What are the hardware requirements for Chocolatine 14B Instruct DPO V1.2?

Chocolatine 14B Instruct DPO V1.2 requires approximately 28 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Chocolatine 14B Instruct DPO V1.2 and how large is it?

Chocolatine 14B Instruct DPO V1.2 is developed by jpacifico, a model with 14b 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 14B Instruct DPO V1.2?

Chocolatine 14B 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 14B Instruct DPO V1.2 by jpacifico — VRAM 28GB, 4K context

Name: Chocolatine 14B Instruct DPO V1.2
Author: jpacifico

Chocolatine 14B Instruct DPO V1.2 is an open-source language model by jpacifico. Features: 14b LLM, VRAM: 28GB, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.23.

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

Model Card on HF 🤗: https://huggingface.co/jpacifico/Chocolatine-14B-Instruct-DPO-v1.2

Chocolatine 14B Instruct DPO V1.2 Parameters and Internals

Model Type

LLM

Additional Notes

Quick demonstration of fine-tuning capabilities; lacks moderation mechanisms.

Supported Languages

fr (French), en (English)

Training Details

Data Sources:

jpacifico/french-orca-dpo-pairs-revised, multilingual-mt-bench

Methodology:

DPO fine-tuning

Context Length:

4000

Input Output

Output Format:

text

LLM Name	Chocolatine 14B Instruct DPO V1.2
Repository 🤗	https://huggingface.co/jpacifico/Chocolatine-14B-Instruct-DPO-v1.2
Model Size	14b
Required VRAM	28 GB
Updated	2026-08-08
Maintainer	jpacifico
Model Type	phi3
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-6 5.0 GB: 2-of-6 4.9 GB: 3-of-6 4.8 GB: 4-of-6 4.8 GB: 5-of-6 3.6 GB: 6-of-6
Supported Languages	fr en
Model Architecture	Phi3ForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32064
Torch Data Type	float16

Rank the Chocolatine 14B 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 14B Instruct DPO V1.2

Best Alternatives	Context / RAM	Downloads	Likes
Phi 3 Medium 128K Instruct	128K / 28 GB	45634	389
...ess V2.5 Phi 3 Medium 128K 14B	128K / 28 GB	16	4
...i 3 Medium 128K Instruct C4 32	128K / 15.5 GB	5	0
Finetuned Phi3 Medium 128K	128K / 28 GB	8	0
Shisa V1 Phi3 14B	128K / 28 GB	5	2
Mahou 1.2 Phi 14B	128K / 28 GB	8	1
...colatine 14B Instruct DPO V1.3	16K / 29.4 GB	16	0
Phi4 Slerp2 14B	16K / 28 GB	5	0
Phi 3 Medium 4K Instruct	4K / 28 GB	14252	226
Neos Phi 3 14B V0.1	4K / 28 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than jpacifico/Chocolatine-14B-Instruct-DPO-v1.2.