commit 70e3a9e7fe06013e7de1f41db96ce5b46fda6644 Author: ModelHub XC Date: Thu Apr 23 23:35:01 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SmolTuring-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..81f154f --- /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 +SmolTuring-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolTuring-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolTuring-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolTuring-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolTuring-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolTuring-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolTuring-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +SmolTuring-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolTuring-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolTuring-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolTuring-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolTuring-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3e3c91b --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: safe049/SmolTuring-8B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/safe049/SmolTuring-8B-Instruct + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmolTuring-8B-Instruct-GGUF/resolve/main/SmolTuring-8B-Instruct.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. + + diff --git a/SmolTuring-8B-Instruct.IQ4_XS.gguf b/SmolTuring-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..bc076b2 --- /dev/null +++ b/SmolTuring-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d8a8e000aecd26261ace7b841cd665dbbd909f4a571237715fc2e0bcedf9d4d +size 4484368320 diff --git a/SmolTuring-8B-Instruct.Q2_K.gguf b/SmolTuring-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..d243046 --- /dev/null +++ b/SmolTuring-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d861d2799461300de5ed22b9ae2a5bc5037096167d0b484edf9bd568166fa31 +size 3179136960 diff --git a/SmolTuring-8B-Instruct.Q3_K_L.gguf b/SmolTuring-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..9106263 --- /dev/null +++ b/SmolTuring-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c1a28e301774761daa9e6f5d216a4c84bf191c417e8002ebcde1a3b4c04b0a +size 4321961920 diff --git a/SmolTuring-8B-Instruct.Q3_K_M.gguf b/SmolTuring-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..6d23afc --- /dev/null +++ b/SmolTuring-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f884a45d9c7399978b4ec20271c4f6a8ced98b8203060250f9027d8193c9e182 +size 4018923456 diff --git a/SmolTuring-8B-Instruct.Q3_K_S.gguf b/SmolTuring-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..aec1357 --- /dev/null +++ b/SmolTuring-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52799079b7ce7af24a80c80246643b84f1315f8a587037f72ad1f8d167c08f8b +size 3664504768 diff --git a/SmolTuring-8B-Instruct.Q4_K_M.gguf b/SmolTuring-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..eab5bc6 --- /dev/null +++ b/SmolTuring-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b713d88995c1228a4584477fa57f89662d99ef9192adbd17070353908ef0a23 +size 4920739776 diff --git a/SmolTuring-8B-Instruct.Q4_K_S.gguf b/SmolTuring-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..c7409aa --- /dev/null +++ b/SmolTuring-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc29ac4af48228fced6cf359fa782e68a3d46eed394c0db7d9fdaf8a003d147a +size 4692674496 diff --git a/SmolTuring-8B-Instruct.Q5_K_M.gguf b/SmolTuring-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..cc20fec --- /dev/null +++ b/SmolTuring-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b1519996c56bda8298200ee3f6415a2c009db7a573740e92cab032efac4b6e +size 5732992960 diff --git a/SmolTuring-8B-Instruct.Q5_K_S.gguf b/SmolTuring-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..06c3d4d --- /dev/null +++ b/SmolTuring-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206fff3ed6b8c961f1c653a6fd584206e7969cc2b163ddb81aff922924d1192b +size 5599299520 diff --git a/SmolTuring-8B-Instruct.Q6_K.gguf b/SmolTuring-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..dd1c268 --- /dev/null +++ b/SmolTuring-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22ce9dfe046013268f620eff054b4146b5f7224ec268669c38701cd84454affd +size 6596011968 diff --git a/SmolTuring-8B-Instruct.Q8_0.gguf b/SmolTuring-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..ebb608b --- /dev/null +++ b/SmolTuring-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dbda703dd9b28d0b317a8150eef6aaa360888378875c69a19183cb86433a489 +size 8540776384 diff --git a/SmolTuring-8B-Instruct.f16.gguf b/SmolTuring-8B-Instruct.f16.gguf new file mode 100644 index 0000000..17a3986 --- /dev/null +++ b/SmolTuring-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba8e2af49ba4c913ca6e06cbe64cc87b912d583efeacb3fa0d0e4d60f046c458 +size 16068896704