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

Kiqu 70B AWQ by maywell

 »  All LLMs  »  maywell  »  Kiqu 70B AWQ   URL Share it on

  13   
  4-bit   Autotrain compatible   Awq   Conversational   En   Endpoints compatible   Ko   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/maywell/kiqu-70b-awq 

Kiqu 70B AWQ Benchmarks

LLME Score: 0.17552
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kiqu 70B AWQ (maywell/kiqu-70b-awq)

Kiqu 70B AWQ Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, education
Applications:
chatbots, language translation
Primary Use Cases:
Korean language processing, conversion for chat applications
Considerations:
Few-shot usage is highly recommended and trailing spaces in instruction format should be avoided.
Additional Notes 
This is an early leaked version. Commercial usage is risky.
Supported Languages 
Korean (high), English (medium)
Training Details 
Data Sources:
Korean datasets
Methodology:
SFT+DPO training based on Miqu-70B-Alpaca-DPO
Model Architecture:
Follows Mistral format
Input Output 
Input Format:
[INST] {instruction} [/INST] {output}
Accepted Modalities:
text
Output Format:
text responses
Performance Tips:
Avoid trailing spaces after [/INST] to maintain performance.
LLM NameKiqu 70B AWQ
Repository 🤗https://huggingface.co/maywell/kiqu-70b-awq 
Model Size70b
Required VRAM36.7 GB
Updated2024-12-22
Maintainermaywell
Model Typellama
Model Files  5.0 GB: 1-of-8   5.0 GB: 2-of-8   4.9 GB: 3-of-8   4.9 GB: 4-of-8   4.9 GB: 5-of-8   4.9 GB: 6-of-8   4.9 GB: 7-of-8   2.2 GB: 8-of-8
Supported Languagesko en
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensecc-by-sa-4.0
Context Length32764
Model Max Length32764
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Kiqu 70B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...0B Instruct Gradient 1048K AWQ1024K / 39.9 GB121
...70B Instruct Gradient 262K AWQ256K / 39.9 GB110
Llama 3.3 70B Instruct AWQ128K / 39.9 GB2044518
...lama 3.3 70B Instruct AWQ INT4128K / 39.9 GB751010
... SauerkrautLM 70B Instruct AWQ128K / 39.9 GB16024
MultiVerse 70B AWQ32K / 41.3 GB932
Opus V1.2 70B AWQ32K / 36.7 GB231
QuartetAnemoi 70B T0.0001 AWQ31K / 36.7 GB131
Senku 70B AWQ 4bit GEMM31K / 36.7 GB131
CodeLlama 70B Hf AWQ16K / 36.6 GB184
Note: green Score (e.g. "73.2") means that the model is better than maywell/kiqu-70b-awq.

Rank the Kiqu 70B 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? 40123 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 v20241217
  Support LLM Explorer