From 5d3c0d13f42db66457fd877b61f3471f5dbcca9a Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 7 Oct 2026 18:06:13 +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: Mungert/Jan-nano-128k-GGUF Source: Original Platform --- .gitattributes | 79 ++++++++++++++ Jan-nano-128k-bf16.gguf | 3 + Jan-nano-128k-bf16_q8_0.gguf | 3 + Jan-nano-128k-f16_q8_0.gguf | 3 + Jan-nano-128k-iq1_m.gguf | 3 + Jan-nano-128k-iq1_s.gguf | 3 + Jan-nano-128k-iq2_m.gguf | 3 + Jan-nano-128k-iq2_s.gguf | 3 + Jan-nano-128k-iq2_xs.gguf | 3 + Jan-nano-128k-iq2_xxs.gguf | 3 + Jan-nano-128k-iq3_m.gguf | 3 + Jan-nano-128k-iq3_s.gguf | 3 + Jan-nano-128k-iq3_xs.gguf | 3 + Jan-nano-128k-iq3_xxs.gguf | 3 + Jan-nano-128k-iq4_nl.gguf | 3 + Jan-nano-128k-iq4_xs.gguf | 3 + Jan-nano-128k-q2_k_m.gguf | 3 + Jan-nano-128k-q2_k_s.gguf | 3 + Jan-nano-128k-q3_k_m.gguf | 3 + Jan-nano-128k-q3_k_s.gguf | 3 + Jan-nano-128k-q4_0.gguf | 3 + Jan-nano-128k-q4_1.gguf | 3 + Jan-nano-128k-q4_k_m.gguf | 3 + Jan-nano-128k-q4_k_s.gguf | 3 + Jan-nano-128k-q5_0.gguf | 3 + Jan-nano-128k-q5_1.gguf | 3 + Jan-nano-128k-q5_k_m.gguf | 3 + Jan-nano-128k-q5_k_s.gguf | 3 + Jan-nano-128k-q6_k_m.gguf | 3 + Jan-nano-128k-q8_0.gguf | 3 + Jan-nano-128k-tq1_0.gguf | 3 + Jan-nano-128k-tq2_0.gguf | 3 + Jan-nano-128k.imatrix | 3 + README.md | 200 +++++++++++++++++++++++++++++++++++ configuration.json | 1 + 35 files changed, 376 insertions(+) create mode 100644 .gitattributes create mode 100644 Jan-nano-128k-bf16.gguf create mode 100644 Jan-nano-128k-bf16_q8_0.gguf create mode 100644 Jan-nano-128k-f16_q8_0.gguf create mode 100644 Jan-nano-128k-iq1_m.gguf create mode 100644 Jan-nano-128k-iq1_s.gguf create mode 100644 Jan-nano-128k-iq2_m.gguf create mode 100644 Jan-nano-128k-iq2_s.gguf create mode 100644 Jan-nano-128k-iq2_xs.gguf create mode 100644 Jan-nano-128k-iq2_xxs.gguf create mode 100644 Jan-nano-128k-iq3_m.gguf create mode 100644 Jan-nano-128k-iq3_s.gguf create mode 100644 Jan-nano-128k-iq3_xs.gguf create mode 100644 Jan-nano-128k-iq3_xxs.gguf create mode 100644 Jan-nano-128k-iq4_nl.gguf create mode 100644 Jan-nano-128k-iq4_xs.gguf create mode 100644 Jan-nano-128k-q2_k_m.gguf create mode 100644 Jan-nano-128k-q2_k_s.gguf create mode 100644 Jan-nano-128k-q3_k_m.gguf create mode 100644 Jan-nano-128k-q3_k_s.gguf create mode 100644 Jan-nano-128k-q4_0.gguf create mode 100644 Jan-nano-128k-q4_1.gguf create mode 100644 Jan-nano-128k-q4_k_m.gguf create mode 100644 Jan-nano-128k-q4_k_s.gguf create mode 100644 Jan-nano-128k-q5_0.gguf create mode 100644 Jan-nano-128k-q5_1.gguf create mode 100644 Jan-nano-128k-q5_k_m.gguf create mode 100644 Jan-nano-128k-q5_k_s.gguf create mode 100644 Jan-nano-128k-q6_k_m.gguf create mode 100644 Jan-nano-128k-q8_0.gguf create mode 100644 Jan-nano-128k-tq1_0.gguf create mode 100644 Jan-nano-128k-tq2_0.gguf create mode 100644 Jan-nano-128k.imatrix create mode 100644 README.md create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b9b2514 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,79 @@ +*.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 + +Jan-nano-128k-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-tq1_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-bf16.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-tq2_0.