commit 9d56ed4e0be7a3a2c07db06bcf45f55186b9ac95 Author: ModelHub XC Date: Fri Jun 26 06:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Doctoraifinetune-3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a3c038b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Doctoraifinetune-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Doctoraifinetune-3.1-8B.IQ4_XS.gguf b/Doctoraifinetune-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..8d40066 --- /dev/null +++ b/Doctoraifinetune-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e888f9c208dd2a584c3031301815f9e4a14b2349504f84abcd01de74bdec554b +size 4484364288 diff --git a/Doctoraifinetune-3.1-8B.Q2_K.gguf b/Doctoraifinetune-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..ba02d9d --- /dev/null +++ b/Doctoraifinetune-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d48bee3d3d66c389db902e59916747a2a8b515d4a1dfffbf522a10189d35851 +size 3179132928 diff --git a/Doctoraifinetune-3.1-8B.Q3_K_L.gguf b/Doctoraifinetune-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..3462531 --- /dev/null +++ b/Doctoraifinetune-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9fbc92e07243b81fb7cd122cecb26b6e271dcdf9544712393a0c9c53b9896a2 +size 4321957888 diff --git a/Doctoraifinetune-3.1-8B.Q3_K_M.gguf b/Doctoraifinetune-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..cc2b06e --- /dev/null +++ b/Doctoraifinetune-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:893a47bb2c0101b5287dd19a4f511a52179ee67ccc5cda8e87704e1cf50c60cb +size 4018919424 diff --git a/Doctoraifinetune-3.1-8B.Q3_K_S.gguf b/Doctoraifinetune-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..5329fcf --- /dev/null +++ b/Doctoraifinetune-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322a804b20b0e57dbc586e4a588cdaedd9a95dbb70353db6fb92d13fc939198c +size 3664500736 diff --git a/Doctoraifinetune-3.1-8B.Q4_K_M.gguf b/Doctoraifinetune-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..6a9f069 --- /dev/null +++ b/Doctoraifinetune-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd53d01d9b5767158fa120615bfe2c1c685341995dba013cdaf5f6e915839c4 +size 4920735744 diff --git a/Doctoraifinetune-3.1-8B.Q4_K_S.gguf b/Doctoraifinetune-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..5696863 --- /dev/null +++ b/Doctoraifinetune-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3655c7f77f75fd459e81f07ee553ddf5d0218b8c5ac42566c0814ccac5ff6dde +size 4692670464 diff --git a/Doctoraifinetune-3.1-8B.Q5_K_M.gguf b/Doctoraifinetune-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..342d33d --- /dev/null +++ b/Doctoraifinetune-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45deaa098c0c9bb8217d162151e6fdbdf37205b29f03c862fb2f8932a0f7f532 +size 5732988928 diff --git a/Doctoraifinetune-3.1-8B.Q5_K_S.gguf b/Doctoraifinetune-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..857ac91 --- /dev/null +++ b/Doctoraifinetune-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b743999dc7635eff32496a09741129bcc6e867567525de5464cebcd45a272d63 +size 5599295488 diff --git a/Doctoraifinetune-3.1-8B.Q6_K.gguf b/Doctoraifinetune-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..7b8bb37 --- /dev/null +++ b/Doctoraifinetune-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65169dcce08df7a3594c3992a94162bbb4ceefb2ce71742218e2658230d8bb21 +size 6596007936 diff --git a/Doctoraifinetune-3.1-8B.Q8_0.gguf b/Doctoraifinetune-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..27f6fef --- /dev/null +++ b/Doctoraifinetune-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:238b335822591e8c97415a87b18e17bc2ec9cebf8dbc07cb8feae8212d5b2d17 +size 8540772352 diff --git a/Doctoraifinetune-3.1-8B.f16.gguf b/Doctoraifinetune-3.1-8B.f16.gguf new file mode 100644 index 0000000..6daff7e --- /dev/null +++ b/Doctoraifinetune-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be67baaa76bb427d67ccbd1fd0e94884e1fd92e5136942aa713eddc7b69efe9 +size 16068892672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..83e5dd1 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: huzaifa525/Doctoraifinetune-3.1-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/huzaifa525/Doctoraifinetune-3.1-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-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/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Doctoraifinetune-3.1-8B-GGUF/resolve/main/Doctoraifinetune-3.1-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.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](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +