base_model: unsloth/llama-3-70b-Instruct-bnb-4bit
exported_from: Dogge/llama-3-70B-instruct-uncensored
language:
- en
library_name: transformers
license: apache-2.0
no_imatrix: 'GGML_ASSERT: llama.cpp/ggml-quants.c:11239: grid_index >= 0'
quantized_by: mradermacher
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
About
weighted/imatrix quants of https://huggingface.co/Dogge/llama-3-70B-instruct-uncensored
No more quants are incoming, as llama.cpp crashes when generating them.
static quants are available at https://huggingface.co/mradermacher/llama-3-70B-instruct-uncensored-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 | i1-Q2_K | 26.5 | IQ3_XXS probably better |
| GGUF | i1-Q3_K_M | 34.4 | IQ3_S probably better |
| GGUF | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
| PART 1 PART 2 | i1-Q6_K | 58.0 | practically like static Q6_K |
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
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.