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

Neural Chat 7B V3.1 by Intel

 »  All LLMs  »  Intel  »  Neural Chat 7B V3.1   URL Share it on

  152797   
  Arxiv:2306.02707   Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   Conversational   Dataset:open-orca/slimorca   En   Endpoints compatible   Finetuned   Intel   Lora   Mistral   Model-index   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Intel/neural-chat-7b-v3-1 

Neural Chat 7B V3.1 Benchmarks

MMLU Pro: 18.64
GPQA: 5.37
MUSR: 22.24
BBH: 29.74
IFEval: 46.87 vs 88 (so35)-46.7%
ARC: 64.25 vs 96.7 (so35)-33.6%
HellaSwag: 82.49 vs 95.3 (gpt4)-13.4%
MMLU: 60.79 vs 88.3 (so35)-31.2%
TruthfulQA: 56.4 vs 59 (gpt4)-4.4%
WinoGrande: 77.35 vs 87.5 (gpt4)-11.6%
GSM8K: 18.12 vs 96.4 (so35)-81.2%
MATH Lvl 5: 3.55
LLME Score: 0.33395
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Neural Chat 7B V3.1 (Intel/neural-chat-7b-v3-1)

Neural Chat 7B V3.1 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
language-related tasks
Limitations:
The model may generate biased or offensive content., The model needs fine-tuning for specific tasks.
Additional Notes 
The model is part of Intel's initiative for advancements in neural chat technologies.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
Open-Orca/SlimOrca
Methodology:
Direct Performance Optimization (DPO)
Context Length:
8192
Hardware Used:
Intel Gaudi 2 processor
Safety Evaluation 
Ethical Considerations:
Neural-chat-7b-v3-1 can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
Responsible Ai Considerations 
Fairness:
Mitigation strategies should be implemented to address potential lewd, biased, or offensive outputs.
Accountability:
Developers should perform safety testing before deploying any applications of neural-chat-7b-v3-1.
Input Output 
Input Format:
text input with context length 8192 tokens
Accepted Modalities:
text
Output Format:
text
Release Notes 
Version:
v3-1
Date:
October, 2023
Notes:
Improved performance metrics and finetuning with Open-Orca/SlimOrca
LLM NameNeural Chat 7B V3.1
Repository 🤗https://huggingface.co/Intel/neural-chat-7b-v3-1 
Base Model(s)  mistralai/Mistral-7B-v0.1   mistralai/Mistral-7B-v0.1
Model Size7b
Required VRAM14.4 GB
Updated2025-02-22
MaintainerIntel
Model Typemistral
Model Files  9.9 GB: 1-of-2   4.5 GB: 2-of-2   9.9 GB: 1-of-2   4.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
LoRA ModelYes
Torch Data Typefloat16

Quantized Models of the Neural Chat 7B V3.1

Model
Likes
Downloads
VRAM
Neural Chat 7B V3.1 AWQ428594 GB
Neural Chat 7B V3.1 GGUF5815563 GB
Neural Chat 7B V3.1 GGUF01752 GB
Neural Chat 7B V3.1 GGUF03452 GB
Neural Chat 7B V3.1 GPTQ7614 GB

Best Alternatives to Neural Chat 7B V3.1

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB462011
MegaBeam Mistral 7B 512K512K / 14.4 GB568150
SpydazWeb AI HumanAI RP512K / 14.4 GB121
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB563316
Hebrew Mistral 7B 200K256K / 30 GB1461915
Astral 256K 7B V2250K / 14.4 GB70
Astral 256K 7B250K / 14.4 GB50
Test001128K / 14.5 GB90

Rank the Neural Chat 7B V3.1 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? 43470 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