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 Claudstruct V1 by jrahn

 »  All LLMs  »  jrahn  »  Llama 3 8B Claudstruct V1   URL Share it on

  7   
  4-bit   Adapter Base model:adapter:meta-llama/... Base model:meta-llama/meta-lla...   Bitsandbytes Dataset:norquinal/claude multi...   En   Finetuned   Generated from trainer   Instruct   Llama   Lora   Peft   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/jrahn/llama-3-8b-claudstruct-v1 

Llama 3 8B Claudstruct V1 Benchmarks

ARC: 59.73 vs 96.7 (so35)-38.2%
HellaSwag: 79.94 vs 95.3 (gpt4)-16.1%
MMLU: 64.98 vs 88.3 (so35)-26.4%
TruthfulQA: 51.82 vs 59 (gpt4)-12.2%
WinoGrande: 74.43 vs 87.5 (gpt4)-14.9%
GSM8K: 64.52 vs 96.4 (so35)-33.1%
LLME Score: 0.2148
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 Claudstruct V1 (jrahn/llama-3-8b-claudstruct-v1)

Llama 3 8B Claudstruct V1 Parameters and Internals

Model Type 
LlamaForCausalLM
Supported Languages 
en (high)
Training Details 
Data Sources:
Norquinal/claude_multi_instruct_30k
Context Length:
512
Hardware Used:
multi-GPU: 2 devices
LLM NameLlama 3 8B Claudstruct V1
Repository 🤗https://huggingface.co/jrahn/llama-3-8b-claudstruct-v1 
Base Model(s)  Meta Llama 3 8B Instruct   meta-llama/Meta-Llama-3-8B-Instruct
Model Size8b
Required VRAM0.1 GB
Updated2024-12-17
Maintainerjrahn
Instruction-BasedYes
Model Files  0.1 GB   0.0 GB
Supported Languagesen
Model ArchitectureAdapter
Licensellama3
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Moduleso_proj|q_proj|k_proj|gate_proj|v_proj|up_proj|down_proj
LoRA Alpha16
LoRA Dropout0.05
R Param8

Best Alternatives to Llama 3 8B Claudstruct V1

Best Alternatives
Context / RAM
Downloads
Likes
... 3 8B Instruct Bvr Finetune V38K / 16.1 GB50
Flippa V60K / 0 GB111
...lama 3 1 8B Instruct Orca ORPO0K / 0.1 GB1312
...ight AGI Llama3.1 8B UC200k V20K / 0.2 GB882
Vortex20K / 4.4 GB80
FineLlama3.1 8B Instruct Lora0K / 0.2 GB01
Llama3 8B Instruct Code0K / 0.2 GB21
Llama 3 8B Claudstruct V30K / 0.1 GB110
Llama 3 8B Instruct 80K QLoRA0K / 2.2 GB024
...Llama 3 8B Instruct ORPO QLoRA0K / 0.7 GB50
Note: green Score (e.g. "73.2") means that the model is better than jrahn/llama-3-8b-claudstruct-v1.

Rank the Llama 3 8B Claudstruct V1 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? 40066 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 v20241217
  Support LLM Explorer