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

Phi 4 14B Grpo Gsm8k 3e by mrm8488

 »  All LLMs  »  mrm8488  »  Phi 4 14B Grpo Gsm8k 3e   URL Share it on

  31   
  4bit   Autotrain compatible Base model:finetune:unsloth/ph... Base model:unsloth/phi-4-bnb-4...   Conversational   En   Endpoints compatible   Grpo   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/mrm8488/phi-4-14B-grpo-gsm8k-3e 

Phi 4 14B Grpo Gsm8k 3e Benchmarks

MMLU Pro: 47.43
GPQA: 11.41
MUSR: 8.29
BBH: 54.02
IFEval: 68.85 vs 88 (so35)-21.8%
MATH Lvl 5: 45.24
LLME Score: 0.36594
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 4 14B Grpo Gsm8k 3e (mrm8488/phi-4-14B-grpo-gsm8k-3e)

Phi 4 14B Grpo Gsm8k 3e Parameters and Internals

LLM NamePhi 4 14B Grpo Gsm8k 3e
Repository 🤗https://huggingface.co/mrm8488/phi-4-14B-grpo-gsm8k-3e 
Base Model(s)  Phi 4 Bnb 4bit   unsloth/phi-4-bnb-4bit
Model Size14b
Required VRAM29.4 GB
Updated2025-03-12
Maintainermrm8488
Model Typellama
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.6 GB: 6-of-6
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.48.2
Tokenizer ClassGPT2Tokenizer
Padding Token<|dummy_87|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Phi 4 14B Grpo Gsm8k 3e

Best Alternatives
Context / RAM
Downloads
Likes
Parm 2 CoT 14B 16K O1 QwQ16K / 29.4 GB2817
Phi 4 14B Grpo Limo16K / 29.4 GB400
...perThoughts CoT 14B 16K O1 QwQ16K / 29.4 GB2656
...hts CoT 14B 16K O1 QwQ PyTorch16K / 29.4 GB01
CausalLM 14B EXL28K / 8.5 GB233
...Qwen2.5llamaify 14B V23.1 200K195K / 29.7 GB21531
...Qwen2.5llamaify 14B V23.3 200K195K / 29.7 GB305
GeM2 Llamion 14B LongChat195K / 29 GB36354
Openbuddy Zero 14B V22.3 32K32K / 28 GB17191
Megatron Opus 14B 2.116K / 29.5 GB148313
Note: green Score (e.g. "73.2") means that the model is better than mrm8488/phi-4-14B-grpo-gsm8k-3e.

Rank the Phi 4 14B Grpo Gsm8k 3e 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? 44902 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 v20241227
  Support LLM Explorer