commit e703b5c4f142cce6207c198e6fa32899a8e26929 Author: ModelHub XC Date: Sat Sep 12 08:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9df3ea4 --- /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 +Llama-3.1-8B-sft-SPIN-self.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-self.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-self.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-self.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-self.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-self.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-self.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-self.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-self.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-self.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-self.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-self.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-sft-SPIN-self.IQ4_XS.gguf b/Llama-3.1-8B-sft-SPIN-self.IQ4_XS.gguf new file mode 100644 index 0000000..007ba05 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:004c32a3ab5762847304c4ac66b9ee3a22bd4ce6134c955a16c8cb9e9599baf8 +size 4484368032 diff --git a/Llama-3.1-8B-sft-SPIN-self.Q2_K.gguf b/Llama-3.1-8B-sft-SPIN-self.Q2_K.gguf new file mode 100644 index 0000000..d8776fc --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ef7b77e5253be5ae889f06e41ab873141caf5bee5d63221333fd2299d5a043 +size 3179136672 diff --git a/Llama-3.1-8B-sft-SPIN-self.Q3_K_L.gguf b/Llama-3.1-8B-sft-SPIN-self.Q3_K_L.gguf new file mode 100644 index 0000000..2c75dbe --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:107a00b9d81f0886db44a40ad5df80da8e22ba0f0acea558a763ec0d56a0cf79 +size 4321961632 diff --git a/Llama-3.1-8B-sft-SPIN-self.Q3_K_M.gguf b/Llama-3.1-8B-sft-SPIN-self.Q3_K_M.gguf new file mode 100644 index 0000000..10db77a --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b98c5da5e33b3d7919e68f924b9f1794f5bc3776b9d9fe2e227abd460a659190 +size 4018923168 diff --git a/Llama-3.1-8B-sft-SPIN-self.Q3_K_S.gguf b/Llama-3.1-8B-sft-SPIN-self.Q3_K_S.gguf new file mode 100644 index 0000000..851d34d --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e55059b91649d18cf5a1dd23757bc2e6592a564f6ad85feb764f70f0167507b5 +size 3664504480 diff --git a/Llama-3.1-8B-sft-SPIN-self.Q4_K_M.gguf b/Llama-3.1-8B-sft-SPIN-self.Q4_K_M.gguf new file mode 100644 index 0000000..226c642 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d4e13247df9a8391a01fda9b3031072ae2fc90a3b92aeefac98eb9e5599946 +size 4920739488 diff --git a/Llama-3.1-8B-sft-SPIN-self.Q4_K_S.gguf b/Llama-3.1-8B-sft-SPIN-self.Q4_K_S.gguf new file mode 100644 index 0000000..6bb50d1 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4cadb78066d47077c16cd75336eb14f9a3064bc3d78621aada2b4ad4c3cb04d +size 4692674208 diff --git a/Llama-3.1-8B-sft-SPIN-self.Q5_K_M.gguf b/Llama-3.1-8B-sft-SPIN-self.Q5_K_M.gguf new file mode 100644 index 0000000..bd9080b --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32101aa70532c1e304262cfb66d530ad4f39278907c7f42a3580e64829b4aa61 +size 5732992672 diff --git a/Llama-3.1-8B-sft-SPIN-self.Q5_K_S.gguf b/Llama-3.1-8B-sft-SPIN-self.Q5_K_S.gguf new file mode 100644 index 0000000..6367767 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ff763720a8821e2109b624e805d3bae5bf0773a8a7f50b2fc675a3a0dd1ea24 +size 5599299232 diff --git a/Llama-3.1-8B-sft-SPIN-self.Q6_K.gguf b/Llama-3.1-8B-sft-SPIN-self.Q6_K.gguf new file mode 100644 index 0000000..e015781 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efb34971e35b6203e7b5d0469b122727b62ef931de7af2178672e30bfbdfdc03 +size 6596011680 diff --git a/Llama-3.1-8B-sft-SPIN-self.Q8_0.gguf b/Llama-3.1-8B-sft-SPIN-self.Q8_0.gguf new file mode 100644 index 0000000..9eaf791 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba8c26326a4a93381e995d7f899bf123912d3fcff973edd1f303cff0b1b1dd36 +size 8540776096 diff --git a/Llama-3.1-8B-sft-SPIN-self.f16.gguf b/Llama-3.1-8B-sft-SPIN-self.f16.gguf new file mode 100644 index 0000000..5b9b6a3 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-self.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a803d4b654b1404cab85c0f698e449442f0d17beda1cfb92995ef5089ea02a25 +size 16068896416 diff --git a/README.md b/README.md new file mode 100644 index 0000000..136f09b --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: AmberYifan/Llama-3.1-8B-sft-SPIN-self +language: +- en +library_name: transformers +model_name: Llama-3.1-8B-sft-SPIN-self +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-3.1-8B-sft-SPIN-self + + +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/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-self-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-self.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. + +