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

UNA SOLAR 10.7B Instruct V1.0 by fblgit

 »  All LLMs  »  fblgit  »  UNA SOLAR 10.7B Instruct V1.0   URL Share it on

  132   
  Alignment-handbook   Autotrain compatible Base model:quantized:upstage/s... Base model:upstage/solar-10.7b...   Conversational   Doi:10.57967/hf/1514   En   Endpoints compatible   Generated from trainer   Ggml   Gguf   Instruct   Llama   Q5   Quantized   Region:us   Safetensors   Sharded   Single-turn   Tensorflow   Una
Model Card on HF 🤗: https://huggingface.co/fblgit/UNA-SOLAR-10.7B-Instruct-v1.0 

UNA SOLAR 10.7B Instruct V1.0 Benchmarks

ARC: 70.73 vs 96.7 (so35)-26.9%
HellaSwag: 88.32 vs 95.3 (gpt4)-7.3%
MMLU: 66.1 vs 88.3 (so35)-25.1%
TruthfulQA: 72.52 vs 59 (gpt4)22.9%
WinoGrande: 83.35 vs 87.5 (gpt4)-4.7%
GSM8K: 63.38 vs 96.4 (so35)-34.3%
LLME Score: 0.13634
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
UNA SOLAR 10.7B Instruct V1.0 (fblgit/UNA-SOLAR-10.7B-Instruct-v1.0)
🌟 Advertise your project 🚀

UNA SOLAR 10.7B Instruct V1.0 Parameters and Internals

Model Type 
single-turn
Additional Notes 
This model, UNA-SOLAR-10.7B-Instruct-v1.0, is an alignment-oriented SFT (Supervised Fine-Tuning) model that builds on the SOLAR base model by incorporating unique tuning layers, allowing for improved regularization and customization.
Supported Languages 
English (Proficient)
Training Details 
Model Architecture:
SFT Further with Linear adjustments and Fan in/out modifications
LLM NameUNA SOLAR 10.7B Instruct V1.0
Repository 🤗https://huggingface.co/fblgit/UNA-SOLAR-10.7B-Instruct-v1.0 
Base Model(s)  upstage/SOLAR-10.7B-Instruct-v1.0   upstage/SOLAR-10.7B-Instruct-v1.0
Model Size10.7b
Required VRAM21.4 GB
Updated2025-09-23
Maintainerfblgit
Model Typellama
Instruction-BasedYes
Model Files  7.6 GB   8.8 GB   4.9 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   1.7 GB: 5-of-5
Supported Languagesen
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typeggml|q5|gguf|q5_k
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-nd-4.0
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to UNA SOLAR 10.7B Instruct V1.0

Best Alternatives
Context / RAM
Downloads
Likes
SOLAR 10.7B Instruct V1.0 GGUF4K / 4.5 GB12232
...ndle SOLAR 10.7B Instruct V1.04K / 21.4 GB340
... 10.7B Instruct V1.0 128K EXL2128K / 5.6 GB31
Eclectus 1.1 Dedup4K / 21.4 GB1030
Eclectus1.14K / 21.4 GB60
Solar 10.7B SLERP EXL24K / 5.6 GB84
...Instruct V1.0 6.0bpw H6 EXL2 24K / 8.2 GB72
...Instruct V1.0 8.0bpw H8 EXL2 24K / 10.8 GB71
...Instruct V1.0 3.0bpw H6 EXL2 24K / 4.3 GB70
SOLAR 10.7B Instruct V1.0 128K128K / 21.4 GB54
Note: green Score (e.g. "73.2") means that the model is better than fblgit/UNA-SOLAR-10.7B-Instruct-v1.0.

Rank the UNA SOLAR 10.7B Instruct V1.0 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? 51544 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 v20241124
  Support LLM Explorer