From 087f31bfc57005d4c61ea6bb439533e6fb4c86f0 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 6 Nov 2026 02:59:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF Source: Original Platform --- .gitattributes | 73 ++++++++++++ LiquidAI_LFM2-1.2B-Tool-IQ2_M.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-IQ3_M.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-IQ3_XS.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-IQ3_XXS.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-IQ4_NL.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-IQ4_XS.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q2_K.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q2_K_L.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q3_K_L.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q3_K_M.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q3_K_S.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q3_K_XL.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q4_0.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q4_1.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q4_K_L.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q4_K_M.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q4_K_S.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q5_K_L.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q5_K_M.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q5_K_S.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q6_K.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q6_K_L.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-Q8_0.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-bf16.gguf | 3 + LiquidAI_LFM2-1.2B-Tool-imatrix.gguf | 3 + README.md | 164 +++++++++++++++++++++++++++ configuration.json | 1 + 28 files changed, 313 insertions(+) create mode 100644 .gitattributes create mode 100644 LiquidAI_LFM2-1.2B-Tool-IQ2_M.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-IQ3_M.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-IQ3_XS.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-IQ3_XXS.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-IQ4_NL.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-IQ4_XS.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q2_K.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q2_K_L.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q3_K_L.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q3_K_M.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q3_K_S.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q3_K_XL.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q4_0.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q4_1.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q4_K_L.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q4_K_M.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q4_K_S.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q5_K_L.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q5_K_M.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q5_K_S.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q6_K.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q6_K_L.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-Q8_0.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-bf16.gguf create mode 100644 LiquidAI_LFM2-1.2B-Tool-imatrix.gguf create mode 100644 README.md create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5ef3fd4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,73 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +LiquidAI_LFM2-1.2B-Tool-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-bf16.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LiquidAI_LFM2-1.2B-Tool-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/LiquidAI_LFM2-1.2B-Tool-IQ2_M.gguf b/LiquidAI_LFM2-1.2B-Tool-IQ2_M.gguf new file mode 100644 index 0000000..2c45cca --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f00daa7bc09b14fb20888a90ecd9529ce4d052e48774166a6f1090b68ed3152d +size 434131488 diff --git a/LiquidAI_LFM2-1.2B-Tool-IQ3_M.gguf b/LiquidAI_LFM2-1.2B-Tool-IQ3_M.gguf new file mode 100644 index 0000000..2d5daa9 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a9765633954adff608b116bcbae28a178ba445a1af2225aea21d2e7ab10070 +size 566792736 diff --git a/LiquidAI_LFM2-1.2B-Tool-IQ3_XS.gguf b/LiquidAI_LFM2-1.2B-Tool-IQ3_XS.gguf new file mode 100644 index 0000000..30d65b9 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d2141f72e721bda4332d3720a3fb85ab2128963c3bcfadf82a08c5cc29af5ec +size 537809440 diff --git a/LiquidAI_LFM2-1.2B-Tool-IQ3_XXS.gguf b/LiquidAI_LFM2-1.2B-Tool-IQ3_XXS.gguf new file mode 100644 index 0000000..236ce80 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a60979bb891a005148ad337b7415983261de6a74768d4dc47769f043430585d +size 490983968 diff --git a/LiquidAI_LFM2-1.2B-Tool-IQ4_NL.gguf b/LiquidAI_LFM2-1.2B-Tool-IQ4_NL.gguf new file mode 100644 index 0000000..89ea40e --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb3a7efe14806aab69ae3d0e1873238c7cdf23f9b5e3977793c0fa5f1f19c6d +size 695751200 diff --git a/LiquidAI_LFM2-1.2B-Tool-IQ4_XS.gguf