TU

allenai_tulu-2-dpo-13b

TuluGGUF by TheBlokeUpdated 2023-11-24
Download on Hugging Face
Parameters13B
Context8K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

allenai_tulu-2-dpo-13b needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 5.4 GB (Q2_K) to 13.8 GB (Q8_0).

Tulu 2 DPO 13B – a 13‑billion‑parameter instruction‑tuned LLM

Tulu 2 DPO 13B is a 13‑billion‑parameter model fine‑tuned from Llama‑2‑13b with Direct Preference Optimization. It is primarily English and designed for chat and instruction following. The model is available in multiple GGUF quantisations for CPU and GPU inference.

Good at

  • Instruction following
  • Chat‑style dialogue
  • English language tasks

Limits

  • No vision support
  • Not aligned for safe completions
  • Requires 8‑k context

Best for

  • Local chat assistants
  • Instruction‑based coding help
  • Text summarisation

Who it’s for. Developers and researchers who need a locally deployable chat model with a 13‑billion‑parameter base. The model is suitable for environments where GPU memory is limited and quantised inference is preferred.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 12.6 GB
Too big Get file →
Q3_K_S5.7 GB 12.9 GB
Too big Get file →
Q3_K_M6.3 GB 13.5 GB
Too big Get file →
Q3_K_L6.9 GB 14.1 GB
Too big Get file →
Q4_07.4 GB 14.6 GB
Too big Get file →
Q4_K_S7.4 GB 14.6 GB
Too big Get file →
Q4_K_M7.9 GB 15.1 GB
Too big Get file →
Q5_09.0 GB 16.2 GB
Too big Get file →
Q5_K_S9.0 GB 16.2 GB
Too big Get file →
Q5_K_M9.2 GB 16.4 GB
Too big Get file →
Q6_K10.7 GB 17.9 GB
Too big Get file →
Q8_013.8 GB 21.0 GB
Too big Get file →

For 8‑GB VRAM, use Q4_0 or Q4_K_S (file size 7.37 GB, estimated 14.6 GB memory). For 12‑GB VRAM, Q5_0 or Q5_K_S (file size 8.97 GB, estimated 16.2 GB memory). For 16‑GB VRAM, Q6_K (file size 10.68 GB, estimated 17.9 GB memory).

What GPU do you need for allenai_tulu-2-dpo-13b?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q4_K_M (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).

Which allenai_tulu-2-dpo-13b quant should you choose?

Q4_K_M is the usual starting point for allenai_tulu-2-dpo-13b: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 GB, about 1.8 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 Q2_K at 5.4 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

Architecturellama
Parameters13B
Layers40
Trained context8,192 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
FamilyTulu
Licenseother
Downloads (HF)1,488
Last updated2023-11-24

Frequently asked questions about allenai_tulu-2-dpo-13b

How much VRAM does allenai_tulu-2-dpo-13b need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 allenai_tulu-2-dpo-13b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of allenai_tulu-2-dpo-13b GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.3 GB, Q3_K_L is 6.9 GB, Q4_0 is 7.4 GB, Q4_K_S is 7.4 GB and 6 more.

What context length does allenai_tulu-2-dpo-13b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 6.7 GB at 8K and 6.7 GB at 8K.

Where can I download allenai_tulu-2-dpo-13b GGUF?

The files are on Hugging Face in the TheBloke/tulu-2-dpo-13B-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 allenai_tulu-2-dpo-13b use?

Hugging Face lists the license as other. 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 Tulu 2 DPO 13B on 8 GB VRAM?

Yes, using a Q4_0 or Q4_K_S quantised model which requires about 14.6 GB of VRAM at 8‑k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under an AI2 ImpACT Low‑risk license.

Other GGUFs of tulu-2-dpo-13b

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Tulu models

All Tulu →

Other medium models

All medium models →