base_model: Blackfrost-AI/LING-3.0-FLASH-ABLITERATED language:
- en
- zh library_name: transformers license: mit mradermacher: readme_rev: 1 quantized_by: mradermacher tags:
- bailing-moe-v3
- ling
- derisked
- moe
- hybrid-attention
- mla
- residual-intervention
- conversational
- long-context
- reasoning
- gated
- research
- security
- cybersecurity
- red-teaming
- adversarial-testing
- evaluation
- not-for-all-audiences
About
weighted/imatrix quants of https://huggingface.co/Blackfrost-AI/LING-3.0-FLASH-ABLITERATED
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/LING-3.0-FLASH-ABLITERATED-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 | imatrix | 0.6 | imatrix file (for creating your own quants) |
| GGUF | i1-Q2_K | 46.6 | IQ3_XXS probably better |
| GGUF | i1-IQ3_S | 55.2 | beats Q3_K* |
| GGUF | i1-Q3_K_S | 55.2 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 55.8 | |
| GGUF | i1-Q3_K_M | 60.9 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 66.1 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 68.1 | |
| GGUF | i1-Q4_0 | 72.3 | fast, low quality |
| GGUF | i1-Q4_K_S | 72.5 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 77.1 | fast, recommended |
| GGUF | i1-Q4_1 | 80.1 | |
| GGUF | i1-Q5_K_S | 88.0 | |
| GGUF | i1-Q5_K_M | 90.6 | |
| PART 1 PART 2 PART 3 | i1-Q6_K | 104.9 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
image.png
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. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.