base_model: tiiuae/falcon-mamba-7b
datasets:
- tiiuae/falcon-refinedweb
- HuggingFaceFW/fineweb-edu
language:
- en
library_name: transformers
license: other
license_link: https://falconllm.tii.ae/falcon-mamba-7b-terms-and-conditions.html
license_name: falcon-mamba-7b-license
no_imatrix: >-
llama.cpp/ggml/src/ggml-cuda/norm.cu:212:
GGML_ASSERT(ggml_is_contiguous(src0)) failed
quantized_by: mradermacher
About
static quants of https://huggingface.co/tiiuae/falcon-mamba-7b
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 | 2.7 | |
| GGUF | IQ3_M | 3.4 | |
| GGUF | IQ3_S | 3.4 | beats Q3_K* |
| GGUF | IQ3_XS | 3.4 | |
| GGUF | Q3_K_L | 3.4 | |
| GGUF | Q3_K_M | 3.4 | lower quality |
| GGUF | Q3_K_S | 3.4 | |
| GGUF | IQ4_XS | 4.1 | |
| GGUF | Q4_K_M | 4.3 | fast, recommended |
| GGUF | Q4_K_S | 4.3 | fast, recommended |
| GGUF | Q5_K_M | 5.2 | |
| GGUF | Q5_K_S | 5.2 | |
| GGUF | Q6_K | 6.1 | very good quality |
| GGUF | Q8_0 | 7.9 | fast, best quality |
| GGUF | f16 | 14.7 | 16 bpw, overkill |
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.