YI

Configurable-Yi-1.5-9B-Chat

YiGGUF by mradermacherUpdated 2024-07-19
Download on Hugging Face
Parameters8.83B
Context4K
Layers48
Architecturellama
Smallest quant3.4 GB
Quick answer

Configurable-Yi-1.5-9B-Chat needs about 6.6 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 3.4 GB (Q2_K) to 17.7 GB (F16).

Configurable-Yi-1.5-9B-Chat – a fine‑tuned Yi model with configurable safety prompts

Configurable-Yi-1.5-9B-Chat is a 8.83‑billion‑parameter llama‑style model fine‑tuned with configurable safety tuning. It supports multiple system prompts for safe, uncensored, or role‑play behavior. The model is released under Apache‑2.0.

Good at

  • Configurable safety prompts
  • Chat‑style interactions
  • Multi‑task prompts

Limits

  • No vision support
  • Requires 8 k context
  • License is Apache‑2.0

Best for

  • Research on safety tuning
  • Custom chat applications
  • Testing prompt variations

Who it’s for. Researchers and developers interested in safety‑tuned language models. The model is suitable for experimentation with different system prompts and safety configurations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.4 GB 4.3 GB
Fits Get file →
IQ3_XS3.7 GB 4.6 GB
Fits Get file →
Q3_K_S3.9 GB 4.8 GB
Fits Get file →
IQ3_S3.9 GB 4.8 GB
Fits Get file →
IQ3_M4.1 GB 5.0 GB
Fits Get file →
Q3_K_M4.3 GB 5.2 GB
Fits Get file →
Q3_K_L4.7 GB 5.6 GB
Fits Get file →
IQ4_XS4.8 GB 5.7 GB
Fits Get file →
Q4_K_S5.1 GB 6.0 GB
Fits Get file →
Q4_K_M5.3 GB 6.2 GB
Fits Get file →
Q5_K_S6.1 GB 7.0 GB
Fits Get file →
Q5_K_M6.3 GB 7.2 GB
Fits Get file →
Q6_K7.2 GB 8.1 GB
Too big Get file →
Q8_09.4 GB 10.3 GB
Too big Get file →
F1617.7 GB 18.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 5.07 GB, memory 6.4 GB). For 12 GB VRAM, Q5_K_S (6.11 GB, 7.4 GB) or Q5_K_M (6.26 GB, 7.6 GB). For 16 GB VRAM, Q6_K (7.25 GB, 8.6 GB) or Q8_0 (9.38 GB, 10.7 GB). Estimates are approximate.

What GPU do you need for Configurable-Yi-1.5-9B-Chat?

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 Q3_K_L (4.7 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.3 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.4 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.4 GB file, about 10.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.7 GB file, about 19.0 GB in use).

Which Configurable-Yi-1.5-9B-Chat quant should you choose?

Q4_K_M is the usual starting point for Configurable-Yi-1.5-9B-Chat: it balances file size and quality well. Here it is a 5.3 GB file.

The Q8_0 file is 9.4 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 3.4 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
Parameters8.83B
Layers48
Trained context4,096 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyYi
Licenseapache-2.0
Downloads (HF)2,328
Last updated2024-07-19

Frequently asked questions about Configurable-Yi-1.5-9B-Chat

How much VRAM does Configurable-Yi-1.5-9B-Chat need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.3 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 Configurable-Yi-1.5-9B-Chat on an 8 GB GPU?

Yes, with Q5_K_M: the 6.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Configurable-Yi-1.5-9B-Chat GGUF?

It depends on the quant: Q2_K is 3.4 GB, IQ3_XS is 3.7 GB, Q3_K_S is 3.9 GB, IQ3_S is 3.9 GB, IQ3_M is 4.1 GB, Q3_K_M is 4.3 GB and 9 more.

What context length does Configurable-Yi-1.5-9B-Chat support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.4 GB at 4K.

Where can I download Configurable-Yi-1.5-9B-Chat GGUF?

The files are on Hugging Face in the mradermacher/Configurable-Yi-1.5-9B-Chat-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 Configurable-Yi-1.5-9B-Chat use?

Hugging Face lists the license as apache-2.0. 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 Configurable-Yi-1.5-9B-Chat on 8 GB VRAM?

Yes, using Q4_K_S or Q4_K_M which require about 6.4–6.6 GB of VRAM at 8 k context.

Does the model support image inputs?

No, the model has no vision capability.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Yi models

All Yi →

Other small models

All small models →