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k.imatrix filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text +Jan-nano-128k-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Jan-nano-128k-bf16.gguf b/Jan-nano-128k-bf16.gguf new file mode 100644 index 0000000..060b86f --- /dev/null +++ b/Jan-nano-128k-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f775419fa4c718ab0260b10928b00ff3c1652f20a944b9dfac585d0b5c1f43a0 +size 8051285376 diff --git a/Jan-nano-128k-bf16_q8_0.gguf b/Jan-nano-128k-bf16_q8_0.gguf new file mode 100644 index 0000000..1ad7c0e --- /dev/null +++ b/Jan-nano-128k-bf16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e1b2fe80532db585e87b7e1986690e1f33a03b5c95530e8ae08006f70feb996 +size 5927918976 diff --git a/Jan-nano-128k-f16_q8_0.gguf b/Jan-nano-128k-f16_q8_0.gguf new file mode 100644 index 0000000..75160f4 --- /dev/null +++ b/Jan-nano-128k-f16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2848e036ea2b21e9d55614d1a5fec52bfa84d13ac3645bd1f3872e6e3f64766 +size 5927918976 diff --git a/Jan-nano-128k-iq1_m.gguf b/Jan-nano-128k-iq1_m.gguf new file mode 100644 index 0000000..fbb4dd3 --- /dev/null +++ b/Jan-nano-128k-iq1_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8998f9311fb230c3c0a9cbc117fdedd7b392a03f69552fde7ab2d99c2512cd +size 1320103584 diff --git a/Jan-nano-128k-iq1_s.gguf b/Jan-nano-128k-iq1_s.gguf new file mode 100644 index 0000000..867c651 --- /dev/null +++ b/Jan-nano-128k-iq1_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dfd79624b635956e3d7c2e077145dd990d402448a8557f216945701527b8294 +size 1228885664 diff --git a/Jan-nano-128k-iq2_m.gguf b/Jan-nano-128k-iq2_m.gguf new file mode 100644 index 0000000..9b7d15c --- /dev/null +++ b/Jan-nano-128k-iq2_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dea2273f1d18fcf302c30db736317bea460ae91c26a14b33dc4e9c1c4683a936 +size 1553616544 diff --git a/Jan-nano-128k-iq2_s.gguf b/Jan-nano-128k-iq2_s.gguf new file mode 100644 index 0000000..0af4691 --- /dev/null +++ b/Jan-nano-128k-iq2_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d17198f1bc35de778b306416487d25a3d82c9dad59bc556736926fd9d4c8fa +size 1489391264 diff --git a/Jan-nano-128k-iq2_xs.gguf b/Jan-nano-128k-iq2_xs.gguf new file mode 100644 index 0000000..7c065f7 --- /dev/null +++ b/Jan-nano-128k-iq2_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe09bf5ac4c6dc3d91a86a46986be0ae28f05a87d3803bd025155bf5ad6101e +size 1446178464 diff --git a/Jan-nano-128k-iq2_xxs.gguf b/Jan-nano-128k-iq2_xxs.gguf new file mode 100644 index 0000000..cb95bde --- /dev/null +++ b/Jan-nano-128k-iq2_xxs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f0bf92c4c8c625bb2807ceab74c5ec0efa6b58d6967e5d26c26b36b033a61c2 +size 1340952224 diff --git a/Jan-nano-128k-iq3_m.gguf b/Jan-nano-128k-iq3_m.gguf new file mode 100644 index 0000000..999e887 --- /dev/null +++ b/Jan-nano-128k-iq3_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30730f9312e0892913c333303818e11e4968b45b21c90cb3fa95881fd30ed93f +size 1951379104 diff --git a/Jan-nano-128k-iq3_s.gguf b/Jan-nano-128k-iq3_s.gguf new file mode 100644 index 0000000..95cd7a3 --- /dev/null +++ b/Jan-nano-128k-iq3_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecacdfd5c3dfe6a2ab44cf0f894267d23cb9df15915f2ce18ddbd8ef900467c8 +size 1951379104 diff --git a/Jan-nano-128k-iq3_xs.gguf b/Jan-nano-128k-iq3_xs.gguf new file mode 100644 index 