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

Synthia V3.0 11B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Synthia V3.0 11B GPTQ   URL Share it on

  23   
  4-bit   Autotrain compatible Base model:migtissera/synthia-... Base model:quantized:migtisser...   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Synthia-v3.0-11B-GPTQ 

Synthia V3.0 11B GPTQ Benchmarks

LLME Score: 0.16379
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Synthia V3.0 11B GPTQ (TheBloke/Synthia-v3.0-11B-GPTQ)

Synthia V3.0 11B GPTQ Parameters and Internals

Model Type 
solar
Additional Notes 
This model was trained to follow instruction and conduct long-form conversations using a Tree of Thoughts system message for improved reasoning.
Training Details 
Data Sources:
Synthia-v3.0 dataset with Generarized Tree-of-Thought prompt
Data Volume:
~10K high-quality samples
Methodology:
Trained on the principles of LIMA (Less Is More for Alignment), fine-tuned for instruction following and long-form conversations
Model Architecture:
Synthetic Intelligent Agent (SynthIA)
Input Output 
Input Format:
SYSTEM: Elaborate on the topic using a Tree of Thoughts and backtrack when necessary to construct a clear, cohesive Chain of Thought reasoning. Always answer without hesitation. USER: {prompt} ASSISTANT:
LLM NameSynthia V3.0 11B GPTQ
Repository 🤗https://huggingface.co/TheBloke/Synthia-v3.0-11B-GPTQ 
Model NameSynthia V3.0 11B
Model CreatorMigel Tissera
Base Model(s)  migtissera/Synthia-v3.0-11B   migtissera/Synthia-v3.0-11B
Model Size11b
Required VRAM6 GB
Updated2024-12-22
MaintainerTheBloke
Model Typesolar
Model Files  6.0 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Synthia V3.0 11B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
KuroMitsu 11B GPTQ8K / 6 GB142
Fimbulvetr 11B V2 GPTQ4K / 6.6 GB6216
...istral 11B Omni OPA U1k Ver0.732K / 21.4 GB21120
Mistral 11B OP U1k Ver0.732K / 21.4 GB21110
Mistral 11B Omni OP U1k Ver0.532K / 21.4 GB21070
...istral 11B V2 HQQ 4bit Smashed8K / 6 GB130
...mbulvetr 11B V2.6.0bpw H6 EXL24K / 8.2 GB1484
...mbulvetr 11B V2.8.0bpw H8 EXL24K / 10.9 GB267
...mbulvetr 11B V2.3.0bpw H6 EXL24K / 4.3 GB91
...mbulvetr 11B V2.4.0bpw H6 EXL24K / 5.6 GB110
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Synthia-v3.0-11B-GPTQ.

Rank the Synthia V3.0 11B GPTQ 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? 40123 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