LL

tifa benchmark llama2 tifa question generation

LlamaGGUF by RichardErkhovUpdated 2024-08-26
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant2.5 GB
Quick answer

tifa benchmark llama2 tifa question generation needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 22 quants, from 2.5 GB (Q2_K) to 7.2 GB (Q8_0).

Fine‑tuned LLaMA‑2 for generating question‑answer pairs from text descriptions

This 6.74B parameter LLaMA model is trained to parse text descriptions and produce multiple‑choice questions for faithfulness evaluation. It is part of the TIFA benchmark and supports text‑generation inference.

Good at

  • Text parsing into entities
  • Question generation for VQA
  • Faithfulness evaluation

Limits

  • No vision input support
  • Requires 8k context
  • Apache‑2.0 license

Best for

  • Automated image‑text evaluation
  • Generating VQA prompts
  • Testing image faithfulness

Who it’s for. Developers building automated evaluation pipelines for text‑to‑image models. Researchers needing a lightweight LLaMA‑2 variant for question generation tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 5.2 GB
Fits Get file →
IQ3_XS2.8 GB 5.4 GB
Fits Get file →
IQ3_S2.9 GB 5.6 GB
Fits Get file →
Q3_K_S2.9 GB 5.6 GB
Fits Get file →
IQ3_M3.1 GB 5.8 GB
Fits Get file →
Q3_K3.3 GB 5.9 GB
Fits Get file →
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q3_K_L3.6 GB 6.2 GB
Fits Get file →
IQ4_XS3.6 GB 6.3 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
IQ4_NL3.8 GB 6.5 GB
Fits Get file →
Q4_K_S3.9 GB 6.5 GB
Fits Get file →
Q4_K4.1 GB 6.7 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
Q4_14.2 GB 6.9 GB
Fits Get file →
Q5_04.7 GB 7.3 GB
Tight Get file →
Q5_K_S4.7 GB 7.3 GB
Tight Get file →
Q5_K4.8 GB 7.4 GB
Tight Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q5_15.1 GB 7.7 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →
Q8_07.2 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 3.83 GB, memory 8.6 GB). For 12 GB VRAM, Q8_0 (7.16 GB, 12 GB). Smaller quants like Q2_K (2.53 GB, 7.3 GB) fit 8 GB VRAM but use more memory.

What GPU do you need for tifa benchmark llama2 tifa question generation?

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: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which tifa benchmark llama2 tifa question generation quant should you choose?

Q4_K_M is the usual starting point for tifa benchmark llama2 tifa question generation: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.5 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
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byRichardErkhov
FamilyLlama
Licenseapache-2.0
Downloads (HF)1,478
Last updated2024-08-26

Frequently asked questions about tifa benchmark llama2 tifa question generation

How much VRAM does tifa benchmark llama2 tifa question generation need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 tifa benchmark llama2 tifa question generation on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of tifa benchmark llama2 tifa question generation GGUF?

It depends on the quant: Q2_K is 2.5 GB, IQ3_XS is 2.8 GB, IQ3_S is 2.9 GB, Q3_K_S is 2.9 GB, IQ3_M is 3.1 GB, Q3_K is 3.3 GB and 16 more.

What context length does tifa benchmark llama2 tifa question generation support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download tifa benchmark llama2 tifa question generation GGUF?

The files are on Hugging Face in the RichardErkhov/tifa-benchmark_-_llama2_tifa_question_generation-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 tifa benchmark llama2 tifa question generation 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 this model on 8 GB VRAM?

Yes, use the Q4_0 quant which requires 8.6 GB of VRAM at 8k context.

Does it support image input?

No, the model only processes text and generates questions.

What license applies?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other small models

All small models →