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

Koishi 120B Qlora by ewof

 »  All LLMs  »  ewof  »  Koishi 120B Qlora   URL Share it on

  6   
  Autotrain compatible Dataset:ewof/koishi-instruct-m...   Endpoints compatible   Instruct   Llama   Pytorch   Region:us   Sharded

Koishi 120B Qlora Benchmarks

LLME Score: 0.17125
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Koishi 120B Qlora Parameters and Internals

LLM NameKoishi 120B Qlora
Repository 🤗https://huggingface.co/ewof/koishi-120b-qlora 
Model Size120b
Required VRAM216.9 GB
Updated2024-09-18
Maintainerewof
Model Typellama
Instruction-BasedYes
Model Files  4.7 GB: 1-of-50   4.7 GB: 2-of-50   5.0 GB: 3-of-50   5.0 GB: 4-of-50   4.7 GB: 5-of-50   4.7 GB: 6-of-50   4.7 GB: 7-of-50   5.0 GB: 8-of-50   5.0 GB: 9-of-50   4.7 GB: 10-of-50   4.7 GB: 11-of-50   4.7 GB: 12-of-50   5.0 GB: 13-of-50   5.0 GB: 14-of-50   4.7 GB: 15-of-50   4.7 GB: 16-of-50   4.7 GB: 17-of-50   5.0 GB: 18-of-50   5.0 GB: 19-of-50   4.7 GB: 20-of-50   4.7 GB: 21-of-50   4.7 GB: 22-of-50   5.0 GB: 23-of-50   5.0 GB: 24-of-50   4.7 GB: 25-of-50   4.7 GB: 26-of-50   4.7 GB: 27-of-50   5.0 GB: 28-of-50   5.0 GB: 29-of-50   4.7 GB: 30-of-50   4.7 GB: 31-of-50   4.7 GB: 32-of-50   5.0 GB: 33-of-50   5.0 GB: 34-of-50   4.7 GB: 35-of-50   4.7 GB: 36-of-50   4.7 GB: 37-of-50   5.0 GB: 38-of-50   5.0 GB: 39-of-50   4.7 GB: 40-of-50   4.7 GB: 41-of-50   4.7 GB: 42-of-50   5.0 GB: 43-of-50   5.0 GB: 44-of-50   4.7 GB: 45-of-50
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.35.1
Vocabulary Size32003
Torch Data Typefloat16
Koishi 120B Qlora (ewof/koishi-120b-qlora)

Quantized Models of the Koishi 120B Qlora

Model
Likes
Downloads
VRAM
Koishi 120B Qlora Gptq169 GB

Best Alternatives to Koishi 120B Qlora

Best Alternatives
Context / RAM
Downloads
Likes
Meta Llama 3 225B Instruct8K / 443.2 GB218
...ma 3 Instruct 120B Cat A Llama8K / 243.9 GB21
...0B Instruct Abliterated Merged8K / 243.7 GB21
...t 120B Cat A Llama EXL2 5.5bpw8K / 85.3 GB3200
...t 120B Cat A Llama EXL2 4.5bpw8K / 70.3 GB21
...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
MegaDolphin 120B AWQ4K / 63.3 GB1682
MegaDolphin 120B GPTQ4K / 61.1 GB74
Note: green Score (e.g. "73.2") means that the model is better than ewof/koishi-120b-qlora.

Rank the Koishi 120B Qlora 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? 36026 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