Llama 3 8B Finetuned by fay-ong

 ยป  All LLMs  ยป  fay-ong  ยป  Llama 3 8B Finetuned   URL Share it on

  4-bit   4bit   Adapter Base model:unsloth/llama-3-8b-...   Bitsandbytes   Finetuned   Generated from trainer   Instruct   License:apache-2.0   Llama   Llama-factory   Lora   Peft   Quantized   Region:us   Safetensors   Tensorboard   Unsloth

Rank the Llama 3 8B Finetuned 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  
Llama 3 8B Finetuned (fay-ong/llama-3-8b-finetuned)

Best Alternatives to Llama 3 8B Finetuned

Best Alternatives
HF Rank
Llama3 8b Sa V0.167.940K / 0 GB100
Llama 3 8B Instruct 80K QLoRA64.110K / 2.2 GB018
...a 3 8B Arabic Customer Service0K / 0 GB60
My Dog Is My Psych0K / 0 GB431
Jimbot 8B Lora0K / 0 GB11
Llama3 Cs0K / 0 GB1320
...eta Llama 3 8B Instruct Amazon0K / 0 GB250
Llama3 8b Taiwan Btc Qlora0K / 0.1 GB45
... 8B Instruct 262K Chinese Lora0K / 0.1 GB04
Llama3 8b Taiwan Stock Qlora0K / 0.1 GB153
Note: green Score (e.g. "73.2") means that the model is better than fay-ong/llama-3-8b-finetuned.

Llama 3 8B Finetuned Parameters and Internals

LLM NameLlama 3 8B Finetuned
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Llama 3 8B Instruct Bnb 4bit   unsloth/llama-3-8b-Instruct-bnb-4bit
Model Size8b
Required VRAM0.1 GB
Model Files  0.1 GB   0.0 GB
Quantization Type4bit
Model ArchitectureAdapter
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
LoRA ModelYes
PEFT Target Modulesgate_proj|o_proj|down_proj|k_proj|up_proj|q_proj|v_proj
LoRA Alpha16
LoRA Dropout0
R Param8

What open-source LLMs or SLMs are you in search of? 34902 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801