LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Yi 34B Spicyboros 2 2 Run3 QLoRA by adamo1139

 »  All LLMs  »  adamo1139  »  Yi 34B Spicyboros 2 2 Run3 QLoRA   URL Share it on

  1   

Yi 34B Spicyboros 2 2 Run3 QLoRA is an open-source language model by adamo1139. Features: 34b LLM, VRAM: 0.5GB, LLM Explorer Score: 0.11.

  4-bit   Bitsandbytes   Endpoints compatible   Generated from trainer   Llama   Lora   Region:us
Model Card on HF 🤗: https://huggingface.co/adamo1139/Yi-34B-Spicyboros-2-2-run3-QLoRA 

Yi 34B Spicyboros 2 2 Run3 QLoRA Benchmarks

LLME Score: 0.10613
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yi 34B Spicyboros 2 2 Run3 QLoRA (adamo1139/Yi-34B-Spicyboros-2-2-run3-QLoRA)
🌟 Advertise your project 🚀

Yi 34B Spicyboros 2 2 Run3 QLoRA Parameters and Internals

Model Type 
text generation
Use Cases 
Limitations:
Use is limited by Yi license
Additional Notes 
Thesaurus mode seems to be solved by lowering repetition penalty to 1.0. It can go into loops of repeating sentences occasionally.
Training Details 
Data Sources:
Jon Durbin's Spicyboros 2.2 dataset
Methodology:
Fine-tuning based on Yi-34B Llama
Training Time:
10 hours
Hardware Used:
single RTX 3090 Ti 24GB
Model Architecture:
Llama-fied Yi-34B
Input Output 
Input Format:
ChatML prompt format
LLM NameYi 34B Spicyboros 2 2 Run3 QLoRA
Repository 🤗https://huggingface.co/adamo1139/Yi-34B-Spicyboros-2-2-run3-QLoRA 
Model Size34b
Required VRAM0.5 GB
Updated2026-03-29
Maintaineradamo1139
Model Files  0.5 GB
Model ArchitectureAutoModelForCausalLM
Model Max Length4096
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesup_proj|q_proj|down_proj|v_proj|gate_proj|o_proj|k_proj
LoRA Alpha32
LoRA Dropout0.05
R Param16

Best Alternatives to Yi 34B Spicyboros 2 2 Run3 QLoRA

Best Alternatives
Context / RAM
Downloads
Likes
...awrr1 LORA DPO Experimental R30K / 0.5 GB7131
Yi 34B Qlora E10K / 5.8 GB7650
Yi 34B 200K AEZAKMI V2 LoRA0K / 0.5 GB31
Yi 34B AEZAKMI V1 LoRA0K / 0.5 GB51
Yi 34B Spicyboros 3.1 2 LoRA0K / 2 GB01
Yi 34B Spicyboros 3.1 LoRA0K / 2 GB94
Limarpv3 Yi Llama 34B Lora0K / 1 GB1010
Limarpv3 Yi Llama 34B Lora0K / 1 GB810
Yi 34B GiftedConvo0K / 5.8 GB22
Note: green Score (e.g. "73.2") means that the model is better than adamo1139/Yi-34B-Spicyboros-2-2-run3-QLoRA.

Rank the Yi 34B Spicyboros 2 2 Run3 QLoRA Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 52392 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer