From 1a7de69876a9827b23c66283e59370ec1972b316 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 15 Jul 2026 16:17:16 +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: Lewdiculous/Layris_9B-GGUF-IQ-Imatrix Source: Original Platform --- .gitattributes | 48 +++++++++++++++++ Layris_9B-F16.gguf | 3 ++ Layris_9B-IQ3_M-imat.gguf | 3 ++ Layris_9B-IQ3_S-imat.gguf | 3 ++ Layris_9B-IQ3_XS-imat.gguf | 3 ++ Layris_9B-IQ3_XXS-imat.gguf | 3 ++ Layris_9B-IQ4_XS-imat.gguf | 3 ++ Layris_9B-Q4_K_M-imat.gguf | 3 ++ Layris_9B-Q4_K_S-imat.gguf | 3 ++ Layris_9B-Q5_K_M-imat.gguf | 3 ++ Layris_9B-Q5_K_S-imat.gguf | 3 ++ Layris_9B-Q6_K-imat.gguf | 3 ++ Layris_9B-Q8_0-imat.gguf | 3 ++ README.md | 103 ++++++++++++++++++++++++++++++++++++ imatrix.dat | 3 ++ 15 files changed, 190 insertions(+) create mode 100644 .gitattributes create mode 100644 Layris_9B-F16.gguf create mode 100644 Layris_9B-IQ3_M-imat.gguf create mode 100644 Layris_9B-IQ3_S-imat.gguf create mode 100644 Layris_9B-IQ3_XS-imat.gguf create mode 100644 Layris_9B-IQ3_XXS-imat.gguf create mode 100644 Layris_9B-IQ4_XS-imat.gguf create mode 100644 Layris_9B-Q4_K_M-imat.gguf create mode 100644 Layris_9B-Q4_K_S-imat.gguf create mode 100644 Layris_9B-Q5_K_M-imat.gguf create mode 100644 Layris_9B-Q5_K_S-imat.gguf create mode 100644 Layris_9B-Q6_K-imat.gguf create mode 100644 Layris_9B-Q8_0-imat.gguf create mode 100644 README.md create mode 100644 imatrix.dat diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8b7038f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Layris_9B-IQ4_XS-imat.gguf filter=lfs diff=lfs merge=lfs -text +Layris_9B-Q4_K_M-imat.gguf filter=lfs diff=lfs merge=lfs -text +Layris_9B-Q4_K_S-imat.gguf filter=lfs diff=lfs merge=lfs -text +Layris_9B-Q5_K_M-imat.gguf filter=lfs diff=lfs merge=lfs -text +Layris_9B-Q5_K_S-imat.gguf filter=lfs diff=lfs merge=lfs -text +Layris_9B-Q6_K-imat.gguf filter=lfs diff=lfs merge=lfs -text +Layris_9B-IQ3_M-imat.gguf filter=lfs diff=lfs merge=lfs -text +Layris_9B-IQ3_S-imat.gguf filter=lfs diff=lfs merge=lfs -text +Layris_9B-Q8_0-imat.gguf filter=lfs diff=lfs merge=lfs -text +Layris_9B-F16.gguf filter=lfs diff=lfs merge=lfs -text +Layris_9B-IQ3_XS-imat.gguf filter=lfs diff=lfs merge=lfs -text +Layris_9B-IQ3_XXS-imat.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Layris_9B-F16.gguf b/Layris_9B-F16.gguf new file mode 100644 index 0000000..7c69aca --- /dev/null +++ b/Layris_9B-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:198a78c9c8660722653fec4a57e1652c453ffbc3981d20cb7b6d0b6f2e37c80f +size 17974658944 diff --git a/Layris_9B-IQ3_M-imat.gguf b/Layris_9B-IQ3_M-imat.gguf new file mode 100644 index 0000000..64edc90 --- /dev/null +++ b/Layris_9B-IQ3_M-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9256ba6ac3168c6f582ab44a0a25449104da3aee75c0b21803c098b20147bdbd +size 4064970688 diff --git a/Layris_9B-IQ3_S-imat.gguf b/Layris_9B-IQ3_S-imat.gguf new file mode 100644 index 0000000..df1c6bc --- /dev/null +++ b/Layris_9B-IQ3_S-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:660f24fb6a21b6cc3ea9ca07ff36b79c3cb809419737de466f1a1285547cf508 +size 3936847808 diff --git a/Layris_9B-IQ3_XS-imat.gguf b/Layris_9B-IQ3_XS-imat.gguf new file mode 100644 index 0000000..8ac8f9d --- /dev/null +++ b/Layris_9B-IQ3_XS-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee06efddc656481179fcbaac03c2f2f07d3de5379840eea4b1caa81c09282ceb +size 3710093248 diff --git a/Layris_9B-IQ3_XXS-imat.gguf b/Layris_9B-IQ3_XXS-imat.gguf new file mode 100644 index 0000000..24bec08 --- /dev/null +++ b/Layris_9B-IQ3_XXS-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba9c2dc2ec7fcca68f70c2db2f2cbc25f9ffcaa8c7a0d2cef1dd93926bdc472d +size 3497387968 diff --git a/Layris_9B-IQ4_XS-imat.gguf b/Layris_9B-IQ4_XS-imat.gguf new file mode 100644 index 0000000..a45d514 --- /dev/null +++ b/Layris_9B-IQ4_XS-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e803b83adf6227ef05d3ee066e791053b9ebbf0e5104bba9e715acfc89ed7758 +size 4840138688 diff --git a/Layris_9B-Q4_K_M-imat.gguf b/Layris_9B-Q4_K_M-imat.gguf new file mode 100644 index 0000000..683d871 --- /dev/null +++ b/Layris_9B-Q4_K_M-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2aa01995c48654d50cc36f6c0ede8f8c79d614442356a069066ea6b61b55a9a +size 5415053248 diff --git a/Layris_9B-Q4_K_S-imat.gguf b/Layris_9B-Q4_K_S-imat.gguf new file mode 100644 index 0000000..51cde4c --- /dev/null +++ b/Layris_9B-Q4_K_S-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf01d4354d9a2ed1942dcfbea0a135cbb7dc9c0b0d0832ccf6a4dd5aee52c65 +size 5129447360 diff --git a/Layris_9B-Q5_K_M-imat.gguf b/Layris_9B-Q5_K_M-imat.gguf new file mode 100644 index 0000000..6a3ebea --- /dev/null +++ b/Layris_9B-Q5_K_M-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d567b5515417793b688ee8b513ec630e897ce21481798a487d78e1952fccb437 +size 6364669888 diff --git a/Layris_9B-Q5_K_S-imat.gguf b/Layris_9B-Q5_K_S-imat.gguf new file mode 100644 index 0000000..3e31019 --- /dev/null +++ b/Layris_9B-Q5_K_S-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be468ad7b725eb954392d5e52c4b01df740c9e055d85898ce9313a12dae88e23 +size 6197553088 diff --git a/Layris_9B-Q6_K-imat.gguf b/Layris_9B-Q6_K-imat.gguf new file mode 100644 index 0000000..c3ea1dd --- /dev/null +++ b/Layris_9B-Q6_K-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ed8dcb2fb8c9861f4a9d5fd1dadb4489852cbd1a0fb364e05f15e818fd10d87 +size 7373637568 diff --git a/Layris_9B-Q8_0-imat.gguf b/Layris_9B-Q8_0-imat.gguf new file mode 100644 index 0000000..84e6cc3 --- /dev/null +++ b/Layris_9B-Q8_0-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128e9bd5fd37b344605196ea1ff7e07ad0a4f9efc13bb5159ef6dccfebc9e150 +size 9550006208 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7d25544 --- /dev/null +++ b/README.md @@ -0,0 +1,103 @@ +--- +library_name: transformers +tags: +- mistral +- quantized +- text-generation-inference +- roleplay +# - rp +# - uncensored +pipeline_tag: text-generation +inference: false +# language: +# - en +# FILL THE INFORMATION: +# Reference: ChaoticNeutrals/Layris_9B +# Author: ChaoticNeutrals +# Model: Layris_9B +# Llama.cpp version: b2350 +--- + +> [!TIP] +> **Support:**
+> My upload speeds have been cooked and unstable lately.
+> Realistically I'd need to move to get a better provider.
+> If you **want** and you are able to...
+> [**You can support my various endeavors here (Ko-fi).**](https://ko-fi.com/Lewdiculous)
+> I apologize for disrupting your experience. + + +```python + quantization_options = [ + "Q4_K_M", "Q4_K_S", "IQ4_XS", "Q5_K_M", + "Q5_K_S", "Q6_K", "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XS", "IQ3_XXS" + ] +``` + +## GGUF-Imatrix quantizations for [ChaoticNeutrals/Layris_9B](https://huggingface.co/ChaoticNeutrals/Layris_9B/). + +All credits belong to the author. + +If you liked these, check out the work with [FantasiaFoundry's GGUF-IQ-Imatrix-Quantization-Script](https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script). + +**Personal note:** + +This model should give you less refusals, given it's merged with the unhinged **Layla-V4**. + +## What does "Imatrix" mean? + +It stands for **Importance Matrix**, a technique used to improve the quality of quantized models.
+[[1]](https://github.com/ggerganov/llama.cpp/discussions/5006/)
+The **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process. The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance and lead to better quality preservation, especially when the calibration data is diverse.
+[[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384/) + +For --imatrix data, included `imatrix.dat` was used. + +Using [llama.cpp-b2350](https://github.com/ggerganov/llama.cpp/releases/tag/b2350/): + +``` +Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants) +``` + +The new **IQ3_S** quant-option has shown to be better than the old Q3_K_S, so I added that instead of the later. Only supported in `koboldcpp-1.59.1` or higher. + +If you want any specific quantization to be added, feel free to ask. + +## Model card: + +![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/aK81BYLc8LzspT5h68hET.jpeg) + +## Original model information: + +# Layris + +![image/jpeg](https://i.imgur.com/yRGzsoO.jpeg) + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). + +## Merge Details +### Merge Method + +This model was merged using the passthrough merge method. + +### Models Merged + +The following models were included in the merge: +* [ChaoticNeutrals/Eris_Remix_7B](https://huggingface.co/ChaoticNeutrals/Eris_Remix_7B) +* [l3utterfly/mistral-7b-v0.1-layla-v4](https://huggingface.co/l3utterfly/mistral-7b-v0.1-layla-v4) + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +slices: + - sources: + - model: ChaoticNeutrals/Eris_Remix_7B + layer_range: [0, 20] + - sources: + - model: l3utterfly/mistral-7b-v0.1-layla-v4 + layer_range: [12, 32] +merge_method: passthrough +dtype: float16 +``` diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..a4a9ae1 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:708cdc2452de406998506bd4efa922b78698cef974125f2e5aad5f9e21f6c0b9 +size 6235174