0000000..345f07b --- /dev/null +++ b/Jan-nano-128k-iq3_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d00088d9b90c6820bb9a3871b12462fe2f47d1cc5054b61e4fc6ee1c6912653c +size 1772547744 diff --git a/Jan-nano-128k-iq3_xxs.gguf b/Jan-nano-128k-iq3_xxs.gguf new file mode 100644 index 0000000..a11905c --- /dev/null +++ b/Jan-nano-128k-iq3_xxs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d79c9bb4bbbefa141e268e2e4e889a9fff7864e88ef8f0ddb0e33f11691e1692 +size 1722044064 diff --git a/Jan-nano-128k-iq4_nl.gguf b/Jan-nano-128k-iq4_nl.gguf new file mode 100644 index 0000000..3d48236 --- /dev/null +++ b/Jan-nano-128k-iq4_nl.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fa3441c98e9672e239eade489c38d63198398aa0fc6ab0f99359abf7c64cc2f +size 2381343904 diff --git a/Jan-nano-128k-iq4_xs.gguf b/Jan-nano-128k-iq4_xs.gguf new file mode 100644 index 0000000..5ab38a6 --- /dev/null +++ b/Jan-nano-128k-iq4_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dae66ee25b553ffe2000c1854e03186110cc7c8ae9cee687488f933b2f7c284 +size 2270751904 diff --git a/Jan-nano-128k-q2_k_m.gguf b/Jan-nano-128k-q2_k_m.gguf new file mode 100644 index 0000000..633236d --- /dev/null +++ b/Jan-nano-128k-q2_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21ababa290cb35f99fac0bb17c67f569064d42a734d2b3db0d0e561f37fdad24 +size 1643203744 diff --git a/Jan-nano-128k-q2_k_s.gguf b/Jan-nano-128k-q2_k_s.gguf new file mode 100644 index 0000000..a576ba1 --- /dev/null +++ b/Jan-nano-128k-q2_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b24aaf2249c839fd7e294e7ac259734bbf3db38b015bf0a567b4a1f8e47bb47 +size 1591545504 diff --git a/Jan-nano-128k-q3_k_m.gguf b/Jan-nano-128k-q3_k_m.gguf new file mode 100644 index 0000000..7dd7d66 --- /dev/null +++ b/Jan-nano-128k-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7a10228891ca6df5c0fd41ce21e6df0f2f514142be4b28a5fcd7444fafc13b6 +size 2059562144 diff --git a/Jan-nano-128k-q3_k_s.gguf b/Jan-nano-128k-q3_k_s.gguf new file mode 100644 index 0000000..21694e3 --- /dev/null +++ b/Jan-nano-128k-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9260979ec9061e994a9c659d1b1a4d42f67774df59831594deecbda737fdf1a8 +size 2007903904 diff --git a/Jan-nano-128k-q4_0.gguf b/Jan-nano-128k-q4_0.gguf new file mode 100644 index 0000000..2a57152 --- /dev/null +++ b/Jan-nano-128k-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:879f8ff718ad359b43205c8412f3af96e98dc288f459411044c3e71c3449fa46 +size 2269269664 diff --git a/Jan-nano-128k-q4_1.gguf b/Jan-nano-128k-q4_1.gguf new file mode 100644 index 0000000..bf5f629 --- /dev/null +++ b/Jan-nano-128k-q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a368c2495047189d6d5ebb9123db882c4ec381f13cfc769d373a3509f63cf5ba +size 2520661664 diff --git a/Jan-nano-128k-q4_k_m.gguf b/Jan-nano-128k-q4_k_m.gguf new file mode 100644 index 0000000..65417c3 --- /dev/null +++ b/Jan-nano-128k-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b057c9c2709507cd10af0db36dc73bd9e1dfadadc2ba98da3a00b0985bb90f +size 2478521504 diff --git a/Jan-nano-128k-q4_k_s.gguf b/Jan-nano-128k-q4_k_s.gguf new file mode 100644 index 0000000..7bf2059 --- /dev/null +++ b/Jan-nano-128k-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b920e7afb9b92e1452ddfd6a0955dc4c52830066f13f92c600b3f5ee50cecbe +size 2407558304 diff --git a/Jan-nano-128k-q5_0.gguf