Wikimedia Wikipedia 100K 100000 Fedavg C4s4 I10 B4a1 L512 R16a32 20241116082857 by prayslaks

 ยป  All LLMs  ยป  prayslaks  ยป  Wikimedia Wikipedia 100K 100000 Fedavg C4s4 I10 B4a1 L512 R16a32 20241116082857   URL Share it on

  Arxiv:1910.09700   Adapter Base model:adapter:prometheus-... Base model:prometheus-eval/pro...   Finetuned   Lora   Peft   Region:us   Safetensors

Wikimedia Wikipedia 100K 100000 Fedavg C4s4 I10 B4a1 L512 R16a32 20241116082857 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Wikimedia Wikipedia 100K 100000 Fedavg C4s4 I10 B4a1 L512 R16a32 20241116082857 (prayslaks/wikimedia_wikipedia_100K_100000_fedavg_c4s4_i10_b4a1_l512_r16a32_20241116082857)

Wikimedia Wikipedia 100K 100000 Fedavg C4s4 I10 B4a1 L512 R16a32 20241116082857 Parameters and Internals

LLM NameWikimedia Wikipedia 100K 100000 Fedavg C4s4 I10 B4a1 L512 R16a32 20241116082857
Repository ๐Ÿค—https://huggingface.co/prayslaks/wikimedia_wikipedia_100K_100000_fedavg_c4s4_i10_b4a1_l512_r16a32_20241116082857 
Base Model(s)  prometheus-eval/prometheus-7b-v2.0   prometheus-eval/prometheus-7b-v2.0
Model Size7b
Required VRAM0 GB
Updated2025-04-29
Maintainerprayslaks
Model Files  0.0 GB   0.1 GB   0.0 GB   0.0 GB
Model ArchitectureAdapter
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token</s>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|q_proj
LoRA Alpha32
LoRA Dropout0.05
R Param16

Best Alternatives to Wikimedia Wikipedia 100K 100000 Fedavg C4s4 I10 B4a1 L512 R16a32 20241116082857

Best Alternatives
Context / RAM
Downloads
Likes
Qwen Megumin0K / 0.1 GB11
...s 25 Mistral 7B Irca DPO Pairs0K / 0.1 GB50
Hr Other 7B Lora0K / 0.2 GB300
Qwen1.5 7B Chat Sa V0.10K / 0 GB50
Zephyr 7B Ipo 0K 15K I10K / 0.7 GB250
Deepseek Llm 7B Chat Sa V0.10K / 0 GB50
Deepthink Reasoning Adapter0K / 0.2 GB142
... Days Of Sodom LoRA Mistral 7B0K / 0.2 GB50
...4a1 L512 R16a32 202411160915540K / 0 GB220
...4a1 L512 R16a32 202411160707310K / 0 GB220
Note: green Score (e.g. "73.2") means that the model is better than prayslaks/wikimedia_wikipedia_100K_100000_fedavg_c4s4_i10_b4a1_l512_r16a32_20241116082857.

Rank the Wikimedia Wikipedia 100K 100000 Fedavg C4s4 I10 B4a1 L512 R16a32 20241116082857 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? 46971 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227