What are the hardware requirements for Chocolatine 3B Instruct DPO V1.2?

Chocolatine 3B Instruct DPO V1.2 requires approximately 7.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Chocolatine 3B Instruct DPO V1.2 and how large is it?

Chocolatine 3B Instruct DPO V1.2 is developed by jpacifico, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Chocolatine 3B Instruct DPO V1.2?

Chocolatine 3B Instruct DPO V1.2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Chocolatine 3B Instruct DPO V1.2 by jpacifico — VRAM 7.7GB, 128K context

Name: Chocolatine 3B Instruct DPO V1.2
Author: jpacifico

Chocolatine 3B Instruct DPO V1.2 is an open-source language model by jpacifico. Features: 3b LLM, VRAM: 7.7GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.22.

Chocolatine Conversational Custom code Dataset:jpacifico/french-orca-... En Endpoints compatible Fr French Instruct Phi3 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-v1.2

Chocolatine 3B Instruct DPO V1.2 Parameters and Internals

Model Type

LLM

Additional Notes

Supports 128K context length. No moderation mechanism.

Supported Languages

French (High proficiency), English (Improved proficiency due to training in French)

Training Details

Data Sources:

jpacifico/french-orca-dpo-pairs-revised

Methodology:

DPO fine-tuned

Context Length:

128

Input Output

Input Format:

Prompt structured for chatbot interaction

Accepted Modalities:

text

Output Format:

Generated text

Performance Tips:

Adjust temperature for sampling

LLM Name	Chocolatine 3B Instruct DPO V1.2
Repository 🤗	https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-v1.2
Model Size	3b
Required VRAM	7.7 GB
Updated	2026-08-02
Maintainer	jpacifico
Model Type	phi3
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 2.7 GB: 2-of-2
Supported Languages	fr en
Model Architecture	Phi3ForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.43.0
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32064
Torch Data Type	float16

Rank the Chocolatine 3B Instruct DPO V1.2 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 Chocolatine 3B Instruct DPO V1.2

Best Alternatives	Context / RAM	Downloads	Likes
ILAB Merging 3B V2	128K / 23.1 GB	13	2
MedIT Mesh 3B Instruct	128K / 7.7 GB	7	1
3Bgeneral ECE PRYMMAL Martial	128K / 7.7 GB	6	0
3Blareneg ECE PRYMMAL Martial	128K / 7.7 GB	5	0
ECE EIFFEL 3B	128K / 7.7 GB	11	0
Chocolatine Admin 3B SFT V0.3B	128K / 7.7 GB	11	4
ECE GRENELLE 3B	128K / 7.7 GB	5	0
Phi3 3B Ultrachat Svd Model	128K / 7.7 GB	9	1
Orpo Phi3 3B 128K	128K / 7.7 GB	11	3
ECE PRYMMAL 3B SLERP 2 V2	4K / 7.7 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than jpacifico/Chocolatine-3B-Instruct-DPO-v1.2.