What are the hardware requirements for PhigRange DPO?

PhigRange DPO requires approximately 5.6 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed PhigRange DPO and how large is it?

PhigRange DPO is developed by johnsnowlabs, a model with 2.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does PhigRange DPO perform on standard benchmarks?

PhigRange DPO has the following published scores: MMLU 25.52. Compare against reference models on this page or on the LLM Explorer leaderboards.

PhigRange DPO by johnsnowlabs — VRAM 5.6GB, 2K context

Name: PhigRange DPO
Author: johnsnowlabs

PhigRange DPO is an open-source language model by johnsnowlabs. Features: 2.7b LLM, VRAM: 5.6GB, Context: 2K, License: cc-by-nc-4.0, LLM Explorer Score: 0.16, Arc: 25.8, HellaSwag: 25.7, MMLU: 25.5.

Chatml Dataset:mlabonne/chatml-openhe... Distillation Dpo En Endpoints compatible Finetuned Generated from trainer Gpt4 Instruct Phi Region:us Safetensors Sharded Synthetic data Tensorflow

Model Card on HF 🤗: https://huggingface.co/johnsnowlabs/PhigRange-DPO

PhigRange DPO Parameters and Internals

Model Type

text-generation

Supported Languages

en (high)

Training Details

Data Sources:

mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha

Methodology:

DPO fine-tuning

LLM Name	PhigRange DPO
Repository 🤗	https://huggingface.co/johnsnowlabs/PhigRange-DPO
Base Model(s)	PhigRange-2.7B-slerp /PhigRange-2.7B-slerp
Model Size	2.7b
Required VRAM	5.6 GB
Updated	2025-12-29
Maintainer	johnsnowlabs
Model Type	phi
Model Files	5.0 GB: 1-of-2 0.6 GB: 2-of-2
Supported Languages	en
Model Architecture	PhiForCausalLM
License	cc-by-nc-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.40.0.dev0
Tokenizer Class	CodeGenTokenizer
Vocabulary Size	51200
Torch Data Type	float16

Rank the PhigRange DPO capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to PhigRange DPO

Best Alternatives	Context / RAM	Downloads	Likes
PhigRange 2.7B Slerp	2K / 5.6 GB	7	0
Damysus 2.7B Chat	2K / 11.1 GB	68	4
JSL MedPhi2 2.7B	2K / 5.6 GB	25	3
Speculor 2.7B	2K / 5.6 GB	6	2
...atural Language To Cypher 2.7B	2K / 5.6 GB	7	0
Codephi 2.7B	2K / 5.6 GB	5	0
Phi 2.7B MERGED	0K / 5.6 GB	5	0
Samanthav2 2.7B	0K / 5.6 GB	3	1
Barcenas 2.7B	0K / 5.6 GB	19	1
Damysus 2.7B Chat GGUF	2K / 1.7 GB	160	0