ST

Starling LM 7B beta iMat

StarlingGGUF by qwp4w3hybUpdated 2024-04-05
Download on Hugging Face
Parameters7.24B
Context8K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

Starling LM 7B beta iMat needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 1.6 GB (IQ1_S) to 7.7 GB (Q8_0).

Starling LM 7B beta iMat – a 7.24B parameter LLM fine‑tuned with RLAIF

Starling LM 7B beta iMat is a 7.24B parameter language model based on the Starling family and the llama architecture. It is fine‑tuned from Openchat‑3.5‑0106 using RLAIF and a custom reward model. The model is released under an Apache‑2.0 license.

Good at

  • Fine‑tuned conversational responses
  • RLAIF‑based alignment
  • Openchat‑style chat template

Limits

  • No vision support
  • Requires 8k context for full performance
  • Apache‑2.0 license restrictions

Best for

  • Chatbot prototypes
  • Research on RLHF models
  • Open‑source LLM deployment

Who it’s for. Developers and researchers who need an open, RLAIF‑trained LLM with a familiar chat template. The model is suitable for building chat applications or studying alignment techniques.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 3.2 GB
Fits Get file →
IQ2_XS2.2 GB 3.8 GB
Fits Get file →
IQ2_S2.3 GB 3.9 GB
Fits Get file →
IQ2_M2.5 GB 4.1 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 GB
Fits Get file →
IQ4_XS3.9 GB 5.5 GB
Fits Get file →
IQ4_NL4.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM, the IQ2_XS (2.2 GB) or IQ2_S (2.31 GB) quantizations are suitable, using about 3.8–3.9 GB of VRAM at 8k context. For 12 GB VRAM, IQ4_XS (3.91 GB) or Q4_K_S (4.14 GB) provide a balance of size and performance. Higher quants like Q6_K (5.94 GB) require 7.5 GB VRAM and are best for larger GPUs.

What GPU do you need for Starling LM 7B beta iMat?

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 IQ2_S (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which Starling LM 7B beta iMat quant should you choose?

Q4_K_M is the usual starting point for Starling LM 7B beta iMat: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 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 IQ1_S at 1.6 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
Parameters7.24B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byqwp4w3hyb
FamilyStarling
Licenseapache-2.0
Downloads (HF)1,604
Last updated2024-04-05

Frequently asked questions about Starling LM 7B beta iMat

How much VRAM does Starling LM 7B beta iMat need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 Starling LM 7B beta iMat on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Starling LM 7B beta iMat GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB, IQ3_XS is 3.0 GB, IQ3_S is 3.2 GB and 9 more.

What context length does Starling LM 7B beta iMat support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Starling LM 7B beta iMat GGUF?

The files are on Hugging Face in the qwp4w3hyb/Starling-LM-7B-beta-iMat-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 Starling LM 7B beta iMat 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 Starling LM 7B beta iMat on 8 GB VRAM?

Yes, the IQ2_XS or IQ2_S quantizations fit within 8 GB VRAM, using approximately 3.8–3.9 GB at 8k context.

Does the model support image input?

No, Starling LM 7B beta iMat does not support vision inputs.

What license applies to this model?

The model is released under the Apache‑2.0 license, with a restriction against competing with OpenAI.

Other GGUFs of Starling-LM-7B-beta

Similar models

Browse all →

More from qwp4w3hyb

All by qwp4w3hyb →

More Starling models

All Starling →

Other small models

All small models →