CH

Chocolatine 14B Instruct DPO v1.1 i1

ChocolatineGGUF by mradermacherUpdated 2024-08-16
Download on Hugging Face
Parameters14B
Context4K
Layers40
Architecturephi3
Smallest quant3.0 GB
Quick answer

Chocolatine 14B Instruct DPO v1.1 i1 needs about 10.7 GB of memory at Q4_K_M (a 8.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 3.0 GB (IQ1_S) to 11.5 GB (Q6_K).

Chocolatine 14B Instruct DPO v1.1 i1 – a Phi‑3 based LLM fine‑tuned for instruction following

Chocolatine 14B Instruct DPO v1.1 i1 is a 14B parameter model based on Phi‑3. It was fine‑tuned with DPO on a French‑English dataset, improving performance in both languages. The model supports a 4096 token context window and is released under the MIT license.

Good at

  • Instruction following
  • French and English language tasks
  • Reasoning in 4k context

Limits

  • No moderation mechanism
  • No vision support
  • Requires 8k context for memory estimates

Best for

  • Chatbots needing bilingual support
  • Educational tutoring in French and English
  • Research prototyping with Phi‑3 architecture

Who it’s for. Developers and researchers who need a fine‑tuned Phi‑3 model for instruction‑driven tasks in French and English. The model is suitable for local deployment using llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.0 GB 4.3 GB
Fits Get file →
IQ1_M3.2 GB 4.6 GB
Fits Get file →
IQ2_XXS3.7 GB 5.1 GB
Fits Get file →
IQ2_XS4.1 GB 5.5 GB
Fits Get file →
IQ2_S4.3 GB 5.7 GB
Fits Get file →
IQ2_M4.7 GB 6.1 GB
Fits Get file →
Q2_K5.1 GB 6.5 GB
Fits Get file →
IQ3_XXS5.5 GB 6.8 GB
Fits Get file →
IQ3_XS5.8 GB 7.1 GB
Fits Get file →
IQ3_S6.1 GB 7.4 GB
Tight Get file →
Q3_K_S6.1 GB 7.4 GB
Tight Get file →
IQ3_M6.5 GB 7.8 GB
Tight Get file →
Q3_K_M6.9 GB 8.3 GB
Too big Get file →
IQ4_XS7.5 GB 8.8 GB
Too big Get file →
Q3_K_L7.5 GB 8.8 GB
Too big Get file →
Q4_07.9 GB 9.3 GB
Too big Get file →
Q4_K_S8.0 GB 9.3 GB
Too big Get file →
Q4_K_M8.6 GB 9.9 GB
Too big Get file →
Q5_K_S9.6 GB 11.0 GB
Too big Get file →
Q5_K_M10.1 GB 11.4 GB
Too big Get file →
Q6_K11.5 GB 12.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.96 GB, memory 5.1 GB) or IQ1_M (3.24 GB, 5.4 GB). If 12 GB VRAM is available, IQ2_M (4.72 GB, 6.9 GB) or Q2_K (5.14 GB, 7.3 GB) provide a balance of size and performance. Higher quality quants such as Q5_K_M (10.07 GB, 12.3 GB) require 16 GB or more.

What GPU do you need for Chocolatine 14B Instruct DPO v1.1 i1?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is IQ2_XXS (3.7 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XS (5.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_S (9.6 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.5 GB file, about 13.6 GB in use).

Which Chocolatine 14B Instruct DPO v1.1 i1 quant should you choose?

Q4_K_M is the usual starting point for Chocolatine 14B Instruct DPO v1.1 i1: it balances file size and quality well. Here it is a 8.6 GB file.

If memory is tight, the smallest file is IQ1_S at 3.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi3
Parameters14B
Layers40
Trained context4,096 tokens
KV cache (fp16)200 KB per token

Source

Quantized bymradermacher
Licensemit
Downloads (HF)2,358
Last updated2024-08-16

Frequently asked questions about Chocolatine 14B Instruct DPO v1.1 i1

How much VRAM does Chocolatine 14B Instruct DPO v1.1 i1 need?

About 10.7 GB at Q4_K_M with an 8K context window. That is the 8.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Chocolatine 14B Instruct DPO v1.1 i1 on an 8 GB GPU?

Yes, with IQ3_XS: the 5.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Chocolatine 14B Instruct DPO v1.1 i1 GGUF?

It depends on the quant: IQ1_S is 3.0 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.7 GB, IQ2_XS is 4.1 GB, IQ2_S is 4.3 GB, IQ2_M is 4.7 GB and 15 more.

What context length does Chocolatine 14B Instruct DPO v1.1 i1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.7 GB at 8K and 0.8 GB at 4K.

Where can I download Chocolatine 14B Instruct DPO v1.1 i1 GGUF?

The files are on Hugging Face in the mradermacher/Chocolatine-14B-Instruct-DPO-v1.1-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Chocolatine 14B Instruct DPO v1.1 i1 use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quant will fit within 8 GB VRAM, with estimated memory usage of 5.1 GB and 5.4 GB respectively.

Does the model support vision inputs?

No, the model does not have vision support and is purely a text LLM.

What license does the model use?

The model is released under the MIT license, allowing free use and modification.

Other GGUFs of Chocolatine-14B-Instruct-DPO-v1.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Chocolatine models

All Chocolatine →

Other medium models

All medium models →