b/Jan-nano-128k-q5_0.gguf new file mode 100644 index 0000000..1c0dacb --- /dev/null +++ b/Jan-nano-128k-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c2fd332800b6eecebdb7aec3ca44c4147ba4eae80030c525dec4fcf7d894104 +size 2772053664 diff --git a/Jan-nano-128k-q5_1.gguf b/Jan-nano-128k-q5_1.gguf new file mode 100644 index 0000000..a846d50 --- /dev/null +++ b/Jan-nano-128k-q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d5e78de80dcc92f9e560e63798c57413e161acfbb0b5a434592ce74b9fc9d1 +size 3023445664 diff --git a/Jan-nano-128k-q5_k_m.gguf b/Jan-nano-128k-q5_k_m.gguf new file mode 100644 index 0000000..b2264bd --- /dev/null +++ b/Jan-nano-128k-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3a96b97826048fd2e7753f270f9a2186ee097d90ee97378ba86d51affff7b8 +size 2900655264 diff --git a/Jan-nano-128k-q5_k_s.gguf b/Jan-nano-128k-q5_k_s.gguf new file mode 100644 index 0000000..0f92d52 --- /dev/null +++ b/Jan-nano-128k-q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5318625675c13d64edd84511308381f1930ef82dc37c1ce96971bb287e221dc2 +size 2864098464 diff --git a/Jan-nano-128k-q6_k_m.gguf b/Jan-nano-128k-q6_k_m.gguf new file mode 100644 index 0000000..4ecba67 --- /dev/null +++ b/Jan-nano-128k-q6_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed61eca4a4adf3f6121cfe2074e9d343b6e56d101a315998f416f8a8d1a9dbf4 +size 3306261664 diff --git a/Jan-nano-128k-q8_0.gguf b/Jan-nano-128k-q8_0.gguf new file mode 100644 index 0000000..5edae71 --- /dev/null +++ b/Jan-nano-128k-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f675be37566d833bc08aa810c84fe0e279edea4106bc8270c33afae03c1d6dc +size 4280405376 diff --git a/Jan-nano-128k-tq1_0.gguf b/Jan-nano-128k-tq1_0.gguf new file mode 100644 index 0000000..d90e697 --- /dev/null +++ b/Jan-nano-128k-tq1_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60e59093612ed6bea979db5bf343f19b64a1a258b96dd60a7ac0d187ade9ad9 +size 1092209824 diff --git a/Jan-nano-128k-tq2_0.gguf b/Jan-nano-128k-tq2_0.gguf new file mode 100644 index 0000000..614cbaa --- /dev/null +++ b/Jan-nano-128k-tq2_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37518a089447b47c8325fd355a6a4e3f434cca9417b02c1e20b8466a649998c6 +size 1262521504 diff --git a/Jan-nano-128k.imatrix b/Jan-nano-128k.imatrix new file mode 100644 index 0000000..c21d3dd --- /dev/null +++ b/Jan-nano-128k.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e4a238a11d51aa36e1bd4151db57e6b1818ae3b524b838e6f671a3408878e47 +size 3842222 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4cfcecf --- /dev/null +++ b/README.md @@ -0,0 +1,200 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Menlo/Jan-nano +pipeline_tag: text-generation +library_name: transformers +--- + +# Jan-nano-128k GGUF Models + + +## Model Generation Details + +This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`8846aace`](https://github.com/ggerganov/llama.cpp/commit/8846aace4934ad29651ea61b8c7e3f6b0556e3d2). + + + + + +--- + +## Quantization Beyond the IMatrix + +I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides. + +In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the `--tensor-type` option in `llama.cpp` to manually "bump" important layers to higher precision. You can see the implementation here: +๐Ÿ‘‰ [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py) + +While this does increase model file size, it significantly improves precision for a given quantization level. + +### **I'd love your feedbackโ€”have you tried this? How does it perform for you?