commit 3efb290bffea04bb3637a46e72faa3c058afa1bc Author: ModelHub XC Date: Tue Sep 29 13:17:20 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-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..63f3e2a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ1_M.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ1_M.gguf new file mode 100644 index 0000000..5b4aadb --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323ec9c7e6e837db54d3799e4accbdfbdc77860ae0b20902c2be3350131910fb +size 2161972896 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ1_S.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ1_S.gguf new file mode 100644 index 0000000..f700bb9 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb3245fb9b21115716ec61380aad87080b946ced74fbd5874e6bae09b384b28c +size 2019628704 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_M.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_M.gguf new file mode 100644 index 0000000..2c2feef --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6643b62408683a8e8e9475718834c615299bcb347b5cb62504e228dd527ed4c3 +size 2948282016 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_S.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_S.gguf new file mode 100644 index 0000000..60f8057 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cce32ce37a2e608012b5a30774e25da36f6053722c6a59e7627ea1811300bad +size 2758489760 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_XS.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_XS.gguf new file mode 100644 index 0000000..61d9575 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1315c38871eb758d0c4e5432dee1b1ff9c287df58601568f8e7947123eb3a2b8 +size 2605782688 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_XXS.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..6e9c72d --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:185f2c6ca59bbcca486c1a2069ca0d92931b4d1f4de993fdafb3a6ca27396dc5 +size 2399213216 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_M.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_M.gguf new file mode 100644 index 0000000..b578490 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf57396a3a115d11168e470470370703349362f237076d2d67b76d90ae755807 +size 3784824480 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_S.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_S.gguf new file mode 100644 index 0000000..629326d --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23f1abfcba3db7191abcf97407e1ee9471685c3ee4f067a5db86118a409d81f4 +size 3682326176 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_XS.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e2ca664 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e1b5779a5b5568fa9814d6cfed9b058e7633d9ce1b548f7409aa5e4e73e2956 +size 3518748320 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_XXS.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..53b4954 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6d76c64777b8d848092d939f05fe7f2c6f06dc9dd897779c9dc5fa60375e39a +size 3274913440 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ4_NL.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ4_NL.gguf new file mode 100644 index 0000000..51bbd40 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5c11da38718d14a7911c91502d48307ed581ece437038dc5c5d7c32f3143add +size 4677990048 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ4_XS.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ4_XS.gguf new file mode 100644 index 0000000..36e3f30 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d58d8aca1d45e904f6107a0a416aca044b5ec0e1813e4469ce2505400f523099 +size 4447663776 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q2_K.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q2_K.gguf new file mode 100644 index 0000000..edb13ac --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e12b6633c1f81ab37041736e2882ec8f42a6fc9e530822e39f3cf5ccf142e195 +size 3179132576 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q2_K_S.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q2_K_S.gguf new file mode 100644 index 0000000..2e90c5a --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:435e19f1532c0b3c5567828b814dbc2d99286c3fe178883657c86105df1526b9 +size 2988816032 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_L.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_L.gguf new file mode 100644 index 0000000..596368d --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59182c0eea9fd1988eb2a492ed6ef36268aae347737360745985acfd08ca39b9 +size 4321957536 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_M.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_M.gguf new file mode 100644 index 0000000..908782b --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0941dc57514a84d775c428db116d52a86e570b6762d955bb0e07aa05699b19f1 +size 4018919072 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_S.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_S.gguf new file mode 100644 index 0000000..726b6fc --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ef63af2a999402d6622a36f4b7842903deabcf904caaa54a5041387f47e000 +size 3664500384 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_0.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_0.gguf new file mode 100644 index 0000000..399d160 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1962adb665e637e139bfb8ecbcc203adeea05b33dbb3235273f0ee6811a22ebb +size 4675892896 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_1.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_1.gguf new file mode 100644 index 0000000..b17ce0c --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b2b808853d70a4f0ecdca8c3a2eaad16f12fc2b896f38ba5757db0c349439d9 +size 5130253984 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_K_M.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_K_M.gguf new file mode 100644 index 0000000..79ba4e8 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cacdafafbaed969ed54c61bb8fb51b37dd0ea7d3b4c62e34a08192c3ca4f89d9 +size 4920735392 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_K_S.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ea286ad --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e165b44b3ed7bf90e76ee4957c2ca064931c12bca77d43a1e8289adbcd462b +size 4692670112 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q5_K_M.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q5_K_M.gguf new file mode 100644 index 0000000..aec8b3a --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19509835137929c750b0c2dec0940837051dc47d7c276ea2e25de0a6676ad98a +size 5732988576 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q5_K_S.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q5_K_S.gguf new file mode 100644 index 0000000..4845333 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a5dd1b43fdeb800517c0cccd4b811553af5356846b9abcbabaf5ba78eb20de6 +size 5599295136 diff --git a/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q6_K.gguf b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q6_K.gguf new file mode 100644 index 0000000..ca99ba8 --- /dev/null +++ b/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:841b8c3874881cdbfccfd2ee787f7192a66eba5d2fbfb3a9f575e628dbba172b +size 6596007584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f24bdee --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +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 + + + + + + +weighted/imatrix quants of https://huggingface.co/AmberYifan/Llama-3.1-8B-sft-SPIN-gpt4o + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-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-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-SPIN-gpt4o-i1-GGUF/resolve/main/Llama-3.1-8B-sft-SPIN-gpt4o.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..dce079c --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04498fc46cbbe7e98010b05533d43744e629b7908d03bf3b0c7dc45771f0fa4 +size 4988157