Dj Phi 3 3.8B 16bit by deepanshdj

 ยป  All LLMs  ยป  deepanshdj  ยป  Dj Phi 3 3.8B 16bit   URL Share it on

  16bit   Autotrain compatible Base model:finetune:unsloth/ph... Base model:unsloth/phi-3-mini-...   Conversational   En   Endpoints compatible   Instruct   Mistral   Phi   Phi3   Pytorch   Quantized   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl

Dj Phi 3 3.8B 16bit Benchmarks

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

Dj Phi 3 3.8B 16bit Parameters and Internals

LLM NameDj Phi 3 3.8B 16bit
Repository ๐Ÿค—https://huggingface.co/deepanshdj/dj-phi-3_3.8b-16bit 
Base Model(s)  Phi 3 Mini 4K Instruct   unsloth/Phi-3-mini-4k-instruct
Model Size3.8b
Required VRAM7.6 GB
Updated2024-09-06
Maintainerdeepanshdj
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2   5.0 GB: 1-of-2   2.6 GB: 2-of-2
Supported Languagesen
Quantization Type16bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typefloat16
Dj Phi 3 3.8B 16bit (deepanshdj/dj-phi-3_3.8b-16bit)

Best Alternatives to Dj Phi 3 3.8B 16bit

Best Alternatives
Context / RAM
Downloads
Likes
...Word Problems 200K Model 16bit4K / 7.6 GB51250
...Word Problems 200K Model 16bit4K / 7.6 GB38790
Porpoise14K / 7.6 GB2180
... 4K Instruct Matter 0.1 Slim A4K / 7.6 GB12
Pii Redaction V0.34K / 7.6 GB320
...rser User V9b Epoch 7 Lr 0.0024K / 7.6 GB50
...100 Percent Low Med Perplexity4K / 7.6 GB50
...22 Epoch7 0.002 Nosystemprompt4K / 7.6 GB50
...20 Epoch7 0.002 Nosystemprompt4K / 7.6 GB50
...Af 50 Percent Low Med Nv Embed4K / 7.6 GB50
Note: green Score (e.g. "73.2") means that the model is better than deepanshdj/dj-phi-3_3.8b-16bit.

Rank the Dj Phi 3 3.8B 16bit 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? 35941 in total.

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