JP

jpacifico Chocolatine 14B Instruct 4k DPO

JpacificoGGUF by RichardErkhovUpdated 2024-08-11
Download on Hugging Face
Parameters14B
Context4K
Layers40
Architecturephi3
Smallest quant1.8 GB
Quick answer

jpacifico Chocolatine 14B Instruct 4k DPO 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 22 quants, from 1.8 GB (Q5_K) to 11.2 GB (Q6_K).

14B Phi‑3 Instruct model fine‑tuned for French and English

Chocolatine 14B Instruct 4k DPO is a 14B‑parameter Phi‑3 model fine‑tuned with a French‑English DPO dataset. It supports a 4k‑token context window and is released under the MIT license.

Good at

  • French instruction following
  • English instruction following
  • DPO‑fine tuned performance

Limits

  • No moderation mechanism
  • No vision support
  • Requires 4k context window

Best for

  • French language tasks
  • English instruction generation
  • Fine‑tuned instruction following

Who it’s for. Developers and researchers who need a 14B Phi‑3 model with strong French and English instruction capabilities. The model is suitable for applications that can run on local hardware with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K1.8 GB 3.1 GB
Fits Get file →
Q8_03.4 GB 4.8 GB
Fits Get file →
Q2_K5.1 GB 6.5 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_K6.9 GB 8.3 GB
Too big Get file →
Q3_K_M6.9 GB 8.3 GB
Too big Get file →
Q3_K_L7.5 GB 8.8 GB
Too big Get file →
IQ4_XS7.5 GB 8.9 GB
Too big Get file →
Q4_07.9 GB 9.2 GB
Too big Get file →
IQ4_NL8.0 GB 9.3 GB
Too big Get file →
Q4_K_S8.0 GB 9.3 GB
Too big Get file →
Q4_K8.6 GB 9.9 GB
Too big Get file →
Q4_K_M8.6 GB 9.9 GB
Too big Get file →
Q4_18.8 GB 10.1 GB
Too big Get file →
Q5_09.6 GB 11.0 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 →
Q5_110.5 GB 11.8 GB
Too big Get file →
Q6_K11.2 GB 12.6 GB
Too big Get file →

For 8 GB VRAM use Q5_K (file size 1.79 GB, estimated 4 GB memory). For 12 GB VRAM use Q4_K (file size 8.57 GB, estimated 10.7 GB memory). For 16 GB VRAM use Q3_K (file size 6.92 GB, estimated 9.1 GB memory).

What GPU do you need for jpacifico Chocolatine 14B Instruct 4k DPO?

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: the best quant that fits is Q5_K (1.8 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 5.6 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_0 (9.6 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.2 GB file, about 13.4 GB in use).

Which jpacifico Chocolatine 14B Instruct 4k DPO quant should you choose?

Q4_K_M is the usual starting point for jpacifico Chocolatine 14B Instruct 4k DPO: it balances file size and quality well. Here it is a 8.6 GB file.

The Q8_0 file is 3.4 GB, about 0.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q5_K at 1.8 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

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 byRichardErkhov
FamilyJpacifico
Licensemit
Downloads (HF)1,436
Last updated2024-08-11

Frequently asked questions about jpacifico Chocolatine 14B Instruct 4k DPO

How much VRAM does jpacifico Chocolatine 14B Instruct 4k DPO 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 jpacifico Chocolatine 14B Instruct 4k DPO 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 jpacifico Chocolatine 14B Instruct 4k DPO GGUF?

It depends on the quant: Q5_K is 1.8 GB, Q8_0 is 3.4 GB, Q2_K is 5.1 GB, IQ3_XS is 5.8 GB, IQ3_S is 6.1 GB, Q3_K_S is 6.1 GB and 16 more.

What context length does jpacifico Chocolatine 14B Instruct 4k DPO 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 jpacifico Chocolatine 14B Instruct 4k DPO GGUF?

The files are on Hugging Face in the RichardErkhov/jpacifico_-_Chocolatine-14B-Instruct-4k-DPO-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 jpacifico Chocolatine 14B Instruct 4k DPO 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, the Q5_K quantization requires about 4 GB of VRAM at 8k context, which fits in 8 GB.

Does the model support vision tasks?

No, the model does not have vision capabilities.

Is there a moderation filter?

No, the model does not include a moderation mechanism.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Jpacifico models

All Jpacifico →

Other medium models

All medium models →