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

Quintellect 10.7B by Walmart-the-bag

 »  All LLMs  »  Walmart-the-bag  »  Quintellect 10.7B   URL Share it on

  90   
  Autotrain compatible   Code   Conversational Dataset:sahil2801/codealpaca-2...   En   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Walmart-the-bag/Quintellect-10.7B 

Quintellect 10.7B Benchmarks

ARC: 65.02 vs 96.7 (so35)-32.8%
HellaSwag: 84.48 vs 95.3 (gpt4)-11.4%
MMLU: 63.28 vs 88.3 (so35)-28.3%
TruthfulQA: 59.57 vs 59 (gpt4)1%
WinoGrande: 79.01 vs 87.5 (gpt4)-9.7%
GSM8K: 60.58 vs 96.4 (so35)-37.2%
LLME Score: 0.19905
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Quintellect 10.7B (Walmart-the-bag/Quintellect-10.7B)

Quintellect 10.7B Parameters and Internals

Model Type 
code generation
Use Cases 
Areas:
coding knowledge accessibility
Primary Use Cases:
coding assistance, code generation
Additional Notes 
This model is designed for coding tasks, specifically for languages like Python and JavaScript. It's beneficial for both standard programming tasks and code creation from scratch.
Supported Languages 
en (proficient)
Input Output 
Input Format:
Alpaca prompt format
Accepted Modalities:
text
Output Format:
text response
LLM NameQuintellect 10.7B
Repository 🤗https://huggingface.co/Walmart-the-bag/Quintellect-10.7B 
Model Size10.7b
Required VRAM21.4 GB
Updated2024-12-22
MaintainerWalmart-the-bag
Model Typemistral
Model Files  6.0 GB: 1-of-4   5.9 GB: 2-of-4   6.0 GB: 3-of-4   3.5 GB: 4-of-4
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Quintellect 10.7B

Best Alternatives
Context / RAM
Downloads
Likes
PiVoT 10.7B Mistral V0.232K / 21.4 GB51545
Barely Regal 10.7B32K / 21.5 GB190
Chikuma 10.7B32K / 21.4 GB3015
Multi Verse Model 10.7B32K / 21.5 GB171
PrimaSumika 10.7B 128K32K / 21.5 GB261
Longcat 10.7B32K / 21.5 GB233
PiVoT 10.7B Mistral V0.2 RP32K / 21.4 GB7207
... Loyal Mistral Maid 32K V0.2 A32K / 21.5 GB291
Chikuma 10.7B V232K / 21.4 GB2221
Mark1 Revision 10.7B32K / 42.9 GB181
Note: green Score (e.g. "73.2") means that the model is better than Walmart-the-bag/Quintellect-10.7B.

Rank the Quintellect 10.7B 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? 40066 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