From 92e5d6667e0ccdedefa802a6791a90c3f9c95caa Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 22 Jun 2026 14:20:18 +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: Quant-Cartel/Luca-MN-iMat-GGUF Source: Original Platform --- .gitattributes | 50 +++++++++++++++++++++++++++++++++++++ Luca-MN-F32.imatrix | 3 +++ Luca-MN-iMat-IQ1_M.gguf | 3 +++ Luca-MN-iMat-IQ1_S.gguf | 3 +++ Luca-MN-iMat-IQ4_XS.gguf | 3 +++ Luca-MN-iMat-Q2_K.gguf | 3 +++ Luca-MN-iMat-Q3_K_L.gguf | 3 +++ Luca-MN-iMat-Q3_K_M.gguf | 3 +++ Luca-MN-iMat-Q3_K_S.gguf | 3 +++ Luca-MN-iMat-Q4_K_M.gguf | 3 +++ Luca-MN-iMat-Q4_K_S.gguf | 3 +++ Luca-MN-iMat-Q5_K_M.gguf | 3 +++ Luca-MN-iMat-Q5_K_S.gguf | 3 +++ Luca-MN-iMat-Q6_K.gguf | 3 +++ Luca-MN-iMat-Q8_0.gguf | 3 +++ README.md | 53 ++++++++++++++++++++++++++++++++++++++++ 16 files changed, 145 insertions(+) create mode 100644 .gitattributes create mode 100644 Luca-MN-F32.imatrix create mode 100644 Luca-MN-iMat-IQ1_M.gguf create mode 100644 Luca-MN-iMat-IQ1_S.gguf create mode 100644 Luca-MN-iMat-IQ4_XS.gguf create mode 100644 Luca-MN-iMat-Q2_K.gguf create mode 100644 Luca-MN-iMat-Q3_K_L.gguf create mode 100644 Luca-MN-iMat-Q3_K_M.gguf create mode 100644 Luca-MN-iMat-Q3_K_S.gguf create mode 100644 Luca-MN-iMat-Q4_K_M.gguf create mode 100644 Luca-MN-iMat-Q4_K_S.gguf create mode 100644 Luca-MN-iMat-Q5_K_M.gguf create mode 100644 Luca-MN-iMat-Q5_K_S.gguf create mode 100644 Luca-MN-iMat-Q6_K.gguf create mode 100644 Luca-MN-iMat-Q8_0.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..84cc781 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +SorcererLM-22B-iMat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-iMat-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Luca-MN-F32.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/Luca-MN-F32.imatrix b/Luca-MN-F32.imatrix new file mode 100644 index 0000000..cf4a82b --- /dev/null +++ b/Luca-MN-F32.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58e991daf8fbf4343fd2e7626fc15eb528e84886cb9e57f96a790c2362901d76 +size 7054409 diff --git a/Luca-MN-iMat-IQ1_M.gguf b/Luca-MN-iMat-IQ1_M.gguf new file mode 100644 index 0000000..8560781 --- /dev/null +++ b/Luca-MN-iMat-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e60677924da2036dac17b2c4f850cdcf55d1fb0ba95fe8b20fd4287130c28c5 +size 3221625280 diff --git a/Luca-MN-iMat-IQ1_S.gguf b/Luca-MN-iMat-IQ1_S.gguf new file mode 100644 index 0000000..2d56026 --- /dev/null +++ b/Luca-MN-iMat-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86122765ef3f7609d3d8d5c5130b91dfb6deaae6dee4746682bb8b2c3c9d5202 +size 2999212480 diff --git a/Luca-MN-iMat-IQ4_XS.gguf b/Luca-MN-iMat-IQ4_XS.gguf new file mode 100644 index 0000000..ad17679 --- /dev/null +++ b/Luca-MN-iMat-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:485eb49c617929d319ed371bd39bd0ccf34d67d6fc342744ff6b99555b8b1335 +size 6742710720 diff --git a/Luca-MN-iMat-Q2_K.gguf b/Luca-MN-iMat-Q2_K.gguf new file mode 100644 index 0000000..6e219bf --- /dev/null +++ b/Luca-MN-iMat-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77b3336d8317890be9877021df19f7f098aace637bfcec707b512303f540910 +size 4791048640 diff --git a/Luca-MN-iMat-Q3_K_L.gguf b/Luca-MN-iMat-Q3_K_L.gguf new file mode 100644 index 0000000..53b01f7 --- /dev/null +++ b/Luca-MN-iMat-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f266fe667608d3da688b796d923dbeea8b931444c0e99b511caae33f1b80737a +size 6561503680 diff --git a/Luca-MN-iMat-Q3_K_M.gguf b/Luca-MN-iMat-Q3_K_M.gguf new file mode 100644 index 0000000..22d8e3d --- /dev/null +++ b/Luca-MN-iMat-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0dd286119a4c9c7daa635e4b2ce4dff3c7459e7d8559abe2c8e55bf18ac2674 +size 6083090880 diff --git