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

MegaDolphin 120B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  MegaDolphin 120B AWQ   URL Share it on

  168   
  Merged Model   4-bit   Autotrain compatible   Awq Base model:cognitivecomputatio... Base model:quantized:cognitive...   Conversational   Dataset:ehartford/dolphin Dataset:ehartford/samantha-dat... Dataset:ehartford/wizardlm evo... Dataset:jondurbin/airoboros-2....   En   Instruct   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow

MegaDolphin 120B AWQ Benchmarks

LLME Score: 0.19072
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

MegaDolphin 120B AWQ Parameters and Internals

LLM NameMegaDolphin 120B AWQ
Repository 🤗https://huggingface.co/TheBloke/MegaDolphin-120b-AWQ 
Model NameMegadolphin 120B
Model CreatorCognitive Computations
Base Model(s)  MegaDolphin 120B   cognitivecomputations/MegaDolphin-120b
Merged ModelYes
Model Size120b
Required VRAM63.3 GB
Updated2024-09-16
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  9.9 GB: 1-of-7   9.9 GB: 2-of-7   9.9 GB: 3-of-7   10.0 GB: 4-of-7   9.9 GB: 5-of-7   9.9 GB: 6-of-7   3.8 GB: 7-of-7
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typefloat16
MegaDolphin 120B AWQ (TheBloke/MegaDolphin-120b-AWQ)

Best Alternatives to MegaDolphin 120B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...t 120B Cat A Llama EXL2 5.5bpw8K / 85.3 GB3080
...t 120B Cat A Llama EXL2 4.5bpw8K / 70.3 GB11
...egaDolphin 120B 2.9bpw H6 EXL24K / 44.3 GB23
...gaDolphin 120B 2.65bpw H6 EXL24K / 40.5 GB52
...egaDolphin 120B 4.0bpw H6 EXL24K / 60.8 GB41
Meta Llama 3 225B Instruct8K / 443.2 GB118
...ma 3 Instruct 120B Cat A Llama8K / 243.9 GB11
...0B Instruct Abliterated Merged8K / 243.7 GB11
MegaDolphin 120B GPTQ4K / 61.1 GB74
Koishi 120B Qlora Gptq4K / 9.9 GB61
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/MegaDolphin-120b-AWQ.

Rank the MegaDolphin 120B AWQ 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? 35926 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 v2024072803
  Support LLM Explorer