b/LiquidAI_LFM2-1.2B-Tool-IQ4_XS.gguf new file mode 100644 index 0000000..a30cfea --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4302b7ba57de40c7b1160b6cbe13ead2b72034e710728c23d99cabb4460f8e9b +size 663376416 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q2_K.gguf b/LiquidAI_LFM2-1.2B-Tool-Q2_K.gguf new file mode 100644 index 0000000..288c648 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de01275b7965c39957724b52544749722f940321d5769c765a80b28b7e577a8b +size 483398176 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q2_K_L.gguf b/LiquidAI_LFM2-1.2B-Tool-Q2_K_L.gguf new file mode 100644 index 0000000..6bd5513 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41e3240f6d097c4d20e636c79451a7e45b457b2df1d7d7950e344277ef1ae7ce +size 515904032 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q3_K_L.gguf b/LiquidAI_LFM2-1.2B-Tool-Q3_K_L.gguf new file mode 100644 index 0000000..26497e2 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2133dcb23deaef2a825ca36e304ad86f0901f4d10461fd7547f52dbeaa0e40fe +size 635474464 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q3_K_M.gguf b/LiquidAI_LFM2-1.2B-Tool-Q3_K_M.gguf new file mode 100644 index 0000000..3639d3f --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c95a5d42b1cb9ad039d387cae512fce7e69f55c779494b429d05cbbef1d094c +size 600347168 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q3_K_S.gguf b/LiquidAI_LFM2-1.2B-Tool-Q3_K_S.gguf new file mode 100644 index 0000000..350f616 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd883f80bce3f9d6d1088aef9ef5bfcfa0360b52ed274ae7861c8e203e3c5079 +size 558158368 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q3_K_XL.gguf b/LiquidAI_LFM2-1.2B-Tool-Q3_K_XL.gguf new file mode 100644 index 0000000..3c81e83 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04def197579d7dd6d06143fb4c7645d1a91fbfbcb74e1965fceb79ecf1f3fd46 +size 667980320 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q4_0.gguf b/LiquidAI_LFM2-1.2B-Tool-Q4_0.gguf new file mode 100644 index 0000000..77bc50f --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e22399c8efab48dce8abf95a10ee9424e3ff4be01ac531a9ea3fbff8cd30b8e5 +size 697848352 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q4_1.gguf b/LiquidAI_LFM2-1.2B-Tool-Q4_1.gguf new file mode 100644 index 0000000..7e27a54 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c71fdc438679510775569e8d27546bcf3f690c33b5adbab08e8555ed18e3d34 +size 760500768 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q4_K_L.gguf b/LiquidAI_LFM2-1.2B-Tool-Q4_K_L.gguf new file mode 100644 index 0000000..2a4b1d9 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e66dfb97cb9f6a5259704f3f323c117490a20ac1a9e5b7fa4c7c60cfee6a3a2 +size 763400736 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q4_K_M.gguf b/LiquidAI_LFM2-1.2B-Tool-Q4_K_M.gguf new file mode 100644 index 0000000..c5a6586 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bdf2292a137c12264a065d73c12b61065293440b753249727cec0b6dc350d64 +size 730894880 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q4_K_S.gguf b/LiquidAI_LFM2-1.2B-Tool-Q4_K_S.gguf new file mode 100644 index 0000000..c939f4b --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7311ecb492afe453750ee6356763a9275e76cb1f93e765def1802a5f1faaf4bc +size 700469792 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q5_K_L.gguf b/LiquidAI_LFM2-1.2B-Tool-Q5_K_L.gguf new file mode 100644 index 0000000..4bde1ff --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04d2c077c4bacafe38fe7cba9d4175ddb151030e869610a86927198e5598126 +size 875860512 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q5_K_M.gguf b/LiquidAI_LFM2-1.2B-Tool-Q5_K_M.gguf new file mode 100644 index 0000000..887dfb5 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f52d446aacd440b4d451f52703cc4f69fe39a637ba939e6d644dacff04188191 +size 843354656 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q5_K_S.gguf b/LiquidAI_LFM2-1.2B-Tool-Q5_K_S.gguf new file mode 100644 index 0000000..eb567c7 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ece7011e9ec0ad5f84b016bfa9c50c4c4f86c33575ab7204aaeca0bc3cb5e59 +size 825250336 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q6_K.gguf b/LiquidAI_LFM2-1.2B-Tool-Q6_K.gguf new file mode 100644 index 0000000..300569b --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c1f1ef1fcfc81b6b047123bc6d23a327ce80e83dc2001b42ce043c08631f3bd +size 962843168 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q6_K_L.gguf b/LiquidAI_LFM2-1.2B-Tool-Q6_K_L.gguf new file mode 100644 index 0000000..22803ed --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b93f8aa32246d3f806ffa83673dd3712f5c427a36c924ac54009b0e27bd5194 +size 995349024 diff --git a/LiquidAI_LFM2-1.2B-Tool-Q8_0.gguf b/LiquidAI_LFM2-1.2B-Tool-Q8_0.gguf new file mode 100644 index 0000000..7dd27d1 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b05f48f31e7d0e7bc9b369c24abed6ff22df2d34868b78ff9dd0bcb90c5a21c +size 1246253600 diff --git a/LiquidAI_LFM2-1.2B-Tool-bf16.gguf b/LiquidAI_LFM2-1.2B-Tool-bf16.gguf new file mode 100644 index 