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

Kuchiki L2 7B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Kuchiki L2 7B AWQ   URL Share it on

  6   
  4-bit   Autotrain compatible   Awq Base model:quantized:zarakique... Base model:zarakiquemparte/kuc...   Llama   Llama2   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Kuchiki-L2-7B-AWQ 

Kuchiki L2 7B AWQ Benchmarks

LLME Score: 0.10903
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kuchiki L2 7B AWQ (TheBloke/Kuchiki-L2-7B-AWQ)
🌟 Advertise your project 🚀

Kuchiki L2 7B AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
research, commercial applications
Limitations:
This model is not intended for supplying factual information or advice in any form
Additional Notes 
The model has been quantized using TheBloke's AWQ and GPTQ, providing options for GPU and CPU inference.
Training Details 
Data Sources:
Nous Hermes Llama2 7b, Airoboros L2 7B GPT4 2.0
Methodology:
The model is a merge of Nous Hermes and Airoboros models, using specific scripts (e.g., merge-cli.py). It also integrates LimaRP LLama2 7B Lora, applied via another script (apply-lora.py).
Model Architecture:
The model architecture involves merging Nous Hermes, Airoboros, and LimaRP Lora models into a single enhanced model.
Input Output 
Input Format:
Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response:
Release Notes 
Notes:
The model is a merge of Nous Hermes, Airoboros, and LimaRP LLama2, quantized by TheBloke, and available in different quantization formats.
LLM NameKuchiki L2 7B AWQ
Repository 🤗https://huggingface.co/TheBloke/Kuchiki-L2-7B-AWQ 
Model NameKuchiki L2 7B
Model CreatorZaraki Quem Parte
Base Model(s)  Kuchiki L2 7B   zarakiquemparte/kuchiki-l2-7b
Model Size7b
Required VRAM3.9 GB
Updated2025-09-23
MaintainerTheBloke
Model Typellama
Model Files  3.9 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Kuchiki L2 7B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Smaugv0.1 AWQ195K / 19.3 GB61
Yarn Llama 2 7B 64K AWQ64K / 3.9 GB370
Calm2 7B Chat AWQ32K / 4.4 GB141
Llama 2 7B 32K Instruct AWQ32K / 3.9 GB102
... SWE Llama 7B Updated 4bit AWQ16K / 3.9 GB50
CodeLlama 7B Instruct AWQ16K / 3.9 GB12794
...Llama 7B Python Hf W4 G128 AWQ16K / 3.9 GB12320
Pandalyst 7B V1.2 AWQ16K / 3.9 GB61
Tora Code 7B V1.0 AWQ16K / 3.9 GB80
...eechless Tora Code 7B V1.0 AWQ16K / 3.9 GB61
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Kuchiki-L2-7B-AWQ.

Rank the Kuchiki L2 7B 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? 51538 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 v20241124
  Support LLM Explorer