ST

dolphincoder starcoder2 7b

StarCoderGGUF by dagbsUpdated 2024-03-10
Download on Hugging Face
Parameters7.4B
Context16K
Layers32
Architecturestarcoder2
Smallest quant2.9 GB
Quick answer

dolphincoder starcoder2 7b needs about 5.6 GB of memory at Q4_K_M (a 4.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 2.9 GB (Q2_K) to 7.9 GB (Q8_0).

dolphincoder starcoder2 7b – a 7.4B parameter code generation model

dolphincoder starcoder2 7b is a 7.4B parameter model from the StarCoder family. It supports coding and tool usage. The model was trained on 16384 context tokens and is released under the bigcode-openrail-m license.

Good at

  • Coding tasks
  • Tool integration
  • Large context handling

Limits

  • No vision support
  • Requires 8k context for full capability
  • License restricts commercial use

Best for

  • Writing code snippets
  • Automating tool workflows
  • Generating documentation

Who it’s for. Developers and researchers needing a lightweight code generation model. The model is suitable for environments with limited GPU memory and for projects that require tool integration.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.9 GB 3.9 GB
Fits Get file →
Q3_K_S3.3 GB 4.3 GB
Fits Get file →
Q3_K_M3.8 GB 4.8 GB
Fits Get file →
Q3_K_L4.2 GB 5.2 GB
Fits Get file →
Q4_K_S4.3 GB 5.4 GB
Fits Get file →
Q4_K_M4.6 GB 5.6 GB
Fits Get file →
Q5_K_S5.1 GB 6.2 GB
Fits Get file →
Q5_K_M5.3 GB 6.3 GB
Fits Get file →
Q6_K6.1 GB 7.1 GB
Fits Get file →
Q8_07.9 GB 8.9 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.59 GB, estimated 5.6 GB memory). For 12 GB VRAM, Q5_K_M (5.31 GB, 6.3 GB memory) or Q6_K (6.08 GB, 7.1 GB memory). For 16 GB VRAM, Q8_0 (7.87 GB, 8.9 GB memory) offers the highest quality.

What GPU do you need for dolphincoder starcoder2 7b?

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 Q2_K (2.9 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.6 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.1 GB file, about 7.1 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.9 GB file, about 8.9 GB in use).

Which dolphincoder starcoder2 7b quant should you choose?

Q4_K_M is the usual starting point for dolphincoder starcoder2 7b: it balances file size and quality well. Here it is a 4.6 GB file.

The Q8_0 file is 7.9 GB, about 1.7 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 2.9 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

Architecturestarcoder2
Parameters7.4B
Layers32
Trained context16,384 tokens
KV cache (fp16)64 KB per token

Source

Quantized bydagbs
FamilyStarCoder
Downloads (HF)1,270
Last updated2024-03-10

Frequently asked questions about dolphincoder starcoder2 7b

How much VRAM does dolphincoder starcoder2 7b need?

About 5.6 GB at Q4_K_M with an 8K context window. That is the 4.6 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 dolphincoder starcoder2 7b on an 8 GB GPU?

Yes, with Q6_K: the 6.1 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of dolphincoder starcoder2 7b GGUF?

It depends on the quant: Q2_K is 2.9 GB, Q3_K_S is 3.3 GB, Q3_K_M is 3.8 GB, Q3_K_L is 4.2 GB, Q4_K_S is 4.3 GB, Q4_K_M is 4.6 GB and 4 more.

What context length does dolphincoder starcoder2 7b support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.1 GB at 16K.

Where can I download dolphincoder starcoder2 7b GGUF?

The files are on Hugging Face in the dagbs/dolphincoder-starcoder2-7b-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 dolphincoder starcoder2 7b use?

Hugging Face lists the license as bigcode-openrail-m. 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 dolphincoder starcoder2 7b on 8 GB VRAM?

Yes, using the Q4_K_M quantized file requires approximately 5.6 GB of VRAM at 8k context.

Does this model support image input?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the bigcode-openrail-m license.

Similar models

Browse all →

More from dagbs

All by dagbs →

More StarCoder models

All StarCoder →

Other small models

All small models →