commit a938bf42bedcdfb7025d0bdbd8236a0484237804 Author: ModelHub XC Date: Sun Oct 4 17:31:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c86a811 --- /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-gpt4o.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.IQ4_XS.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.IQ4_XS.gguf new file mode 100644 index 0000000..1c9df71 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4349aa3e6276858b4109da950fe8fe5b4e2968b54afcd95a27cd92b0e0abe413 +size 4484363680 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.Q2_K.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.Q2_K.gguf new file mode 100644 index 0000000..8b11fb9 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80d653ef6e65b5b54f450c14e223e320022398491fc9f2c0be207d388f7a5b8c +size 3179132320 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_L.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_L.gguf new file mode 100644 index 0000000..c08ec24 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d436317e679e10d44a73d3b6085281faa9423447ee7c2f61295fde44b8945da +size 4321957280 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_M.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_M.gguf new file mode 100644 index 0000000..d391a85 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b620d4d7d3161202d064e16c81f4351de4862e11c5a6d9e8b8c802052f70c4dd +size 4018918816 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_S.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_S.gguf new file mode 100644 index 0000000..096b9ea --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdcd8c5411abb19f7319143a87e6d9f1d4033137e358945a492257cc7ddb6e3e +size 3664500128 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.Q4_K_M.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.Q4_K_M.gguf new file mode 100644 index 0000000..b3a71b1 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1d81632cc70cbc0b3eabb41c0205a49c704b5214d0dd721e185399ecf068f3 +size 4920735136 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.Q4_K_S.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.Q4_K_S.gguf new file mode 100644 index 0000000..23826f8 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94a40819b9b506ac66da9148a0a87e74cd490c62ce622f19f70602a11edaad68 +size 4692669856 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.Q5_K_M.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.Q5_K_M.gguf new file mode 100644 index 0000000..52a6dfd --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c46ef8876b8ffa086e01f76c762a2a248733e0e97f2a9e827506a97f9a9658c4 +size 5732988320 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.Q5_K_S.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.Q5_K_S.gguf new file mode 100644 index 0000000..0872eac --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd6a45712f7b9c4cd90ee26b7b3042172d31cbac1087dbe437c229c3012fab7 +size 5599294880 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.Q6_K.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.Q6_K.gguf new file mode 100644 index 0000000..9c18148 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee1841a8fdce59185a2de6a372cbf7a4e31496ba38fedd16c20bc27df1da7c3c +size 6596007328 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.Q8_0.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.Q8_0.gguf new file mode 100644 index 0000000..ebb7785 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2244739263851f86523c03521bedaa32163c2e014b625618492b3c2c54f87a6 +size 8540771744 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.f16.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.f16.gguf new file mode 100644 index 0000000..1a0dc7a --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:903757c21de68c3bc1195f769d04225e6db5a20b37d5ef3c4a8e1b8c8baf82d0 +size 16068892064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a236174 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: AmberYifan/Llama-3.1-8B-sft-SPIN-gpt4o +language: +- en +library_name: transformers +model_name: Llama-3.1-8B-sft-SPIN-gpt4o +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-3.1-8B-sft-SPIN-gpt4o + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-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/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.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. + +