** + + + + +--- + + + Click here to get info on choosing the right GGUF model format + + +--- + + + + + + +# Jan-Nano-128k: Empowering deeper research through extended context understanding. + +[![GitHub](https://img.shields.io/badge/GitHub-Repository-blue?logo=github)](https://github.com/menloresearch/deep-research) +[![License](https://img.shields.io/badge/License-Apache%202.0-yellow)](https://opensource.org/licenses/Apache-2.0) + +
+ Jan-Nano-128k +
+ +**Authors:** [Alan Dao](https://scholar.google.com/citations?user=eGWws2UAAAAJ&hl=en), [Bach Vu Dinh](https://scholar.google.com/citations?user=7Lr6hdoAAAAJ&hl=vi), [Thinh Le](https://scholar.google.com/citations?user=8tcN7xMAAAAJ&hl=en) + + +![image/gif](https://cdn-uploads.huggingface.co/production/uploads/62d7b2339b629105a5d6888a/aLL8fyMLE3ujV75qD4WKI.gif) + + +## Overview + +Jan-Nano-128k represents a significant advancement in compact language models for research applications. Building upon the success of [Jan-Nano](https://huggingface.co/Menlo/Jan-nano), this enhanced version features a **native 128k context window** that enables deeper, more comprehensive research capabilities without the performance degradation typically associated with context extension methods. + +**Key Improvements:** +- **๐Ÿ” Research Deeper**: Extended context allows for processing entire research papers, lengthy documents, and complex multi-turn conversations +- **โšก Native 128k Window**: Built from the ground up to handle long contexts efficiently, maintaining performance across the full context range +- **๐Ÿ“ˆ Enhanced Performance**: Unlike traditional context extension methods, Jan-Nano-128k shows improved performance with longer contexts + +This model maintains full compatibility with Model Context Protocol (MCP) servers while dramatically expanding the scope of research tasks it can handle in a single session. + +## Evaluation + +Jan-Nano-128k has been rigorously evaluated on the SimpleQA benchmark using our MCP-based methodology, demonstrating superior performance compared to its predecessor: + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/Bc0ehij86l_NX52OfxeOj.png) + +## Why Jan-Nano-128k? + +Traditional approaches to extending context length, such as YaRN (Yet another RoPE extensioN), often result in performance degradation as context length increases. Jan-Nano-128k breaks this paradigm: + +This fundamental difference makes Jan-Nano-128k ideal for research applications requiring deep document analysis, multi-document synthesis, and complex reasoning over large information sets. + +## ๐Ÿ–ฅ๏ธ How to Run Locally + +Jan desktop will eventually support this model (WIP). Otherwise you can check the deployment options below that we have tested. + +For additional tutorials and community guidance, visit our [Discussion Forums](https://huggingface.co/Menlo/Jan-nano-128k/discussions). + +### Deployment + +Deploy using VLLM: +```bash +vllm serve Menlo/Jan-nano-128k \ + --host 0.0.0.0 \ + --port 1234 \ + --enable-auto-tool-choice \ + --tool-call-parser hermes \ + --rope-scaling '{"rope_type":"yarn","factor":3.2,"original_max_position_embeddings":40960}' --max-model-len 