commit 1db4c3caa0b96a79cb5deb2162145c8d9055b6f7 Author: ModelHub XC Date: Fri Oct 2 23:59:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2e07490 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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-3-15B-Instruct-ft-v2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-15B-Instruct-ft-v2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-15B-Instruct-ft-v2.i1-IQ1_M.gguf b/Llama-3-15B-Instruct-ft-v2.i1-IQ1_M.gguf new file mode 100644 index 0000000..137ab6c --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c28e51a6a3d35733435f265fb92e0039b4ac1530d2e33b175115e059812db8c9 +size 3782564576 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-IQ1_S.gguf b/Llama-3-15B-Instruct-ft-v2.i1-IQ1_S.gguf new file mode 100644 index 0000000..8d2abf7 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cfc8c58c492a880854ed82b43b0d14e74e8266834410f4b08cee5c9621e1f48 +size 3497876192 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-IQ2_M.gguf b/Llama-3-15B-Instruct-ft-v2.i1-IQ2_M.gguf new file mode 100644 index 0000000..85ab29e --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f2b275665c38c5abb4ec2cd55ed0d61ce16f1eb0e563580545a6d0a7546c71 +size 5301828320 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-IQ2_S.gguf b/Llama-3-15B-Instruct-ft-v2.i1-IQ2_S.gguf new file mode 100644 index 0000000..52a95c0 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2eab505a864744d408f99a80b32e558954171e7d5fd4e71b48ce96d169c5cef +size 4922243808 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-IQ2_XS.gguf b/Llama-3-15B-Instruct-ft-v2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..32c8b2c --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b37964e3d5e2374d7d44c72a613afe3151f71c7d153f0506487eed3c1d64aa99 +size 4670184160 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-IQ2_XXS.gguf b/Llama-3-15B-Instruct-ft-v2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..62f0341 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d8ce6a5707d8020c8fb33786c3fc7f0429db8a743c09cd53c416fd6b4729763 +size 4257045216 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-IQ3_M.gguf b/Llama-3-15B-Instruct-ft-v2.i1-IQ3_M.gguf new file mode 100644 index 0000000..412763e --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942e7693a6f815a178cc3d542c0b6d9564468b79317ab732a8336547b10cc92a +size 6905141984 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-IQ3_S.gguf b/Llama-3-15B-Instruct-ft-v2.i1-IQ3_S.gguf new file mode 100644 index 0000000..c84e493 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be9314f7280e39a767e1c81c800cb51599ae08b7eb069e55abc10e6713d1fca8 +size 6700145376 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-IQ3_XS.gguf b/Llama-3-15B-Instruct-ft-v2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..3a57c16 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c68e1e437add6bb24b4ddff18911534e86c995dfbdbb01c9f130a387ea584f8a +size 6372989664 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-IQ3_XXS.gguf b/Llama-3-15B-Instruct-ft-v2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..50d316e --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d0077d4e02c5cb8afe4d23aacdbea5b989e365c7f5c73ec7564c5c68e38b26c +size 5955091168 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-IQ4_XS.gguf b/Llama-3-15B-Instruct-ft-v2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..c67649f --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39f17e9a5989c097491a23ed1f5597628bf3d6f3c8c984bd201e875d03306daa +size 8177466080 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-Q2_K.gguf b/Llama-3-15B-Instruct-ft-v2.i1-Q2_K.gguf new file mode 100644 index 0000000..a414546 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cceda6c80b71b790ed50dac4ecb94ca55e4aa7e0a744b7b0aade61c260d3b635 +size 5747112672 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-Q2_K_S.gguf b/Llama-3-15B-Instruct-ft-v2.i1-Q2_K_S.gguf new file mode 100644 index 0000000..10ed8c6 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be312f4b4dee160a05e7f790aa3392f3dcd7436b99dc3fd359ce4241fdb77d50 +size 5366479584 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_L.gguf b/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ae20b05 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d71a832421cbac233f36623c3277ff7e9ddf961ef7a9984bc5a982e6fcbd3b2 +size 7979408096 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_M.gguf b/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a4a3596 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8777f2d827d603e3927e0f3ef1261a472192cfd4efaad4f910be653c066c2b24 +size 7372282592 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_S.gguf b/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..9d48c48 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae0359bb691e661e1c358ae578b6cd5dd148782845129a1c2e07a9d13b26d0dd +size 6664493792 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-Q4_0.gguf b/Llama-3-15B-Instruct-ft-v2.i1-Q4_0.gguf new file mode 100644 index 0000000..3a626ea --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657541e96e9f85f8270c6a26154f840f9ec140b7daa3be445e6919723e8a31bb +size 8617507552 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-Q4_K_M.gguf b/Llama-3-15B-Instruct-ft-v2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..0224ef7 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c86c89386a403acafb12f9dbe1caa7c0180a726a69f907d6f16ff38f4c0afc97 +size 9107192544 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-Q4_K_S.gguf b/Llama-3-15B-Instruct-ft-v2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..576be10 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039c20393a971f63fc3af7f45a781d63d97d84b0d17b9729e7e8decc2fc1cad8 +size 8648964832 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-Q5_K_M.gguf b/Llama-3-15B-Instruct-ft-v2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a949963 --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d62dc26a31fcbe9ad60dc6e801765d644ce47ebf3956242c3406e1209a4315bd +size 10666031840 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-Q5_K_S.gguf b/Llama-3-15B-Instruct-ft-v2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..473e3df --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24aa0d5dce783dd9f310fba8947309a196ec8f8a53fe5578e3e1b658b4b7e4a8 +size 10398644960 diff --git a/Llama-3-15B-Instruct-ft-v2.i1-Q6_K.gguf b/Llama-3-15B-Instruct-ft-v2.i1-Q6_K.gguf new file mode 100644 index 0000000..c23848a --- /dev/null +++ b/Llama-3-15B-Instruct-ft-v2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fffe516d214562e88cf9ddcedb7faf172131543537d6fbd227e920c5b17401a +size 12322298592 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c1aaee1 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: elinas/Llama-3-15B-Instruct-ft-v2 +datasets: +- Chat-Error/Pure-dove-sharegpt +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- mergekit +- merge +- finetune +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/elinas/Llama-3-15B-Instruct-ft-v2 + + +static quants are available at https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-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-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-IQ1_S.gguf) | i1-IQ1_S | 3.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-IQ1_M.gguf) | i1-IQ1_M | 3.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-IQ2_S.gguf) | i1-IQ2_S | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-Q2_K.gguf) | i1-Q2_K | 5.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-Q4_0.gguf) | i1-Q4_0 | 8.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-15B-Instruct-ft-v2-i1-GGUF/resolve/main/Llama-3-15B-Instruct-ft-v2.i1-Q6_K.gguf) | i1-Q6_K | 12.4 | 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..41e374f --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a42f41604bcb7349a53be569fb800c73ee7c0055bc51702a09fa6ea2f21dacd0 +size 9976349