Yi 34B 200K Rawrr1 LORA DPO Experimental R2 by adamo1139

 ยป  All LLMs  ยป  adamo1139  ยป  Yi 34B 200K Rawrr1 LORA DPO Experimental R2   URL Share it on

  4-bit   Adapter   Bitsandbytes   Finetuned   Generated from trainer   Llama   Lora   Peft   Region:us

Yi 34B 200K Rawrr1 LORA DPO Experimental R2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Yi 34B 200K Rawrr1 LORA DPO Experimental R2 Parameters and Internals

LLM NameYi 34B 200K Rawrr1 LORA DPO Experimental R2
Repository ๐Ÿค—https://huggingface.co/adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r2 
Model Size34b
Required VRAM0.1 GB
Updated2024-09-07
Maintaineradamo1139
Model Files  0.1 GB
Model ArchitectureAdapter
Model Max Length200000
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesk_proj|down_proj|up_proj|v_proj|q_proj|gate_proj|o_proj
LoRA Alpha8
LoRA Dropout0.05
R Param4
Yi 34B 200K Rawrr1 LORA DPO Experimental R2 (adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r2)

Best Alternatives to Yi 34B 200K Rawrr1 LORA DPO Experimental R2

Best Alternatives
Context / RAM
Downloads
Likes
30B 2e0K / 0 GB50
Airoboros 34B 3.3 Peft0K / 0.5 GB01
Bagel 34B V0.5 Peft0K / 0.5 GB01
...34B 200K AEZAKMI RAW 2301 LoRA0K / 0.5 GB01
34B Beta Onc V10K / 0 GB31
...pmoney 34B 200K Chat Evaluator0K / 2 GB034
...awrr V1 Run1 Experimental LoRA0K / 0.5 GB21
Deacon 34B Qlora Adapter0K / 0.1 GB02
Yi 34B 200K MiniOrca Adapter0K / 0.1 GB01
Yi 34B Alpaca Cot Lora0K / 0.1 GB015
Note: green Score (e.g. "73.2") means that the model is better than adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r2.

Rank the Yi 34B 200K Rawrr1 LORA DPO Experimental R2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 35693 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803