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

L3 ChaoticSoliloquy V1.5 4x8B 8bpw H8 EXL2 by JayhC

 »  All LLMs  »  JayhC  »  L3 ChaoticSoliloquy V1.5 4x8B 8bpw H8 EXL2   URL Share it on

  8   
  8-bit   Autotrain compatible   Conversational   En   Endpoints compatible   Exl2   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/JayhC/L3-ChaoticSoliloquy-v1.5-4x8B-8bpw-h8-exl2 

L3 ChaoticSoliloquy V1.5 4x8B 8bpw H8 EXL2 Benchmarks

LLME Score: 0.18598
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
L3 ChaoticSoliloquy V1.5 4x8B 8bpw H8 EXL2 (JayhC/L3-ChaoticSoliloquy-v1.5-4x8B-8bpw-h8-exl2)

L3 ChaoticSoliloquy V1.5 4x8B 8bpw H8 EXL2 Parameters and Internals

Model Type 
MoE, RP-oriented
Additional Notes 
Experimental RP-oriented MoE, aimed to improve RP/ERP tasks.
Training Details 
Methodology:
exl2 quantization using default exllamav2 calibration dataset
Model Architecture:
MoE with experts per token = 2 and gate mode = random
Input Output 
Input Format:
Prompt format: Llama 3
LLM NameL3 ChaoticSoliloquy V1.5 4x8B 8bpw H8 EXL2
Repository 🤗https://huggingface.co/JayhC/L3-ChaoticSoliloquy-v1.5-4x8B-8bpw-h8-exl2 
Model Size8b
Required VRAM25.3 GB
Updated2025-02-05
MaintainerJayhC
Model Typemixtral
Model Files  8.5 GB: 1-of-3   8.6 GB: 2-of-3   8.2 GB: 3-of-3
Supported Languagesen
Quantization Typeexl2
Model ArchitectureMixtralForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.37.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|begin_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to L3 ChaoticSoliloquy V1.5 4x8B 8bpw H8 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...Storm V1.15 4x8B B 8 0bpw EXL28K / 25.2 GB50
... SnowStorm 4x8B 6.5bpw H8 EXL28K / 21 GB42
L3 SnowStorm 4x8B 8bpw H8 EXL28K / 25.2 GB51
...oquy V2 4x8B Test 8bpw H8 EXL28K / 24.9 GB91
...loquy V1.5 4x8B 6.5bpw H8 EXL28K / 21 GB62
...oquy 4x8B Bpw600 H6 EXL2 Rpcal8K / 19.4 GB52
...oquy 4x8B Bpw800 H8 EXL2 Rpcal8K / 25.3 GB61
...ticSoliloquy 4x8B 6bpw H6 EXL28K / 19.4 GB53
...oquy 4x8B Bpw500 H6 EXL2 Rpcal8K / 16.4 GB51
...ticSoliloquy 4x8B 8bpw H8 EXL28K / 25.3 GB43
Note: green Score (e.g. "73.2") means that the model is better than JayhC/L3-ChaoticSoliloquy-v1.5-4x8B-8bpw-h8-exl2.

Rank the L3 ChaoticSoliloquy V1.5 4x8B 8bpw H8 EXL2 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