| --- |
| base_model: MasterControlAIML/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured |
| language: |
| - en |
| library_name: transformers |
| license: apache-2.0 |
| mradermacher: |
| readme_rev: 1 |
| quantized_by: mradermacher |
| tags: |
| - DeepSeek |
| - R1 |
| - SFT |
| - Qwen |
| - JSON |
| - Unstructured |
| - Structured |
| --- |
| ## About |
|
|
| <!-- ### quantize_version: 2 --> |
| <!-- ### output_tensor_quantised: 1 --> |
| <!-- ### convert_type: hf --> |
| <!-- ### vocab_type: --> |
| <!-- ### tags: nicoboss --> |
| weighted/imatrix quants of https://huggingface.co/MasterControlAIML/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured |
| |
| <!-- provided-files --> |
| |
| ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF).*** |
| |
| static quants are available at https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-GGUF |
| ## Usage |
| |
| If you are unsure how to use GGUF files, refer to one of [TheBloke's |
| READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) 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](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.6 | | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ2_S.gguf) | i1-IQ2_S | 0.7 | | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ2_M.gguf) | i1-IQ2_M | 0.7 | | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.8 | | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.9 | IQ3_XS probably better | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ3_S.gguf) | i1-IQ3_S | 0.9 | beats Q3_K* | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.0 | IQ3_M probably better | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.0 | | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.0 | prefer IQ4_XS | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q4_0.gguf) | i1-Q4_0 | 1.0 | fast, low quality | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q4_1.gguf) | i1-Q4_1 | 1.1 | | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.2 | | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.2 | | |
| | [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured-i1-GGUF/resolve/main/DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured.i1-Q6_K.gguf) | i1-Q6_K | 1.4 | 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 |
|
|
| ## 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](https://www.nethype.de/), for letting |
| me use its servers and providing upgrades to my workstation to enable |
| this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/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. |
| |
| <!-- end --> |
| |
