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

WestLake 10.7B V2 EXL2 8.0 by StopTryharding

 »  All LLMs  »  StopTryharding  »  WestLake 10.7B V2 EXL2 8.0   URL Share it on

  6   
  Merged Model   8-bit   Autotrain compatible Base model:quantized:senseable... Base model:senseable/westlake-...   En   Endpoints compatible   Exl2   Mistral   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/StopTryharding/WestLake-10.7B-v2-exl2-8.0 

WestLake 10.7B V2 EXL2 8.0 Benchmarks

LLME Score: 0.17375
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
WestLake 10.7B V2 EXL2 8.0 (StopTryharding/WestLake-10.7B-v2-exl2-8.0)

WestLake 10.7B V2 EXL2 8.0 Parameters and Internals

Model Type 
Role-Play, Text Generation
Use Cases 
Areas:
Creative Writing, Education, Gaming, Customer Support, Social Media
Applications:
Generating new ideas for authors, Enhancing language learning platforms, Dynamic NPC interactions in games, Creating advanced chatbots, Social media content generation
Additional Notes 
The model includes enhancements for a better writing style and is part of a self-merge project after multiple testing rounds.
Supported Languages 
English (High Proficiency)
Training Details 
Data Sources:
Vast corpus of diverse texts
Methodology:
Passthrough merge method with mergekit
Context Length:
8192
Training Time:
Trained for 3 epochs
Input Output 
Input Format:
Alpaca, ChatML, Mistral Instruct, Zephyr
Accepted Modalities:
Text
Output Format:
Text
Performance Tips:
Use recommended prompt formats for optimal results.
Release Notes 
Version:
2.0
Notes:
Trained for 1 additional epoch cycle for 3 total.
LLM NameWestLake 10.7B V2 EXL2 8.0
Repository 🤗https://huggingface.co/StopTryharding/WestLake-10.7B-v2-exl2-8.0 
Base Model(s)  WestLake 7B V2   senseable/WestLake-7B-v2
Merged ModelYes
Model Size7b
Required VRAM10.8 GB
Updated2025-02-05
MaintainerStopTryharding
Model Typemistral
Model Files  8.6 GB: 1-of-2   2.2 GB: 2-of-2
Supported Languagesen
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to WestLake 10.7B V2 EXL2 8.0

Best Alternatives
Context / RAM
Downloads
Likes
...al Nemo Instruct 2407 Bnb 4bit1000K / 8.3 GB1367427
...istral Nemo Base 2407 Bnb 4bit1000K / 8.3 GB749214
...t 3.5 0106 128K 8.0bpw H8 EXL2128K / 7.4 GB61
...t 3.5 0106 128K 4.0bpw H6 EXL2128K / 3.9 GB51
...tral 7B Instruct V0.3 Bnb 4bit32K / 4.1 GB8294918
Mistral 7B Sci Pretrain32K / 4.1 GB5120
Mistral 7B V0.3 Bnb 4bit32K / 4.1 GB2635015
Mistral 7B Instruct V0.2 Fp1632K / 14.4 GB260
Mistral 7B Instruct V0.2 4bit32K / 4.3 GB2901
...tral 7B Instruct V0.2 Bnb 4bit32K / 4.1 GB1177032
Note: green Score (e.g. "73.2") means that the model is better than StopTryharding/WestLake-10.7B-v2-exl2-8.0.

Rank the WestLake 10.7B V2 EXL2 8.0 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