a/Luca-MN-iMat-Q3_K_S.gguf b/Luca-MN-iMat-Q3_K_S.gguf new file mode 100644 index 0000000..cdedeb5 --- /dev/null +++ b/Luca-MN-iMat-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a459d49333383a6cb0aed6b1a416c70f51065928271b1443ece124224b833b +size 5534226880 diff --git a/Luca-MN-iMat-Q4_K_M.gguf b/Luca-MN-iMat-Q4_K_M.gguf new file mode 100644 index 0000000..8aaa995 --- /dev/null +++ b/Luca-MN-iMat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fef7f7a37d278bbb25478de3e10e856a27e66128f722b967925db01f7b48ca23 +size 7477205440 diff --git a/Luca-MN-iMat-Q4_K_S.gguf b/Luca-MN-iMat-Q4_K_S.gguf new file mode 100644 index 0000000..d00b60c --- /dev/null +++ b/Luca-MN-iMat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd64554a8afee819cd523374a797810e3e48a9c485d65669bd9cba867436c4ee +size 7120198080 diff --git a/Luca-MN-iMat-Q5_K_M.gguf b/Luca-MN-iMat-Q5_K_M.gguf new file mode 100644 index 0000000..7a5dec9 --- /dev/null +++ b/Luca-MN-iMat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b61b1c4df6eaacb2c4d8f915c1560142a9016c9af33fe0b7268a3e1f6258dca +size 8727632320 diff --git a/Luca-MN-iMat-Q5_K_S.gguf b/Luca-MN-iMat-Q5_K_S.gguf new file mode 100644 index 0000000..4865d2a --- /dev/null +++ b/Luca-MN-iMat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab63add7cb77bac6b68ed74e08f99b92badaa1bc8775213cbef5727bb7491a8b +size 8518736320 diff --git a/Luca-MN-iMat-Q6_K.gguf b/Luca-MN-iMat-Q6_K.gguf new file mode 100644 index 0000000..7c2be8c --- /dev/null +++ b/Luca-MN-iMat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384978819ef72d08e0743eedf8188105b7bea64b066fa315d64eb6f0db3dc340 +size 10056210880 diff --git a/Luca-MN-iMat-Q8_0.gguf b/Luca-MN-iMat-Q8_0.gguf new file mode 100644 index 0000000..586b27f --- /dev/null +++ b/Luca-MN-iMat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31836ce62d9aac470346f84e03e5af194bb9bf0e648b86d55d508d5d8961b56e +size 13022370240 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b3bcab8 --- /dev/null +++ b/README.md @@ -0,0 +1,53 @@ +--- +license: apache-2.0 +base_model_relation: quantized +quantized_by: Quant-Cartel +base_model: rAIfle/Luca-MN-bf16 +pipeline_tag: text-generation +tags: +- iMat +- GGUF +- unsloth +- trl +- sft +--- +``` + e88 88e d8 + d888 888b 8888 8888 ,"Y88b 888 8e d88 +C8888 8888D 8888 8888 "8" 888 888 88b d88888 + Y888 888P Y888 888P ,ee 888 888 888 888 + "88 88" "88 88" "88 888 888 888 888 + b + 8b, + + e88'Y88 d8 888 + d888 'Y ,"Y88b 888,8, d88 ,e e, 888 +C8888 "8" 888 888 " d88888 d88 88b 888 + Y888 ,d ,ee 888 888 888 888 , 888 + "88,d88 "88 888 888 888 "YeeP" 888 + +PROUDLY PRESENTS +``` +# Luca-MN-iMat-GGUF + +Quantized with love from fp32. + +* Importance Matrix calculated using [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) +* 92 chunks +* n_ctx=512 +* Importance Matrix uses fp32 precision model weights, fp32.imatrix file to be added in repo + +Original model README [here](https://huggingface.co/rAIFle/Luca-MN-bf16) and below: + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6569a4ed2419be6072890cf8/T_ITjuaHakgamjwuElcAs.png) + +## Luca-MN-iMat-GGUF + + +This thing was just intended as an experiment but it turned out quite good. I had it both name and prompt imagegen for itself. + +Created by running a high-r LoRA-pass over Nemo-Base with 2 epochs of some RP data, then a low-r pass with 0.5 epochs of the c2-data, then 3 epochs of DPO using [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1). + +## Prompting + +Use the `Mistral V3-Tekken` context- and instruct-templates. Temperature at about `1.25` seems to be the sweet spot, with either MinP at `0.05` or TopP at `0.9`. DRY/Smoothing etc depending on your preference. \ No newline at end of file