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 MoE 4 Spider by VictorDCh

 »  All LLMs  »  VictorDCh  »  Llama 3 8B Instruct MoE 4 Spider   URL Share it on

  6   
  Adapter Base model:adapter:victordch/l... Base model:victordch/llama-3-8...   Dataset:generator   Finetuned   Generated from trainer   Instruct   Lora   Mixtral   Moe   Peft   Region:us   Safetensors   Sft   Sharded   Tensorboard   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/VictorDCh/Llama-3-8B-Instruct-MoE-4-spider 

Llama 3 8B Instruct MoE 4 Spider Benchmarks

LLME Score: 0.17435
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 MoE 4 Spider (VictorDCh/Llama-3-8B-Instruct-MoE-4-spider)

Llama 3 8B Instruct MoE 4 Spider Parameters and Internals

Additional Notes 
Model requires more information on description, intended uses, and training/evaluation data. Specific hyperparameters mentioned: learning_rate of 0.0002, train_batch_size of 1, eval_batch_size of 8, total_train_batch_size of 2. Using Adam optimizer with cosine learning rate scheduler.
Training Details 
Data Sources:
generator
LLM NameLlama 3 8B Instruct MoE 4 Spider
Repository 🤗https://huggingface.co/VictorDCh/Llama-3-8B-Instruct-MoE-4-spider 
Base Model(s)  Llama 3 8B Instruct MoE 4   VictorDCh/Llama-3-8B-Instruct-MoE-4
Model Size47.5b
Required VRAM95.3 GB
Updated2024-08-15
MaintainerVictorDCh
Instruction-BasedYes
Model Files  2.5 GB   5.0 GB: 1-of-20   5.0 GB: 2-of-20   4.9 GB: 3-of-20   5.0 GB: 4-of-20   5.0 GB: 5-of-20   4.9 GB: 6-of-20   5.0 GB: 7-of-20   5.0 GB: 8-of-20   5.0 GB: 9-of-20   4.9 GB: 10-of-20   5.0 GB: 11-of-20   5.0 GB: 12-of-20   4.9 GB: 13-of-20   5.0 GB: 14-of-20   5.0 GB: 15-of-20   4.9 GB: 16-of-20   5.0 GB: 17-of-20   5.0 GB: 18-of-20   4.7 GB: 19-of-20   1.1 GB: 20-of-20   0.0 GB
Model ArchitectureAdapter
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|im_end|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesdown_proj|v_proj|o_proj|up_proj|gate_proj|k_proj|q_proj
LoRA Alpha128
LoRA Dropout0.05
R Param256

Rank the Llama 3 8B Instruct MoE 4 Spider 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? 47770 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 v20241227
  Support LLM Explorer