commit 52df4fc334cc897e2fb14d01ed1766af96c9b482 Author: ModelHub XC Date: Wed Sep 30 04:15:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Sam-flash-mini-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4bdb9cd --- /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 +Sam-flash-mini-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Sam-flash-mini-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Sam-flash-mini-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Sam-flash-mini-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sam-flash-mini-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sam-flash-mini-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sam-flash-mini-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sam-flash-mini-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sam-flash-mini-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sam-flash-mini-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Sam-flash-mini-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Sam-flash-mini-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f39d59f --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Smilyai-labs/Sam-flash-mini-v1 +language: en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- gpt2 +- distilgpt2 +- smilyai +- sam-flash +--- +## About + + + + + + +static quants of https://huggingface.co/Smilyai-labs/Sam-flash-mini-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Sam-flash-mini-v1-GGUF).*** + +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/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Sam-flash-mini-v1-GGUF/resolve/main/Sam-flash-mini-v1.f16.gguf) | f16 | 0.3 | 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/Sam-flash-mini-v1.IQ4_XS.gguf b/Sam-flash-mini-v1.IQ4_XS.gguf new file mode 100644 index 0000000..ca450e3 --- /dev/null +++ b/Sam-flash-mini-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ec04a540b5912b0e53b456a94649660d958d8d60d39cf29623918daefc8935c +size 59386176 diff --git a/Sam-flash-mini-v1.Q2_K.gguf b/Sam-flash-mini-v1.Q2_K.gguf new file mode 100644 index 0000000..38f12a2 --- /dev/null +++ b/Sam-flash-mini-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b4d0fdf6bebd721f1b949ca8071f46ec87f6cc74fe5741299d4503c224168a2 +size 52557120 diff --git a/Sam-flash-mini-v1.Q3_K_L.gguf b/Sam-flash-mini-v1.Q3_K_L.gguf new file mode 100644 index 0000000..1b0e79b --- /dev/null +++ b/Sam-flash-mini-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f1aa8a5fc4a3d47773184e78226e7a8e2e060da0fed07e65d5f82dce3ac5ea2 +size 61045056 diff --git a/Sam-flash-mini-v1.Q3_K_M.gguf b/Sam-flash-mini-v1.Q3_K_M.gguf new file mode 100644 index 0000000..4161bbb --- /dev/null +++ b/Sam-flash-mini-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ff99bb29c68678086de702fbbad1975702574663c55781fbbbd718f9697e9bc +size 58833216 diff --git a/Sam-flash-mini-v1.Q3_K_S.gguf b/Sam-flash-mini-v1.Q3_K_S.gguf new file mode 100644 index 0000000..c199e95 --- /dev/null +++ b/Sam-flash-mini-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595a098e47c8e674d273d8b4e829a070f7fae8e435625a9f7a6da4188d5d4c60 +size 55073088 diff --git a/Sam-flash-mini-v1.Q4_K_M.gguf b/Sam-flash-mini-v1.Q4_K_M.gguf new file mode 100644 index 0000000..b9f4795 --- /dev/null +++ b/Sam-flash-mini-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e445ccb807541660c09aae86f328e4901d557f2f318336c2a3a133c1a94921e6 +size 63256896 diff --git a/Sam-flash-mini-v1.Q4_K_S.gguf b/Sam-flash-mini-v1.Q4_K_S.gguf new file mode 100644 index 0000000..7d32909 --- /dev/null +++ b/Sam-flash-mini-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:024348e39d1a64c316aca9de40ff4618eb38baf02a03bcddac3124ad97a749f4 +size 60713280 diff --git a/Sam-flash-mini-v1.Q5_K_M.gguf b/Sam-flash-mini-v1.Q5_K_M.gguf new file mode 100644 index 0000000..7b342b7 --- /dev/null +++ b/Sam-flash-mini-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98f5c038bb4e13c52ce0a516f3db5d3d8e823d730fe56f8e0a312adcd59ae9ee +size 68058432 diff --git a/Sam-flash-mini-v1.Q5_K_S.gguf b/Sam-flash-mini-v1.Q5_K_S.gguf new file mode 100644 index 0000000..e335759 --- /dev/null +++ b/Sam-flash-mini-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed00e7729362261d46722744048c111d5c93735f47a0ee8778ab4a6108d873d +size 66021696 diff --git a/Sam-flash-mini-v1.Q6_K.gguf b/Sam-flash-mini-v1.Q6_K.gguf new file mode 100644 index 0000000..fb3b229 --- /dev/null +++ b/Sam-flash-mini-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:215c80aa117bc6666eaa41a92d7846a6171b65a50d81adc01a8b86cecacd2516 +size 71661888 diff --git a/Sam-flash-mini-v1.Q8_0.gguf b/Sam-flash-mini-v1.Q8_0.gguf new file mode 100644 index 0000000..ae4ff53 --- /dev/null +++ b/Sam-flash-mini-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d32db1065668a38a2b473975942d1a03dbcc1c58c875fc755e0cc2b939f876 +size 91294752 diff --git a/Sam-flash-mini-v1.f16.gguf b/Sam-flash-mini-v1.f16.gguf new file mode 100644 index 0000000..1ab70f1 --- /dev/null +++ b/Sam-flash-mini-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bfc278603541c6419058222a185b575aba97f6e47c980b343e74ce827214e77 +size 167292896