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

Freeze KoSoLAR 10.7B V0.2 1.4 Dedup by jingyeom

 ยป  All LLMs  ยป  jingyeom  ยป  Freeze KoSoLAR 10.7B V0.2 1.4 Dedup   URL Share it on

  93   

Freeze KoSoLAR 10.7B V0.2 1.4 Dedup is an open-source language model by jingyeom. Features: 10.7b LLM, VRAM: 43.2GB, Context: 4K, License: apache-2.0, Quantized, HF Score: 60.1, LLM Explorer Score: 0.14, Arc: 58.5, HellaSwag: 81.3, MMLU: 64.8, TruthfulQA: 44.5, WinoGrande: 79.1, GSM8K: 32.2.

  32bit   Conversational   Deploy:azure   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/jingyeom/freeze_KoSoLAR-10.7B-v0.2_1.4_dedup 

Freeze KoSoLAR 10.7B V0.2 1.4 Dedup Benchmarks

ARC: 58.45 vs 96.7 (so35)-39.6%
HellaSwag: 81.26 vs 95.3 (gpt4)-14.7%
MMLU: 64.83 vs 88.3 (so35)-26.6%
TruthfulQA: 44.5 vs 59 (gpt4)-24.6%
WinoGrande: 79.08 vs 87.5 (gpt4)-9.6%
GSM8K: 32.22 vs 96.4 (so35)-66.6%
LLME Score: 0.13776
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Freeze KoSoLAR 10.7B V0.2 1.4 Dedup (jingyeom/freeze_KoSoLAR-10.7B-v0.2_1.4_dedup)
๐ŸŒŸ Advertise your project ๐Ÿš€

Freeze KoSoLAR 10.7B V0.2 1.4 Dedup Parameters and Internals

Model Type 
causal LM
Training Details 
Data Sources:
๊ณต๊ฐœ ๋ฐ์ดํ„ฐ ์ˆ˜์ง‘
Methodology:
instruction Tuning using Deduplicating Training Data Makes Language Models Better algorithm
Model Architecture:
freeze
LLM NameFreeze KoSoLAR 10.7B V0.2 1.4 Dedup
Repository ๐Ÿค—https://huggingface.co/jingyeom/freeze_KoSoLAR-10.7B-v0.2_1.4_dedup 
Model Size10.7b
Required VRAM43.2 GB
Updated2026-04-09
Maintainerjingyeom
Model Typellama
Model Files  4.8 GB: 1-of-9   5.0 GB: 2-of-9   5.0 GB: 3-of-9   4.8 GB: 4-of-9   5.0 GB: 5-of-9   5.0 GB: 6-of-9   4.8 GB: 7-of-9   5.0 GB: 8-of-9   3.8 GB: 9-of-9
Quantization Type32bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size40960
Torch Data Typefloat32

Best Alternatives to Freeze KoSoLAR 10.7B V0.2 1.4 Dedup

Best Alternatives
Context / RAM
Downloads
Likes
... 10.7B Instruct V1.0 128K EXL2128K / 5.6 GB21
KoSoLAR 10.7B V0.2 1.4 Dedup4K / 21.6 GB910
Solar Test 240517 16bit4K / 21.4 GB100
KoSoLAR 10.7B V0.2 1.4 Dedup 14K / 21.6 GB50
Frostwind 10.7B V1 EXL24K / 10.9 GB41
Solar 10.7B Bnb 4bit4K / 5.9 GB103
...ess 10.7B V1.5B 8.0bpw H8 EXL24K / 10.9 GB01
SnowLotus V2.10.7B 3bpw EXL24K / 4.3 GB31
DaringLotus V2.10.7B 3bpw EXL24K / 4.3 GB11
...gLotus V2.10.7B Bpw500 H6 EXL24K / 6.9 GB72
Note: green Score (e.g. "73.2") means that the model is better than jingyeom/freeze_KoSoLAR-10.7B-v0.2_1.4_dedup.

Rank the Freeze KoSoLAR 10.7B V0.2 1.4 Dedup 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? 52721 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.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer