From f40607d3c43f08a1f374c953547b7c926cfe070c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 5 Aug 2026 16:17:13 +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_LFM2.5-2.6B-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++ LiquidAI_LFM2.5-2.6B-IQ2_M.gguf | 3 + LiquidAI_LFM2.5-2.6B-IQ3_M.gguf | 3 + LiquidAI_LFM2.5-2.6B-IQ3_XS.gguf | 3 + LiquidAI_LFM2.5-2.6B-IQ3_XXS.gguf | 3 + LiquidAI_LFM2.5-2.6B-IQ4_NL.gguf | 3 + LiquidAI_LFM2.5-2.6B-IQ4_XS.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q2_K.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q2_K_L.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q3_K_L.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q3_K_M.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q3_K_S.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q3_K_XL.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q4_0.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q4_1.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q4_K_L.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q4_K_M.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q4_K_S.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q5_K_L.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q5_K_M.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q5_K_S.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q6_K.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q6_K_L.gguf | 3 + LiquidAI_LFM2.5-2.6B-Q8_0.gguf | 3 + LiquidAI_LFM2.5-2.6B-bf16.gguf | 3 + LiquidAI_LFM2.5-2.6B-imatrix.gguf | 3 + README.md | 175 ++++++++++++++++++++++++++++++ configuration.json | 1 + 28 files changed, 298 insertions(+) create mode 100644 .gitattributes create mode 100644 LiquidAI_LFM2.5-2.6B-IQ2_M.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-IQ3_M.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-IQ3_XS.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-IQ3_XXS.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-IQ4_NL.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-IQ4_XS.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q2_K.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q2_K_L.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q3_K_L.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q3_K_M.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q3_K_S.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q3_K_XL.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q4_0.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q4_1.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q4_K_L.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q4_K_M.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q4_K_S.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q5_K_L.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q5_K_M.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q5_K_S.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q6_K.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q6_K_L.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-Q8_0.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-bf16.gguf create mode 100644 LiquidAI_LFM2.5-2.6B-imatrix.gguf create mode 100644 README.md create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /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 +*.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 +*.gguf* 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 \ No newline at end of file diff --git a/LiquidAI_LFM2.5-2.6B-IQ2_M.gguf b/LiquidAI_LFM2.5-2.6B-IQ2_M.gguf new file mode 100644 index 0000000..630b163 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4411044044c637274ad07cab250bad3dd9d804b3d5fd823827f78736ea84ce6 +size 1022470432 diff --git a/LiquidAI_LFM2.5-2.6B-IQ3_M.gguf b/LiquidAI_LFM2.5-2.6B-IQ3_M.gguf new file mode 100644 index 0000000..8886cc1 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e6d4876484c09246831062afc4961efa45405e06c622765f8e5c31c484b4096 +size 1292470560 diff --git a/LiquidAI_LFM2.5-2.6B-IQ3_XS.gguf b/LiquidAI_LFM2.5-2.6B-IQ3_XS.gguf new file mode 100644 index 0000000..f34f761 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ad8fa13972d24c82527b858f47224344169048cb8481cc2bae029b2f2baae95 +size 1229596960 diff --git a/LiquidAI_LFM2.5-2.6B-IQ3_XXS.gguf b/LiquidAI_LFM2.5-2.6B-IQ3_XXS.gguf new file mode 100644 index 0000000..44b0064 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60e72d4976b7a3b43101a05563624d4c55cb5b8e10a1d8f5ea80194cd9b25f08 +size 1130490144 diff --git a/LiquidAI_LFM2.5-2.6B-IQ4_NL.gguf b/LiquidAI_LFM2.5-2.6B-IQ4_NL.gguf new file mode 100644 index 0000000..6942d23 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ef7c1c666977f144c23693bdae622775940fb45264f7ae9fbc717488daf355 +size 1598220576 diff --git a/LiquidAI_LFM2.5-2.6B-IQ4_XS.gguf b/LiquidAI_LFM2.5-2.6B-IQ4_XS.gguf new file mode 100644 index 0000000..6d5e9d2 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34844da05ab6e4ca773299d97a2691e47f4f0e1587a3a632f4ca82b3916754b6 +size 1522657568 diff --git a/LiquidAI_LFM2.5-2.6B-Q2_K.gguf b/LiquidAI_LFM2.5-2.6B-Q2_K.gguf new file mode 100644 index 0000000..ac8b35e --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67bc2f2c18cff83ffd82d3c83583f01a1ed937ba860ab7de052235bc8d2ce880 +size 1102850336 diff --git a/LiquidAI_LFM2.5-2.6B-Q2_K_L.gguf b/LiquidAI_LFM2.5-2.6B-Q2_K_L.gguf new file mode 100644 index 0000000..56d82a6 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:455470f8d123d034df5b8fbb2aac1774018a37256c78ff9f3622fc5392ef840d +size 1166338336 diff --git a/LiquidAI_LFM2.5-2.6B-Q3_K_L.gguf b/LiquidAI_LFM2.5-2.6B-Q3_K_L.gguf new file mode 100644 index 0000000..d67fb43 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98aec36cffe8f21c37bd1b230caa424e44746b2c4f5a31625e2973b26a7e402 +size 1454008608 diff --git a/LiquidAI_LFM2.5-2.6B-Q3_K_M.gguf b/LiquidAI_LFM2.5-2.6B-Q3_K_M.gguf new file mode 100644 index 0000000..e8f47ee --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08dc6cb8cfe80722e20e523564f49d2624265721f7b596d6b9c167001b058ff9 +size 1373661472 diff --git a/LiquidAI_LFM2.5-2.6B-Q3_K_S.gguf b/LiquidAI_LFM2.5-2.6B-Q3_K_S.gguf new file mode 100644 index 0000000..c11b710 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6c2408cf0d287b51268ba131d43f388fb534ad31719b53cc13df26ece5e2ed7 +size 1277077792 diff --git a/LiquidAI_LFM2.5-2.6B-Q3_K_XL.gguf b/LiquidAI_LFM2.5-2.6B-Q3_K_XL.gguf new file mode 100644 index 0000000..b5acc08 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cad506e52d105bc8138e42cac42f347c320584da9fc966cc35d98b63282512bc +size 1517496608 diff --git a/LiquidAI_LFM2.5-2.6B-Q4_0.gguf b/LiquidAI_LFM2.5-2.6B-Q4_0.gguf new file mode 100644 index 0000000..85c8e0e --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b0e51637960e8c75c32ef10b73ed241a2cecbf8224fd8fb720434b15dc304d +size 1602349344 diff --git a/LiquidAI_LFM2.5-2.6B-Q4_1.gguf b/LiquidAI_LFM2.5-2.6B-Q4_1.gguf new file mode 100644 index 0000000..7ed963c --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:261c0986fb6d97463c16eb0873433ddfe244e03bda2edc0b5da95aa2436eecdf +size 1749346592 diff --git a/LiquidAI_LFM2.5-2.6B-Q4_K_L.gguf b/LiquidAI_LFM2.5-2.6B-Q4_K_L.gguf new file mode 100644 index 0000000..e9702f8 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:240d0d0e2415f297772580c6480eeaab38c65f57676570367fa0300c3cfef8d3 +size 1747511584 diff --git a/LiquidAI_LFM2.5-2.6B-Q4_K_M.gguf b/LiquidAI_LFM2.5-2.6B-Q4_K_M.gguf new file mode 100644 index 0000000..bed4ccd --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03ab6106f4636ae7f316245d2adf7394ccf3cd80a684ec0c473b1a4720f3108e +size 1684023584 diff --git a/LiquidAI_LFM2.5-2.6B-Q4_K_S.gguf b/LiquidAI_LFM2.5-2.6B-Q4_K_S.gguf new file mode 100644 index 0000000..a2edb4e --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2109c5be64fdbd0a4139d136190be1ef96068cae384beb1fedd51deb8eb40a3 +size 1607002400 diff --git a/LiquidAI_LFM2.5-2.6B-Q5_K_L.gguf b/LiquidAI_LFM2.5-2.6B-Q5_K_L.gguf new file mode 100644 index 0000000..77742e9 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fcf7008dfc678e8129b418d407a5fdce6509338c271b10ecc60790885a97a2b +size 2011031840 diff --git a/LiquidAI_LFM2.5-2.6B-Q5_K_M.gguf b/LiquidAI_LFM2.5-2.6B-Q5_K_M.gguf new file mode 100644 index 0000000..c82df4f --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f1f9739a61bd8edf245b7b0c24cb2a20abc287665e35653a3772e7474506a6 +size 1947543840 diff --git a/LiquidAI_LFM2.5-2.6B-Q5_K_S.gguf b/LiquidAI_LFM2.5-2.6B-Q5_K_S.gguf new file mode 100644 index 0000000..c777275 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73e692b159fea4e02423952bdca1cca5ba694c0ebad2c9293f045e96f2a8f0c3 +size 1900472608 diff --git a/LiquidAI_LFM2.5-2.6B-Q6_K.gguf b/LiquidAI_LFM2.5-2.6B-Q6_K.gguf new file mode 100644 index 0000000..c857922 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:499c120820935273c5eec587333ce18e0d4369911bd795b537f041ab4b20052f +size 2236852512 diff --git a/LiquidAI_LFM2.5-2.6B-Q6_K_L.gguf b/LiquidAI_LFM2.5-2.6B-Q6_K_L.gguf new file mode 100644 index 0000000..593505f --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ebd3b3d64967bbdbfcf0f0bbacc18686d9faab552c9d369ba18743cd68148c7 +size 2300340512 diff --git a/LiquidAI_LFM2.5-2.6B-Q8_0.gguf b/LiquidAI_LFM2.5-2.6B-Q8_0.gguf new file mode 100644 index 0000000..a17217b --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83bbdbb27c8a2b8636e554f364dad63f76588d4dec4629c819093a0317f07da8 +size 2874779936 diff --git a/LiquidAI_LFM2.5-2.6B-bf16.gguf b/LiquidAI_LFM2.5-2.6B-bf16.gguf new file mode 100644 index 0000000..c50753d --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:917b46ebb876cfbda1243567a819bd754cdaa8d912508e0030938792182ef66a +size 5403158560 diff --git a/LiquidAI_LFM2.5-2.6B-imatrix.gguf b/LiquidAI_LFM2.5-2.6B-imatrix.gguf new file mode 100644 index 0000000..8d61872 --- /dev/null +++ b/LiquidAI_LFM2.5-2.6B-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6dfa9f4fac87d56a418a6cb9774c849fc5d375bc08b0dfcfb3ba091c4d79fef +size 2430880 diff --git a/README.md b/README.md new file mode 100644 index 0000000..364c9d2 --- /dev/null +++ b/README.md @@ -0,0 +1,175 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +license_link: LICENSE +language: +- ar +- zh +- en +- fr +- de +- hi +- id +- it +- ja +- ko +- pl +- pt +- ru +- es +- th +- vi +base_model_relation: quantized +base_model: LiquidAI/LFM2.5-2.6B +license_name: lfm1.0 +tags: +- liquid +- lfm2.5 +- edge +license: other +--- + +## Llamacpp imatrix Quantizations of LFM2.5-2.6B by LiquidAI + +Using llama.cpp release b10262 for quantization. + +Original model: https://huggingface.co/LiquidAI/LFM2.5-2.6B + +**Model details:** +- Parameter count: 3B +- Input support: text +- MTP: no +- imatrix: yes - [details](#imatrix) + +[How to run](#how-to-run) + +## Prompt format + +``` +<|startoftext|><|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant + +``` + +**Don't know which to choose?** Grab [Q4_K_M](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q4_K_M.gguf) (1.68GB) - usually a good mix of size and performance. Download instructions available [here](#downloading-using-the-hugging-face-cli) + +## Available files: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [LiquidAI_LFM2.5-2.6B-bf16.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-bf16.gguf) | bf16 | 5.40GB | false | Full BF16 weights. | +| [LiquidAI_LFM2.5-2.6B-Q8_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q8_0.gguf) | Q8_0 | 2.87GB | false | Extremely high quality, generally unneeded but max available quant. | +| [LiquidAI_LFM2.5-2.6B-Q6_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q6_K_L.gguf) | Q6_K_L | 2.30GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [LiquidAI_LFM2.5-2.6B-Q6_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q6_K.gguf) | Q6_K | 2.24GB | false | Very high quality, near perfect, *recommended*. | +| [LiquidAI_LFM2.5-2.6B-Q5_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q5_K_L.gguf) | Q5_K_L | 2.01GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [LiquidAI_LFM2.5-2.6B-Q5_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q5_K_M.gguf) | Q5_K_M | 1.95GB | false | High quality, *recommended*. | +| [LiquidAI_LFM2.5-2.6B-Q5_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q5_K_S.gguf) | Q5_K_S | 1.90GB | false | High quality, *recommended*. | +| [LiquidAI_LFM2.5-2.6B-Q4_1.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q4_1.gguf) | Q4_1 | 1.75GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [LiquidAI_LFM2.5-2.6B-Q4_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q4_K_L.gguf) | Q4_K_L | 1.75GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [LiquidAI_LFM2.5-2.6B-Q4_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q4_K_M.gguf) | Q4_K_M | 1.68GB | false | Good quality, default size for most use cases, *recommended*. | +| [LiquidAI_LFM2.5-2.6B-Q4_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q4_K_S.gguf) | Q4_K_S | 1.61GB | false | Slightly lower quality with more space savings, *recommended*. | +| [LiquidAI_LFM2.5-2.6B-Q4_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q4_0.gguf) | Q4_0 | 1.60GB | false | Legacy format, kept for compatibility with older tools. | +| [LiquidAI_LFM2.5-2.6B-IQ4_NL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-IQ4_NL.gguf) | IQ4_NL | 1.60GB | false | Similar to IQ4_XS, but slightly larger. | +| [LiquidAI_LFM2.5-2.6B-IQ4_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-IQ4_XS.gguf) | IQ4_XS | 1.52GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [LiquidAI_LFM2.5-2.6B-Q3_K_XL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q3_K_XL.gguf) | Q3_K_XL | 1.52GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [LiquidAI_LFM2.5-2.6B-Q3_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q3_K_L.gguf) | Q3_K_L | 1.45GB | false | Lower quality but usable, good for low RAM availability. | +| [LiquidAI_LFM2.5-2.6B-Q3_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q3_K_M.gguf) | Q3_K_M | 1.37GB | false | Low quality. | +| [LiquidAI_LFM2.5-2.6B-IQ3_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-IQ3_M.gguf) | IQ3_M | 1.29GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [LiquidAI_LFM2.5-2.6B-Q3_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q3_K_S.gguf) | Q3_K_S | 1.28GB | false | Low quality, not recommended. | +| [LiquidAI_LFM2.5-2.6B-IQ3_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-IQ3_XS.gguf) | IQ3_XS | 1.23GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [LiquidAI_LFM2.5-2.6B-Q2_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q2_K_L.gguf) | Q2_K_L | 1.17GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [LiquidAI_LFM2.5-2.6B-IQ3_XXS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-IQ3_XXS.gguf) | IQ3_XXS | 1.13GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [LiquidAI_LFM2.5-2.6B-Q2_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-Q2_K.gguf) | Q2_K | 1.10GB | false | Very low quality but surprisingly usable. | +| [LiquidAI_LFM2.5-2.6B-IQ2_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-IQ2_M.gguf) | IQ2_M | 1.02GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +Download a specific file: + +``` +hf download bartowski/LiquidAI_LFM2.5-2.6B-GGUF --include "LiquidAI_LFM2.5-2.6B-Q4_K_M.gguf" --local-dir ./ +``` + +## Downloading using the Hugging Face CLI + +
+ Click to view download instructions + +First, make sure you have the Hugging Face CLI installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Download a specific file: + +``` +hf download bartowski/LiquidAI_LFM2.5-2.6B-GGUF --include "LiquidAI_LFM2.5-2.6B-Q4_K_M.gguf" --local-dir ./ +``` + +
+ +## How to run + +These quants run with [llama.cpp](https://github.com/ggml-org/llama.cpp) - installable in one line via [llama.app](https://llama.app/): + +``` +curl -LsSf https://llama.app/install.sh | sh +llama-server -hf bartowski/LiquidAI_LFM2.5-2.6B-GGUF:Q4_K_M +``` + +llama-server includes a built-in chat web UI, served at http://localhost:8080 by default. + +These quants were made with llama.cpp release b10262 - if this model's architecture is newly supported, you'll need that release or newer to run them. + +They also work in: [LM Studio](https://lmstudio.ai/) · [koboldcpp](https://github.com/LostRuins/koboldcpp) · [ramalama](https://github.com/containers/ramalama) · [Jan AI](https://www.jan.ai/) · [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui) · [LoLLMs](https://github.com/ParisNeo/lollms) · [Atomic Chat](https://atomic.chat/) + +## imatrix + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d). The imatrix is available here: [LiquidAI_LFM2.5-2.6B-imatrix.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-2.6B-GGUF/blob/main/LiquidAI_LFM2.5-2.6B-imatrix.gguf). + +## 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. + +## ARM/AVX information + +llama.cpp automatically "repacks" weights into an interleaved layout at load time for faster inference on ARM and AVX machines - details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). This once required downloading special Q4_0_4_4/4_8/8_8 files; those are long gone. Online repacking now covers Q4_0, IQ4_NL, and most K-quants, so no special quant choice is needed for CPU inference. + +## Which file should I choose? + +
+ Click here for details + +An older (early 2024) but still useful write-up with charts comparing quant 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. + +Hugging Face can also do this math for you: add your hardware in your [Local Apps settings](https://huggingface.co/settings/local-apps) and the model page will show which files fit. + +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. + +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