4bit Autotrain compatible Conversational En Endpoints compatible Instruct Llama Pytorch Quantized Region:us Safetensors Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI/DeepPhi-3.5-mini-instruct
DeepPhi 3.5 Mini Instruct Benchmarks
MMLU Pro: 1.14
MUSR: 4.04
BBH: 1.67
IFEval: 13.26 vs 88 (so35)-84.9%
MATH Lvl 5: 0.68
LLME Score: 0.23754
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
DeepPhi 3.5 Mini Instruct Parameters and Internals
| LLM Name | DeepPhi 3.5 Mini Instruct |
| Repository 🤗 | https://huggingface.co/EpistemeAI/DeepPhi-3.5-mini-instruct |
| Base Model(s) | |
| Model Size | 3.8b |
| Required VRAM | 7.6 GB |
| Updated | 2025-04-02 |
| Maintainer | EpistemeAI |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Gated Model | Yes |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | proprietary |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.48.3 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|placeholder6|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to DeepPhi 3.5 Mini Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Model | 128K / 7.6 GB | 41 | 0 |
| Phi 3 5 Mini 3k Each | 128K / 7.6 GB | 19 | 0 |
| ...ene Phi 3.5 Mini Instruct Orpo | 128K / 7.6 GB | 9 | 2 |
| Tara 3.8B | 146K / 7.6 GB | 15 | 0 |
| Phi3 Unlearned | 128K / 7.6 GB | 653 | 0 |
| ...hi3 Unlearning General Methode | 128K / 7.6 GB | 355 | 0 |
| Phi 3.5 Mini Instruct | 128K / 7.6 GB | 10008 | 45 |
| Superthoughts Mini V1.3.8B | 128K / 7.6 GB | 78 | 1 |
| Phi 3 5 Mini Kp 12k Cfr Sft | 128K / 7.6 GB | 14 | 0 |
| Phi 3 5 Mini Tictactoe1200 | 128K / 7.6 GB | 14 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI/DeepPhi-3.5-mini-instruct .
Rank the DeepPhi 3.5 Mini Instruct 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! 🌟
What open-source LLMs or SLMs are you in search of? 48046 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124