| | --- |
| | base_model: diffusionfamily/diffullama |
| | datasets: |
| | - bigcode/starcoderdata |
| | - cerebras/SlimPajama-627B |
| | language: |
| | - en |
| | library_name: transformers |
| | license: apache-2.0 |
| | mradermacher: |
| | readme_rev: 1 |
| | quantized_by: mradermacher |
| | tags: |
| | - llama-factory |
| | - full |
| | - diffusion |
| | --- |
| | ## About |
| |
|
| | <!-- ### quantize_version: 2 --> |
| | <!-- ### output_tensor_quantised: 1 --> |
| | <!-- ### convert_type: hf --> |
| | <!-- ### vocab_type: --> |
| | <!-- ### tags: --> |
| | static quants of https://huggingface.co/diffusionfamily/diffullama |
| | |
| | <!-- provided-files --> |
| | |
| | ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#diffullama-GGUF).*** |
| | |
| | weighted/imatrix quants are available at https://huggingface.co/mradermacher/diffullama-i1-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/diffullama-GGUF/resolve/main/diffullama.Q2_K.gguf) | Q2_K | 2.6 | | |
| | | [GGUF](https://huggingface.co/mradermacher/diffullama-GGUF/resolve/main/diffullama.Q3_K_S.gguf) | Q3_K_S | 3.0 | | |
| | | [GGUF](https://huggingface.co/mradermacher/diffullama-GGUF/resolve/main/diffullama.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | |
| | | [GGUF](https://huggingface.co/mradermacher/diffullama-GGUF/resolve/main/diffullama.Q3_K_L.gguf) | Q3_K_L | 3.7 | | |
| | | [GGUF](https://huggingface.co/mradermacher/diffullama-GGUF/resolve/main/diffullama.IQ4_XS.gguf) | IQ4_XS | 3.7 | | |
| | | [GGUF](https://huggingface.co/mradermacher/diffullama-GGUF/resolve/main/diffullama.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | |
| | | [GGUF](https://huggingface.co/mradermacher/diffullama-GGUF/resolve/main/diffullama.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | |
| | | [GGUF](https://huggingface.co/mradermacher/diffullama-GGUF/resolve/main/diffullama.Q5_K_S.gguf) | Q5_K_S | 4.8 | | |
| | | [GGUF](https://huggingface.co/mradermacher/diffullama-GGUF/resolve/main/diffullama.Q5_K_M.gguf) | Q5_K_M | 4.9 | | |
| | | [GGUF](https://huggingface.co/mradermacher/diffullama-GGUF/resolve/main/diffullama.Q6_K.gguf) | Q6_K | 5.6 | very good quality | |
| | | [GGUF](https://huggingface.co/mradermacher/diffullama-GGUF/resolve/main/diffullama.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | |
| | | [GGUF](https://huggingface.co/mradermacher/diffullama-GGUF/resolve/main/diffullama.f16.gguf) | f16 | 13.6 | 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](https://www.nethype.de/), for letting |
| | me use its servers and providing upgrades to my workstation to enable |
| | this work in my free time. |
| |
|
| | <!-- end --> |
| |
|
