LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Phi 3 Mini 128K Instruct AWQ by jsincn

 »  All LLMs  »  jsincn  »  Phi 3 Mini 128K Instruct AWQ   URL Share it on

  1671   
  4-bit   Autotrain compatible   Awq   Conversational   Custom code   Endpoints compatible   Instruct   Phi3   Quantized   Region:us   Safetensors

Phi 3 Mini 128K Instruct AWQ Benchmarks

LLME Score: 0.23091
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 128K Instruct AWQ Parameters and Internals

Additional Notes 
The model is quantized using AWQ via AutoAWQ. Utilizes a TGI docker image where hosting fails due to fallback issues with AutoModel. Recommended to host using vLLM with an appropriate trust-remote-code flag. Code should be validated despite being sourced from Microsoft.
LLM NamePhi 3 Mini 128K Instruct AWQ
Repository 🤗https://huggingface.co/jsincn/phi-3-mini-128k-instruct-awq 
Model Size682m
Required VRAM2.3 GB
Updated2024-11-21
Maintainerjsincn
Model Typephi3
Instruction-BasedYes
Model Files  2.3 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.41.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typefloat16
Phi 3 Mini 128K Instruct AWQ (jsincn/phi-3-mini-128k-instruct-awq)

Best Alternatives to Phi 3 Mini 128K Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Flow Judge V0.1 AWQ128K / 2.3 GB23236
...8K Instruct Abliterated V3 AWQ128K / 2.3 GB60
... 3 Mini 128K Instruct AWQ 4bit128K / 2.3 GB21
Note: green Score (e.g. "73.2") means that the model is better than jsincn/phi-3-mini-128k-instruct-awq.

Rank the Phi 3 Mini 128K Instruct AWQ Capabilities

🆘 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! 🌟

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? 38149 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110
  Support LLM Explorer