LL

cais HarmBench Llama 2 13b cls

LlamaGGUF by RichardErkhovUpdated 2024-05-10
Download on Hugging Face
Parameters13B
Context2K
Layers40
Architecturellama
Smallest quant4.9 GB
Quick answer

cais HarmBench Llama 2 13b cls 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 21 quants, from 4.9 GB (Q2_K) to 10.7 GB (Q6_K).

cais HarmBench Llama 2 13b cls – a text behavior classifier

cais HarmBench Llama 2 13b cls is a 13 billion‑parameter Llama model fine‑tuned for classifying text behaviors. It supports standard and contextual behaviors and is trained on distilled GPT‑4 data.

Good at

  • Classifying text behaviors
  • Handling contextual behavior cues
  • Comparative performance to GPT‑4

Limits

  • No vision support
  • Context limited to 2048 tokens
  • License not specified

Best for

  • Content moderation pipelines
  • Behavior analysis tools
  • Research on text safety

Who it’s for. Developers building moderation systems or researchers studying text behavior. The model is suitable for those needing a classifier that aligns with HarmBench standards.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.9 GB 7.0 GB
Fits Get file →
IQ3_XS5.4 GB 7.5 GB
Tight Get file →
IQ3_S5.7 GB 7.8 GB
Tight Get file →
Q3_K_S5.7 GB 7.8 GB
Tight Get file →
IQ3_M6.0 GB 8.2 GB
Too big Get file →
Q3_K6.3 GB 8.5 GB
Too big Get file →
Q3_K_M6.3 GB 8.5 GB
Too big Get file →
Q3_K_L6.9 GB 9.1 GB
Too big Get file →
IQ4_XS7.0 GB 9.2 GB
Too big Get file →
Q4_07.4 GB 9.5 GB
Too big Get file →
IQ4_NL7.4 GB 9.6 GB
Too big Get file →
Q4_K_S7.4 GB 9.6 GB
Too big Get file →
Q4_K7.9 GB 10.0 GB
Too big Get file →
Q4_K_M7.9 GB 10.0 GB
Too big Get file →
Q4_18.2 GB 10.3 GB
Too big Get file →
Q5_09.0 GB 11.2 GB
Too big Get file →
Q5_K_S9.0 GB 11.2 GB
Too big Get file →
Q5_K9.2 GB 11.4 GB
Too big Get file →
Q5_K_M9.2 GB 11.4 GB
Too big Get file →
Q5_19.8 GB 12.0 GB
Too big Get file →
Q6_K10.7 GB 12.9 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (4.85 GB, 12.1 GB memory) or IQ3_XS (5.36 GB, 12.6 GB). For 12 GB VRAM, Q4_0 (7.37 GB, 14.6 GB) or Q4_K (7.87 GB, 15.1 GB) are suitable. Higher quants give better fidelity but require more memory.

What GPU do you need for cais HarmBench Llama 2 13b cls?

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_1 (8.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (10.7 GB file, about 17.9 GB in use).

Which cais HarmBench Llama 2 13b cls quant should you choose?

Q4_K_M is the usual starting point for cais HarmBench Llama 2 13b cls: it balances file size and quality well. Here it is a 7.9 GB file.

If memory is tight, the smallest file is Q2_K at 4.9 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 context2,048 tokens
KV cache (fp16)800 KB per token

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)689
Last updated2024-05-10

Frequently asked questions about cais HarmBench Llama 2 13b cls

How much VRAM does cais HarmBench Llama 2 13b cls 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 cais HarmBench Llama 2 13b cls on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of cais HarmBench Llama 2 13b cls GGUF?

It depends on the quant: Q2_K is 4.9 GB, IQ3_XS is 5.4 GB, IQ3_S is 5.7 GB, Q3_K_S is 5.7 GB, IQ3_M is 6.0 GB, Q3_K is 6.3 GB and 15 more.

What context length does cais HarmBench Llama 2 13b cls support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.7 GB at 8K and 1.7 GB at 2K.

Where can I download cais HarmBench Llama 2 13b cls GGUF?

The files are on Hugging Face in the RichardErkhov/cais_-_HarmBench-Llama-2-13b-cls-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, with Q2_K or IQ3_XS quantization, which fit within 8 GB VRAM and use about 12–13 GB of memory at 8k context.

Does this model support vision inputs?

No, it only processes text inputs.

What is the context length limit?

The model supports a maximum context length of 2048 tokens.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other medium models

All medium models →