0000000..bb95801 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2897913d03b5466309689329124f8ff707b7f39cb93b3b025562eeebc3e0569d +size 2343325952 diff --git a/LiquidAI_LFM2-1.2B-Tool-imatrix.gguf b/LiquidAI_LFM2-1.2B-Tool-imatrix.gguf new file mode 100644 index 0000000..dab62a7 --- /dev/null +++ b/LiquidAI_LFM2-1.2B-Tool-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e128463ecc515b6a1a3cc3c6544438b391ea335c0a6aa68672f2d48828399f08 +size 1161536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6bca41f --- /dev/null +++ b/README.md @@ -0,0 +1,164 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: LiquidAI/LFM2-1.2B-Tool +--- + +## Llamacpp imatrix Quantizations of LFM2-1.2B-Tool by LiquidAI + +Using llama.cpp release b6683 for quantization. + +Original model: https://huggingface.co/LiquidAI/LFM2-1.2B-Tool + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project + +## Prompt format + +No prompt format found, check original model page + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [LFM2-1.2B-Tool-bf16.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-bf16.gguf) | bf16 | 2.34GB | false | Full BF16 weights. | +| [LFM2-1.2B-Tool-Q8_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q8_0.gguf) | Q8_0 | 1.25GB | false | Extremely high quality, generally unneeded but max available quant. | +| [LFM2-1.2B-Tool-Q6_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q6_K_L.gguf) | Q6_K_L | 1.00GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [LFM2-1.2B-Tool-Q6_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q6_K.gguf) | Q6_K | 0.96GB | false | Very high quality, near perfect, *recommended*. | +| [LFM2-1.2B-Tool-Q5_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q5_K_L.gguf) | Q5_K_L | 0.88GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [LFM2-1.2B-Tool-Q5_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q5_K_M.gguf) | Q5_K_M | 0.84GB | false | High quality, *recommended*. | +| [LFM2-1.2B-Tool-Q5_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q5_K_S.gguf) | Q5_K_S | 0.83GB | false | High quality, *recommended*. | +| [LFM2-1.2B-Tool-Q4_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q4_K_L.gguf) | Q4_K_L | 0.76GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [LFM2-1.2B-Tool-Q4_1.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q4_1.gguf) | Q4_1 | 0.76GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [LFM2-1.2B-Tool-Q4_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q4_K_M.gguf) | Q4_K_M | 0.73GB | false | Good quality, default size for most use cases, *recommended*. | +| [LFM2-1.2B-Tool-Q4_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q4_K_S.gguf) | Q4_K_S | 0.70GB | false | Slightly lower quality with more space savings, *recommended*. | +| [LFM2-1.2B-Tool-Q4_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q4_0.gguf) | Q4_0 | 0.70GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [LFM2-1.2B-Tool-IQ4_NL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ4_NL.gguf) | IQ4_NL | 0.70GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [LFM2-1.2B-Tool-Q3_K_XL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q3_K_XL.gguf) | Q3_K_XL | 0.67GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [LFM2-1.2B-Tool-IQ4_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ4_XS.gguf) | IQ4_XS | 0.66GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [LFM2-1.2B-Tool-Q3_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q3_K_L.gguf) | Q3_K_L | 0.64GB | false | Lower quality but usable, good for low RAM availability. | +| [LFM2-1.2B-Tool-Q3_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q3_K_M.gguf) | Q3_K_M | 0.60GB | false | Low quality. | +| [LFM2-1.2B-Tool-IQ3_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ3_M.gguf) | IQ3_M | 0.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [LFM2-1.2B-Tool-Q3_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q3_K_S.gguf) | Q3_K_S | 0.56GB | false | Low quality, not recommended. | +| [LFM2-1.2B-Tool-IQ3_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ3_XS.gguf) | IQ3_XS | 0.54GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [LFM2-1.2B-Tool-Q2_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q2_K_L.gguf) | Q2_K_L | 0.52GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [LFM2-1.2B-Tool-IQ3_XXS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ3_XXS.gguf) | IQ3_XXS | 0.49GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [LFM2-1.2B-Tool-Q2_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-Q2_K.gguf) | Q2_K | 0.48GB | false | Very low quality but surprisingly usable. | +| [LFM2-1.2B-Tool-IQ2_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF/blob/main/LiquidAI_LFM2-1.2B-Tool-IQ2_M.gguf) | IQ2_M | 0.43GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF --include "LiquidAI_LFM2-1.2B-Tool-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/LiquidAI_LFM2-1.2B-Tool-GGUF --include "LiquidAI_LFM2-1.2B-Tool-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (LiquidAI_LFM2-1.2B-Tool-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file