LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Synatra 7B V0.3 Base AWQ by TheBloke

What open-source LLMs or SLMs are you in search of? 18732 in total.

 ยป  All LLMs  ยป  TheBloke  ยป  Synatra 7B V0.3 Base AWQ   URL Share it on

  4-bit   Autotrain compatible   Awq Base model:maywell/synatra-7b-...   Conversational   Ko   License:cc-by-nc-4.0   Mistral   Quantized   Region:us   Safetensors

Rank the Synatra 7B V0.3 Base AWQ 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  
Synatra 7B V0.3 Base AWQ (TheBloke/Synatra-7B-v0.3-base-AWQ)

Best Alternatives to Synatra 7B V0.3 Base AWQ

Best Alternatives
HF Rank
Ogno Monarch Jaskier Merge 7B76.4332K / 14.5 GB592
Jaskier 7B DPO V5.676.4132K / 14.4 GB3027
Jaskier 7B DPO V6.176.3632K / 14.4 GB210
OGNO 7B76.3432K / 14.4 GB103611
Omningotex 7B Slerp76.3332K / 14.4 GB6123
StrangeMerges 25 7B Dare Ties76.3332K / 14.4 GB1200
DPO Binarized NeutrixOmnibe 7B76.3132K / 14.4 GB5342
OgnoMonarch 7B76.332K / 14.5 GB1680
StrangeMerges 21 7B Slerp76.2932K / 14.4 GB6580
Monarch 7B76.2532K / 14.4 GB8495
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Synatra-7B-v0.3-base-AWQ.

Synatra 7B V0.3 Base AWQ Parameters and Internals

LLM NameSynatra 7B V0.3 Base AWQ
RepositoryOpen on ๐Ÿค— 
Model NameSynatra 7B v0.3 Base
Model CreatorJeonghwan Park
Base Model(s)  Synatra 7B V0.3 Base   maywell/Synatra-7B-v0.3-base
Model Size7b
Required VRAM4.2 GB
Model Typemistral
Model Files  4.2 GB
Supported Languagesko
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Initializer Range0.02
Torch Data Typefloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003