base_model: lightgpt/LightGPT-13B-Llama2
extra_gated_button_content: Submit
extra_gated_fields:
I agree to share my name, email address and username with Meta and confirm that I have already been granted download access on the Meta website: checkbox
extra_gated_heading: Access LLMLight-LightGPT on Hugging Face
extra_gated_prompt: >-
**Your Hugging Face account email address MUST match the email you provide on
the Meta website, or your request will not be approved.**
language:
- en
library_name: transformers
license: mit
quantized_by: mradermacher
tags:
- pytorch
- llama-2
- traffic signal control
- lightgpt
- llmlight
About
static quants of https://huggingface.co/lightgpt/LightGPT-13B-Llama2
weighted/imatrix quants are available at https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | Q2_K | 5.0 | |
| GGUF | IQ3_XS | 5.5 | |
| GGUF | IQ3_S | 5.8 | beats Q3_K* |
| GGUF | Q3_K_S | 5.8 | |
| GGUF | IQ3_M | 6.1 | |
| GGUF | Q3_K_M | 6.4 | lower quality |
| GGUF | Q3_K_L | 7.0 | |
| GGUF | IQ4_XS | 7.1 | |
| GGUF | Q4_K_S | 7.5 | fast, recommended |
| GGUF | Q4_K_M | 8.0 | fast, recommended |
| GGUF | Q5_K_S | 9.1 | |
| GGUF | Q5_K_M | 9.3 | |
| GGUF | Q6_K | 10.8 | very good quality |
| GGUF | Q8_0 | 13.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.