LLM EXPLORER 63,407 MODELS INDEXED

Ref 70 E3 by mattshumer

By mattshumer · 23 downloads
HF Repo ↗ Copy URL

Ref 70 E3 is an open-source language model by mattshumer. Features: 70b LLM, VRAM: 141.2GB, Context: 128K, License: llama3.1, Instruction-Based, LLM Explorer Score: 0.24.

Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/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
Updated2026-07-07
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
Reflection Llama 3.1 70B GGUF511526 GB
...lection Llama 3.1 70B Bnb 4bit141039 GB

Best Alternatives to Ref 70 E3

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB90695
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB76844
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB22122
Llama3 Function Calling 1048K1024K / 141.9 GB51
...a 3 70B Instruct Gradient 524K512K / 141.9 GB2423
...a 3 70B Instruct Gradient 262K256K / 141.9 GB2056
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB103
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB50
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB213
Llama 3.1 70B Instruct128K / 141.9 GB813492938
Note: green Score (e.g. "73.2") means that the model is better than mattshumer/ref_70_e3.