Smaug 72B V0.1 AWQ by LoneStriker

 ยป  All LLMs  ยป  LoneStriker  ยป  Smaug 72B V0.1 AWQ   URL Share it on

  4-bit   Autotrain compatible   Awq Base model:moreh/momo-72b-lora... Base model:quantized:moreh/mom...   Endpoints compatible   Llama   Lora   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Smaug 72B V0.1 AWQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Smaug 72B V0.1 AWQ (LoneStriker/Smaug-72B-v0.1-AWQ)
๐ŸŒŸ Advertise your project ๐Ÿš€

Smaug 72B V0.1 AWQ Parameters and Internals

Training Details 
Methodology:
finetuning
LLM NameSmaug 72B V0.1 AWQ
Repository ๐Ÿค—https://huggingface.co/LoneStriker/Smaug-72B-v0.1-AWQ 
Base Model(s)  moreh/MoMo-72B-lora-1.8.7-DPO   moreh/MoMo-72B-lora-1.8.7-DPO
Model Size72b
Required VRAM41.3 GB
Updated2025-07-30
MaintainerLoneStriker
Model Typellama
Model Files  10.0 GB: 1-of-5   10.0 GB: 2-of-5   10.0 GB: 3-of-5   8.8 GB: 4-of-5   2.5 GB: 5-of-5
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.37.1
Tokenizer ClassGPT2Tokenizer
Vocabulary Size152064
LoRA ModelYes
Torch Data Typefloat16

Best Alternatives to Smaug 72B V0.1 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Smaug 72B V0.1 AWQ32K / 41.3 GB63
Smaug 72B V0.1 2.4bpw H6 EXL232K / 24.5 GB171
2 Pro Math128K / 141.9 GB70
Smaug 72B V0.132K / 144.5 GB9027469
TW3 JRGL V232K / 79.7 GB179600
Le Triomphant ECE TW332K / 79.7 GB179384
ECE TW3 JRGL V532K / 159.6 GB98401
MoMo 72B Lora 1.8.7 DPO32K / 208.5 GB225768
Rhea 72B V0.532K / 144.5 GB9845136
JuliusCesar 72B BeyonderV.032K / 74.2 GB50
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Smaug-72B-v0.1-AWQ.

Rank the Smaug 72B V0.1 AWQ 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  

What open-source LLMs or SLMs are you in search of? 50262 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124