SQAA Instruct Phi3 V1 Merged by JohnDoe70

 ยป  All LLMs  ยป  JohnDoe70  ยป  SQAA Instruct Phi3 V1 Merged   URL Share it on

  Arxiv:1910.09700   Autotrain compatible   Conversational   Custom code   Endpoints compatible   Instruct   Onnx   Phi3   Region:us   Safetensors   Sharded   Tensorflow

Rank the SQAA Instruct Phi3 V1 Merged 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  
SQAA Instruct Phi3 V1 Merged (JohnDoe70/SQAA_Instruct_Phi3_v1_merged)

Best Alternatives to SQAA Instruct Phi3 V1 Merged

Best Alternatives
HF Rank
Phi 3 Mini 4K Instruct V0.370.264K / 7.7 GB11459
Phi 3 Mini 4K Instruct69.914K / 7.7 GB901038720
Phi 3 Mini 4K Instruct V0.269.784K / 7.7 GB3572
Phi3 4K69.64K / 7.7 GB590
Phi 3 Mini 4K Instruct V0.169.574K / 7.7 GB3641
Phi 3 Mini 128K Instruct68.07128K / 7.7 GB10656421354
...hi 3 Medical Instruct Themanas128K / 4 GB2491
Phi Marketing128K / 7.6 GB8021
...i 3 Mini 128K Function Calling128K / 7.6 GB981
... Sft Mathinstruct Lima Partial128K / 7.6 GB130
Note: green Score (e.g. "73.2") means that the model is better than JohnDoe70/SQAA_Instruct_Phi3_v1_merged.

SQAA Instruct Phi3 V1 Merged Parameters and Internals

LLM NameSQAA Instruct Phi3 V1 Merged
RepositoryOpen on ๐Ÿค— 
Model Size3.8b
Required VRAM7.7 GB
Model Typephi3
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Model ArchitecturePhi3ForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.41.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32064
Initializer Range0.02
Torch Data Typebfloat16
Embedding Dropout0

What open-source LLMs or SLMs are you in search of? 34902 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801