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 Gptq by ewof

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

  4   
  4bit   Autotrain compatible Dataset:ewof/koishi-instruct-m...   Endpoints compatible   Gptq   Instruct   Llama   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/ewof/koishi-120b-qlora-gptq 

Koishi 120B Qlora Gptq Benchmarks

LLME Score: 0.15023
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 Gptq (ewof/koishi-120b-qlora-gptq)

Koishi 120B Qlora Gptq Parameters and Internals

Training Details 
Data Sources:
ewof/koishi-instruct-metharme
Methodology:
Trained on prompts using roles denoted by tokens: '<|system|>', '<|user|>', and '<|model|>'.
Context Length:
2048
Hardware Used:
8x Nvidia A100 GPU cluster
LLM NameKoishi 120B Qlora Gptq
Repository 🤗https://huggingface.co/ewof/koishi-120b-qlora-gptq 
Base Model(s)  Koishi 120B Qlora   ewof/koishi-120b-qlora
Model Size120b
Required VRAM59.8 GB
Updated2025-02-05
Maintainerewof
Model Typellama
Instruction-BasedYes
Model Files  10.0 GB: 1-of-6   9.9 GB: 2-of-6   10.0 GB: 3-of-6   10.0 GB: 4-of-6   10.0 GB: 5-of-6   9.9 GB: 6-of-6
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.35.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32003
Torch Data Typefloat16

Best Alternatives to Koishi 120B Qlora Gptq

Best Alternatives
Context / RAM
Downloads
Likes
MegaDolphin 120B GPTQ4K / 61.1 GB154
...t 120B Cat A Llama EXL2 5.5bpw8K / 85.3 GB80
...t 120B Cat A Llama EXL2 4.5bpw8K / 70.3 GB71
...egaDolphin 120B 2.9bpw H6 EXL24K / 44.3 GB63
...gaDolphin 120B 2.65bpw H6 EXL24K / 40.5 GB52
...egaDolphin 120B 4.0bpw H6 EXL24K / 60.8 GB31
Meta Llama 3 225B Instruct8K / 443.2 GB718
...ma 3 Instruct 120B Cat A Llama8K / 243.9 GB171
...0B Instruct Abliterated Merged8K / 243.7 GB41
MegaDolphin 120B AWQ4K / 63.3 GB1172
Note: green Score (e.g. "73.2") means that the model is better than ewof/koishi-120b-qlora-gptq.

Rank the Koishi 120B Qlora Gptq 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? 42577 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 v20241227
  Support LLM Explorer