BA

bagel dpo 34b v0.5 i1

BagelGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant8.1 GB
Quick answer

bagel dpo 34b v0.5 i1 needs about 23.7 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 8.1 GB (IQ1_S) to 28.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Bagel DPO 34B v0.5 i1 – a 34 billion‑parameter LLM fine‑tuned with direct preference optimization

Bagel DPO 34B v0.5 i1 is a fine‑tuned version of yi‑34b‑200k with enhanced long‑context support. It was trained with DPO to improve alignment and includes coding, roleplay, and tools abilities. The model supports up to 200 k context tokens.

Good at

  • Long‑context reasoning
  • Coding assistance
  • Roleplay and tool usage

Limits

  • Large VRAM requirement for higher‑quality quants
  • No vision support
  • License type is other

Best for

  • Developers needing long‑context code generation
  • Chatbot creators requiring roleplay capabilities
  • Tool‑integrated AI applications

Who it’s for. Engineers and researchers who need a large, aligned model with strong coding and roleplay abilities. The model is suitable for projects that can accommodate its memory demands and do not require vision or multimodal features.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S8.1 GB 10.6 GB
Too big Get file →
IQ1_M8.8 GB 11.3 GB
Too big Get file →
IQ2_XXS9.9 GB 12.4 GB
Too big Get file →
IQ2_XS10.9 GB 13.4 GB
Too big Get file →
IQ2_S11.5 GB 14.0 GB
Too big Get file →
IQ2_M12.4 GB 14.9 GB
Too big Get file →
Q2_K13.4 GB 15.9 GB
Too big Get file →
IQ3_XXS13.9 GB 16.4 GB
Too big Get file →
IQ3_XS14.8 GB 17.3 GB
Too big Get file →
Q3_K_S15.5 GB 18.0 GB
Too big Get file →
IQ3_S15.6 GB 18.1 GB
Too big Get file →
IQ3_M16.1 GB 18.6 GB
Too big Get file →
Q3_K_M17.2 GB 19.7 GB
Too big Get file →
Q3_K_L18.7 GB 21.2 GB
Too big Get file →
IQ4_XS19.0 GB 21.5 GB
Too big Get file →
Q4_020.1 GB 22.6 GB
Too big Get file →
Q4_K_S20.1 GB 22.7 GB
Too big Get file →
Q4_K_M21.2 GB 23.7 GB
Too big Get file →
Q5_K_S24.2 GB 26.8 GB
Too big Get file →
Q5_K_M24.9 GB 27.4 GB
Too big Get file →
Q6_K28.8 GB 31.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (8.1 GB file, ~10.6 GB memory at 8 k context). With 12 GB VRAM, IQ1_M or IQ2_XXS are suitable. For 16 GB VRAM, IQ2_XS or IQ2_S provide a balance between size and performance. Memory estimates are approximate.

What GPU do you need for bagel dpo 34b v0.5 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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ1_M (8.8 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (13.4 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.8 GB file, about 31.3 GB in use).

Which bagel dpo 34b v0.5 i1 quant should you choose?

Q4_K_M is the usual starting point for bagel dpo 34b v0.5 i1: it balances file size and quality well. Here it is a 21.2 GB file.

If memory is tight, the smallest file is IQ1_S at 8.1 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
Parameters34.4B
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized bymradermacher
FamilyBagel
Licenseother
Downloads (HF)4,585
Last updated2024-05-06

Frequently asked questions about bagel dpo 34b v0.5 i1

How much VRAM does bagel dpo 34b v0.5 i1 need?

About 23.7 GB at Q4_K_M with an 8K context window. That is the 21.2 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 bagel dpo 34b v0.5 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of bagel dpo 34b v0.5 i1 GGUF?

It depends on the quant: IQ1_S is 8.1 GB, IQ1_M is 8.8 GB, IQ2_XXS is 9.9 GB, IQ2_XS is 10.9 GB, IQ2_S is 11.5 GB, IQ2_M is 12.4 GB and 15 more.

What context length does bagel dpo 34b v0.5 i1 support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download bagel dpo 34b v0.5 i1 GGUF?

The files are on Hugging Face in the mradermacher/bagel-dpo-34b-v0.5-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 bagel dpo 34b v0.5 i1 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 this model on 8 GB VRAM?

Yes, the IQ1_S quant is 8.1 GB and requires about 10.6 GB of VRAM at 8 k context, which fits within 8 GB with some batching or lower context.

Does this model support image input?

No, the model has no vision capabilities and only handles text.

What license applies to this model?

The model is released under an other license; check the Hugging Face page for details.

Other GGUFs of bagel-dpo-34b-v0.5

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bagel models

All Bagel →

Other large models

All large models →