SOLAR 10.7B V1.0 GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  SOLAR 10.7B V1.0 GPTQ   URL Share it on

  4-bit   Autotrain compatible Base model:quantized:upstage/s... Base model:upstage/solar-10.7b...   Gptq   Llama   Quantized   Region:us   Safetensors

SOLAR 10.7B V1.0 GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SOLAR 10.7B V1.0 GPTQ (TheBloke/SOLAR-10.7B-v1.0-GPTQ)

SOLAR 10.7B V1.0 GPTQ Parameters and Internals

Model Type 
solar
Additional Notes 
The model uses Depth Up-Scaling technique and is integrated with Mistral 7B weights for enhanced performance.
Training Details 
Model Architecture:
Built on the Llama2 architecture, incorporating Upstage Depth Up-Scaling and integrated Mistral 7B weights.
Input Output 
Input Format:
{prompt}
LLM NameSOLAR 10.7B V1.0 GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/SOLAR-10.7B-v1.0-GPTQ 
Model NameSolar 10.7B v1.0
Model Creatorupstage
Base Model(s)  upstage/SOLAR-10.7B-v1.0   upstage/SOLAR-10.7B-v1.0
Model Size10.7b
Required VRAM6 GB
Updated2024-12-21
MaintainerTheBloke
Model Typesolar
Model Files  6.0 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to SOLAR 10.7B V1.0 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Tess 10.7B V1.5B GPTQ4K / 6 GB385
Nous Hermes 2 SOLAR 10.7B GPTQ4K / 6 GB3815
Sensualize Solar 10.7B GPTQ4K / 6 GB218
CarbonVillain En 10.7B V4 GPTQ4K / 6 GB152
SOLAR 10.7B Instruct V1.0 GPTQ4K / 6 GB182
LMCocktail 10.7B V1 GPTQ4K / 6 GB142
SOLAR 10.7B Instruct V1.0 GPTQ4K / 6 GB3812
Frostwind 10.7B V1 GPTQ4K / 6 GB202
Solar 10.7B SLERP GPTQ4K / 6 GB243
SOLAR Platypus 10.7B V2 GPTQ4K / 6 GB191
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/SOLAR-10.7B-v1.0-GPTQ.

Rank the SOLAR 10.7B V1.0 GPTQ Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40013 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217