language model by Feluda. Features: 7b LLM, License: mit, Quantized, Fine-Tuned, LLM Explorer Score: 0.1.

  4-bit   Adapter Base model:adapter:thebloke/ze... Base model:thebloke/zephyr-7b-...   Conversational Dataset:joelniklaus/legal case...   Finetuned   Generated from trainer   Gptq   Lora   Mistral   Peft   Quantized   Region:us   Safetensors   Sft   Tensorboard   Trl
Model Card on HF 🤗: https://huggingface.co/Feluda/zephyr-finetuned-legal 

Zephyr Finetuned Legal Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model is a fine-tuned version of TheBloke/zephyr-7B-beta-GPTQ.
Training Details 
Data Sources:
joelniklaus/legal_case_document_summarization
LLM NameZephyr Finetuned Legal
Repository 🤗https://huggingface.co/Feluda/zephyr-finetuned-legal 
Base Model(s)  Zephyr 7B Beta GPTQ   TheBloke/zephyr-7B-beta-GPTQ
Model Size7b
Required VRAM0 GB
Updated2026-05-16
MaintainerFeluda
Model Files  0.0 GB   0.0 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureAdapter
Licensemit
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token</s>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|v_proj
LoRA Alpha16
LoRA Dropout0.05
R Param16

Best Alternatives to Zephyr Finetuned Legal

Best Alternatives
Context / RAM
Downloads
Likes
Mistral Finetuned Bookcorpus0K / 0 GB50
Term Qwen2 7 Json Lora0K / 0.1 GB60
LMS Chatbot0K / 0 GB50
Llama 2 7B Chat Text2code0K / 0 GB124
Zephyr 7B Alpha GPTQ0K / 0 GB21
Selfbot 256 Mistral0K / 0.4 GB60
Thesa0K / 0 GB41
Futadom Mistral0K / 0.2 GB71
Humiliation Mistral0K / 0.2 GB41
Gnosis Reformatted Mistral0K / 0.2 GB70
Note: green Score (e.g. "73.2") means that the model is better than Feluda/zephyr-finetuned-legal.