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

Ref 70 E3 by mattshumer

 »  All LLMs  »  mattshumer  »  Ref 70 E3   URL Share it on

  74   
  Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/meta-lla...   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mattshumer/ref_70_e3 

Ref 70 E3 Benchmarks

MMLU Pro: 47.81
GPQA: 11.41
MUSR: 13
BBH: 49.27
IFEval: 62.94 vs 88 (so35)-28.5%
LLME Score: 0.34598
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ref 70 E3 (mattshumer/ref_70_e3)

Ref 70 E3 Parameters and Internals

Model Type 
text generation
Additional Notes 
System prompt is available with recommendations for maximizing the model's reflection capability.
Training Details 
Data Sources:
synthetic data generated by Glaive
Methodology:
Reflection-Tuning
Input Output 
Input Format:
Uses the standard Llama 3.1 chat format with special tokens for reasoning and reflection.
Accepted Modalities:
text
Output Format:
Outputs reasoning and final answer in separate tagged sections.
Performance Tips:
Recommended temperature of 0.7 and top_p of 0.95. Append 'Think carefully.' for increased accuracy.
LLM NameRef 70 E3
Repository 🤗https://huggingface.co/mattshumer/ref_70_e3 
Base Model(s)  meta-llama/Meta-Llama-3.1-70B-Instruct   meta-llama/Meta-Llama-3.1-70B-Instruct
Model Size70b
Required VRAM141.2 GB
Updated2024-12-22
Maintainermattshumer
Model Typellama
Instruction-BasedYes
Model Files  9.7 GB: 1-of-15   9.8 GB: 2-of-15   10.0 GB: 3-of-15   9.8 GB: 4-of-15   9.8 GB: 5-of-15   9.8 GB: 6-of-15   10.0 GB: 7-of-15   9.8 GB: 8-of-15   9.8 GB: 9-of-15   9.8 GB: 10-of-15   10.0 GB: 11-of-15   9.8 GB: 12-of-15   9.8 GB: 13-of-15   9.8 GB: 14-of-15   3.5 GB: 15-of-15
Model ArchitectureLlamaForCausalLM
Licensellama3.1
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128262
Torch Data Typefloat16

Quantized Models of the Ref 70 E3

Model
Likes
Downloads
VRAM
...lection Llama 3.1 70B Bnb 4bit1535139 GB
Reflection Llama 3.1 70B GGUF414926 GB

Best Alternatives to Ref 70 E3

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB32225
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB285121
Llama3 Function Calling 1048K1024K / 141.9 GB31
...a 3 70B Instruct Gradient 524K512K / 141.9 GB5123
...a 3 70B Instruct Gradient 262K256K / 141.9 GB20255
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB503
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB150
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB302
...a 3.1 Nemotron 70B Instruct HF128K / 141.9 GB1534001927
Meta Llama 3.1 70B Instruct128K / 141.9 GB521937513
Note: green Score (e.g. "73.2") means that the model is better than mattshumer/ref_70_e3.

Rank the Ref 70 E3 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