Phi3 History V2 by ambrosfitz

 ยป  All LLMs  ยป  ambrosfitz  ยป  Phi3 History V2   URL Share it on

  4bit   Autotrain compatible   Conversational Dataset:ambrosfitz/10k history...   Endpoints compatible   Instruct   Mistral   Phi3   Pytorch   Quantized   Region:us   Sft   Sharded   Trl   Unsloth

Phi3 History V2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Phi3 History V2 Parameters and Internals

LLM NamePhi3 History V2
Repository ๐Ÿค—https://huggingface.co/ambrosfitz/phi3_history_v2 
Required VRAM7.6 GB
Updated2024-09-07
Maintainerambrosfitz
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typefloat16
Phi3 History V2 (ambrosfitz/phi3_history_v2)

Best Alternatives to Phi3 History V2

Best Alternatives
Context / RAM
Downloads
Likes
... Mini 4K Instruct Bnb 4bit Ita4K / 7.6 GB22650
...ini New Model With Lora Merged4K / 7.6 GB50
Phired4K / 7.6 GB50
Phi 3 Mini Hospital Topic 504K / 7.6 GB50
Model4K / 7.6 GB50
MainPHI34K / 7.6 GB50
Model4K / 7.6 GB50
Phi3 Finetune Test4K / 7.6 GB60
MediChat Revision4K / 7.6 GB60
Phi3 Lora Unsloth4K / 7.6 GB60
Note: green Score (e.g. "73.2") means that the model is better than ambrosfitz/phi3_history_v2.

Rank the Phi3 History V2 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? 36966 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803