Phi 3 Mini 4K Instruct DPO EPFL GPTQ 8bit by StefanKrsteski

 ยป  All LLMs  ยป  StefanKrsteski  ยป  Phi 3 Mini 4K Instruct DPO EPFL GPTQ 8bit   URL Share it on

  Arxiv:1910.09700   8-bit   8bit   Autotrain compatible   Conversational   Custom code   Endpoints compatible   Gptq   Instruct   Phi3   Quantized   Region:us   Safetensors

Phi 3 Mini 4K Instruct DPO EPFL GPTQ 8bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 3 Mini 4K Instruct DPO EPFL GPTQ 8bit (StefanKrsteski/Phi-3-mini-4k-instruct-DPO-EPFL-GPTQ-8bit)

Phi 3 Mini 4K Instruct DPO EPFL GPTQ 8bit Parameters and Internals

LLM NamePhi 3 Mini 4K Instruct DPO EPFL GPTQ 8bit
Repository ๐Ÿค—https://huggingface.co/StefanKrsteski/Phi-3-mini-4k-instruct-DPO-EPFL-GPTQ-8bit 
Model Size1.1b
Required VRAM4.1 GB
Updated2024-12-22
MaintainerStefanKrsteski
Model Typephi3
Instruction-BasedYes
Model Files  4.1 GB
GPTQ QuantizationYes
Quantization Typegptq|8bit
Model ArchitecturePhi3ForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typefloat16

Best Alternatives to Phi 3 Mini 4K Instruct DPO EPFL GPTQ 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Phi3 Gptq 8bits4K / 4.1 GB290
...i 3 Mini 4K Instruct GPTQ 8bit4K / 4.1 GB120
Phi 3.5 Mini Instruct 8bit128K / 4.1 GB636
Phi 3 Mini 128K Instruct 8bit128K / 4.1 GB529
...hi 3 Mini 4K Instruct Sft 8bit4K / 4.1 GB260
Phi 3 Mini 4K Instruct 8bit4K / 4.1 GB272
Note: green Score (e.g. "73.2") means that the model is better than StefanKrsteski/Phi-3-mini-4k-instruct-DPO-EPFL-GPTQ-8bit.

Rank the Phi 3 Mini 4K Instruct DPO EPFL GPTQ 8bit 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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217