131072 +``` + +Or `llama-server` from `llama.cpp`: +```bash +llama-server ... --rope-scaling yarn --rope-scale 3.2 --yarn-orig-ctx 40960 +``` +**Note:** The chat template is included in the tokenizer. For troubleshooting, download the [Non-think chat template](https://qwen.readthedocs.io/en/latest/_downloads/c101120b5bebcc2f12ec504fc93a965e/qwen3_nonthinking.jinja). + +### Recommended Sampling Parameters + +```yaml +Temperature: 0.7 +Top-p: 0.8 +Top-k: 20 +Min-p: 0.0 +``` + +## ๐Ÿค Community & Support + +- **Discussions**: [HuggingFace Community](https://huggingface.co/Menlo/Jan-nano-128k/discussions) +- **Issues**: [GitHub Repository](https://github.com/menloresearch/jan/issues) +- **Documentation**: [Official Docs](https://menloresearch.github.io/deep-research/) + +## ๐Ÿ“„ Citation + +```bibtex +@model{jan-nano-128k, + title={Jan-Nano-128k: Deep Research with Extended Context}, + author={Dao, Alan and Dinh, Bach Vu and Le Thinh}, + year={2024}, + url={https://huggingface.co/Menlo/Jan-nano-128k} +} +``` + +--- + +*Jan-Nano-128k: Empowering deeper research through extended context understanding.* + + + +--- + +# ๐Ÿš€ If you find these models useful + +Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**: + +๐Ÿ‘‰ [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) + + +The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder) + +๐Ÿ’ฌ **How to test**: + Choose an **AI assistant type**: + - `TurboLLM` (GPT-4.1-mini) + - `HugLLM` (Hugginface Open-source models) + - `TestLLM` (Experimental CPU-only) + +### **What Iโ€™m Testing** +Iโ€™m pushing the limits of **small open-source models for AI network monitoring**, specifically: +- **Function calling** against live network services +- **How small can a model go** while still handling: + - Automated **Nmap security scans** + - **Quantum-readiness checks** + - **Network Monitoring tasks** + +๐ŸŸก **TestLLM** โ€“ Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space): +- โœ… **Zero-configuration setup** +- โณ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low. +- ๐Ÿ”ง **Help wanted!** If youโ€™re into **edge-device AI**, letโ€™s collaborate! + +### **Other Assistants** +๐ŸŸข **TurboLLM** โ€“ Uses **gpt-4.1-mini** : +- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. +- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents** +- **Real-time network diagnostics and monitoring** +- **Security Audits** +- **Penetration testing** (Nmap/Metasploit) + +๐Ÿ”ต **HugLLM** โ€“ Latest Open-source models: +- ๐ŸŒ Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita. + +### ๐Ÿ’ก **Example commands you could test**: +1. `"Give me info on my websites SSL certificate"` +2. `"Check if my server is using quantum safe encyption for communication"` +3. `"Run a comprehensive security audit on my server"` +4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution! + +### Final Word + +I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAIโ€”all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful. + +If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) โ˜•. Your support helps cover service costs and allows me to raise token limits for everyone. + +I'm also open to job opportunities or sponsorship. + +Thank you! ๐Ÿ˜Š 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