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

Mixtral 8x7b MonsterInstruct by Zangs3011

 »  All LLMs  »  Zangs3011  »  Mixtral 8x7b MonsterInstruct   URL Share it on

  5   
  Arxiv:1910.09700   Adapter Base model:adapter:mistralai/m... Base model:mistralai/mixtral-8... Dataset:qblocks/monsterinstruc...   Finetuned   Lora   Moe   Peft   Region:us   Safetensors

Mixtral 8x7b MonsterInstruct Benchmarks

ARC: 65.19-32.3%
HellaSwag: 85.81-10%
MMLU: 70.15-18.9%
TruthfulQA: 48.47-17.8%
WinoGrande: 80.27-8.3%
GSM8K: 48.14-47.7%
nn.n% — How the model compares to the GPT-4.

Mixtral 8x7b MonsterInstruct Parameters and Internals

LLM NameMixtral 8x7b MonsterInstruct
RepositoryOpen on 🤗 
Base Model(s)  mistralai/Mixtral-8x7B-v0.1   mistralai/Mixtral-8x7B-v0.1
Required VRAM1 GB
Updated2024-07-27
MaintainerZangs3011
Model Files  1.0 GB
Model ArchitectureAdapter
Licenseapache-2.0
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token</s>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesw3|o_proj|w1|w2|q_proj|k_proj|v_proj
LoRA Alpha32
LoRA Dropout0
R Param16
Mixtral 8x7b MonsterInstruct (Zangs3011/mixtral_8x7b_MonsterInstruct)

Best Alternatives to Mixtral 8x7b MonsterInstruct

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Tot Llama Update0.30K / 0 GB15360
CodeHAWK0.30K / 0 GB90
Zephyr Phi 1 5 Sft Qlora0.30K / 0 GB50
Phi Openllm Lb Test0.30K / 0 GB50
Hua V0.10.30K / 0 GB100
Cap Iaa Lora Attn0.30K / 0.2 GB320
...uu Lora Pretrain V3.17193385290.20K / 0.6 GB280
Absa 10 Domains Large0.20K / 0.1 GB190
...uu Lora Pretrain V3.17193397920.20K / 0.3 GB150
Dreamtobenlpsama Mnlp M30.20K / 0 GB480
Note: green Score (e.g. "73.2") means that the model is better than Zangs3011/mixtral_8x7b_MonsterInstruct.

Rank the Mixtral 8x7b MonsterInstruct 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? 34446 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 v2024072501
  Support LLM Explorer