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

Llama 3 8B Instruct 80K QLoRA by namespace-Pt

 »  All LLMs  »  namespace-Pt  »  Llama 3 8B Instruct 80K QLoRA   URL Share it on

  0   
  Arxiv:2308.14508   Arxiv:2402.13718   Adapter   Conversational   Finetuned   Instruct   Lora   Region:us   Safetensors

Llama 3 8B Instruct 80K QLoRA Benchmarks

ARC: 57.42 vs 96.7 (so35)-40.6%
HellaSwag: 77.34 vs 95.3 (gpt4)-18.8%
MMLU: 64.91 vs 88.3 (so35)-26.5%
TruthfulQA: 47.86 vs 59 (gpt4)-18.9%
WinoGrande: 74.9 vs 87.5 (gpt4)-14.4%
GSM8K: 62.24 vs 96.4 (so35)-35.4%
LLME Score: 0.2206
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Llama 3 8B Instruct 80K QLoRA Parameters and Internals

Model Type 
text generation
Training Details 
Data Sources:
3.5K long-context training data synthesized from GPT-4
Methodology:
QLoRA
Context Length:
80000
Training Time:
8 hours
Hardware Used:
8xA800 (80G) machine
Input Output 
Accepted Modalities:
text
LLM NameLlama 3 8B Instruct 80K QLoRA
Repository 🤗https://huggingface.co/namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA 
Model Size8b
Required VRAM2.2 GB
Updated2024-11-23
Maintainernamespace-Pt
Instruction-BasedYes
Model Files  2.2 GB
Model ArchitectureAdapter
Licensemit
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|k_proj|q_proj|o_proj
LoRA Alpha16
LoRA Dropout0
R Param32
Llama 3 8B Instruct 80K QLoRA (namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA)

Best Alternatives to Llama 3 8B Instruct 80K QLoRA

Best Alternatives
Context / RAM
Downloads
Likes
... 3 8B Instruct Bvr Finetune V38K / 16.1 GB50
Vortex20K / 4.4 GB80
FineLlama3.1 8B Instruct Lora0K / 0.2 GB01
Llama3 8B Instruct Code0K / 0.2 GB91
Llama 3 8B Claudstruct V30K / 0.1 GB90
Llama 3 8B Claudstruct V10K / 0.1 GB60
...Llama 3 8B Instruct ORPO QLoRA0K / 0.7 GB50
Llama3 8b Sa V0.10K / 0 GB60
Llama3 Tw 8B Btc Qlora0K / 0.1 GB103
Results0K / 4.4 GB190
Note: green Score (e.g. "73.2") means that the model is better than namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA.

Rank the Llama 3 8B Instruct 80K 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? 38255 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.
Release v20241110
  Support LLM Explorer