初始化项目，由ModelHub XC社区提供模型

Model: Lewdiculous/Kunocchini-7b-128k-test-GGUF-Imatrix
Source: Original Platform

.gitattributes

@@ -0,0 +1,57 @@
+*.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-Kunocchini-7b-128k-test-F16.dat filter=lfs diff=lfs merge=lfs -text
+Kunocchini-7b-128k-test-IQ3_S-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+Kunocchini-7b-128k-test-Q3_K_M-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+Kunocchini-7b-128k-test-Q4_K_M-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+Kunocchini-7b-128k-test-Q4_K_S-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+Kunocchini-7b-128k-test-Q5_K_M-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+Kunocchini-7b-128k-test-Q5_K_S-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+Kunocchini-7b-128k-test-Q6_K-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+Kunocchini-7b-128k-test-Q8_0-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+v2_imatrix-Kunocchini-7b-128k-test-F16.dat filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-F16.gguf filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-IQ3_M-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-IQ3_S-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-IQ3_XXS-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-Q4_K_M-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-Q4_K_S-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-Q5_K_M-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-Q5_K_S-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-Q6_K-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-Q8_0-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-IQ4_NL-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+v2_Kunocchini-7b-128k-test-IQ4_XS-imatrix.gguf filter=lfs diff=lfs merge=lfs -text

Kunocchini-7b-128k-test-IQ3_S-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6fce2f11cad39bff5f0e4337fb7c5662de7c2ad310e8239822c64d3248d9071
+size 3182393312

Kunocchini-7b-128k-test-Q3_K_M-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a296c76cf00a00e65c08ae5e36a18b8257e7fe536bcd443a6af02b6be57f956
+size 3518986208

Kunocchini-7b-128k-test-Q4_K_M-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334f0ba17bbd066575405f4c3448f889dcba26c0b70cfdcf47d93e22c5bcd9da
+size 4368439264

Kunocchini-7b-128k-test-Q4_K_S-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7a1abd41e3905b78c4702f5220b6b784aded935e44b262badc73604a2f66b4
+size 4140373984

Kunocchini-7b-128k-test-Q5_K_M-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab205ae64b5ebc9ef1ea55f28bf78a836988069f5204ba66bf7a2b0de9eb27a
+size 5131409376

Kunocchini-7b-128k-test-Q5_K_S-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a9b7022b08f49e9cd95da01097d83851c556e2e5d8a35c5436e91e1766ba44
+size 4997715936

Kunocchini-7b-128k-test-Q6_K-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:356dea3e2c418794a4d5b64c16e60d8e290c4054182a2e677233a2b4aa48767d
+size 5942065120

Kunocchini-7b-128k-test-Q8_0-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6639e5830eacd503bdef42bd8e53aafb3cca7e52e7c0db189baed4efd6146054
+size 7695857632

README.md

@@ -0,0 +1,93 @@
+---
+base_model:
+- SanjiWatsuki/Kunoichi-DPO-v2-7B
+- Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context
+library_name: transformers
+tags:
+- mistral
+- quantized
+- text-generation-inference
+- merge
+- mergekit
+pipeline_tag: text-generation
+inference: false
+
+---
+
+> [!TIP]
+> **Support:** <br>
+> My upload speeds have been cooked and unstable lately. <br>
+> Realistically I'd need to move to get a better provider. <br>
+> If you **want** and you are able to... <br>
+> [**You can support my various endeavors here (Ko-fi).**](https://ko-fi.com/Lewdiculous) <br>
+> I apologize for disrupting your experience.
+
+
+# **GGUF-Imatrix quantizations for [Kunocchini-7b-128k-test](https://huggingface.co/Test157t/Kunocchini-7b-128k-test/).**
+
+# UPDATED: Please download the v2 files that are now available. The new IQ4_NL and IQ4_XS quants were also added.
+
+# What does "Imatrix" mean?
+
+It stands for **Importance Matrix**, a technique used to improve the quality of quantized models.
+
+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.
+
+One of the benefits of using an Imatrix is that it can lead to better model performance, especially when the calibration data is diverse.
+
+More information: [[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
+
+## *This has been my personal favourite and daily-driver role-play model for a while, so I decided to make new quantizations for it using the full F16-Imatrix data.*
+
+SillyTavern preset files are located [here](https://huggingface.co/Test157t/Kunocchini-7b-128k-test/tree/main/ST%20presets).
+
+*If you want any specific quantization to be added, feel free to ask.*
+
+All credits belong to the [creator](https://huggingface.co/Test157t/).
+
+`Base⇢ GGUF(F16)⇢ GGUF(Quants)`
+
+The new **IQ3_S** merged today 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.
+
+Using [llama.cpp](https://github.com/ggerganov/llama.cpp/)-[b2254](https://github.com/ggerganov/llama.cpp/releases/tag/b2254).
+
+For --imatrix data, `imatrix-Kunocchini-7b-128k-test-F16.dat` was used.
+
+# Original model information:
+
+Thanks to @Epiculous for the dope model/ help with llm backends and support overall.
+
+Id like to also thank @kalomaze for the dope sampler additions to ST. 
+
+@SanjiWatsuki Thank you very much for the help, and the model!
+
+ST users can find the TextGenPreset in the folder labeled so.
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/9obNSalcJqCilQwr_4ssM.jpeg)
+
+The following models were included in the merge:
+* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
+* [Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context](https://huggingface.co/Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
+        layer_range: [0, 32]
+      - model: Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```

imatrix-Kunocchini-7b-128k-test-F16.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d179b065033b9907d09c5b991580d4223bd2ddc75b063afc4a87f6796d8e1fb0
+size 4988126

v2_Kunocchini-7b-128k-test-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e3747cea185e3fcb518ffcb7fe49a928a8e58a0af8d615471da85f6395bbf6d
+size 14484732032

v2_Kunocchini-7b-128k-test-IQ3_M-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e57ea37fee39fcc90ecf5fe4485285493f499b39efa824c87349e8c05d65781b
+size 3284891808

v2_Kunocchini-7b-128k-test-IQ3_S-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270c5bb16d56ad4c465119e0523a24dedbde6820914b73d52fb91844679a1c5c
+size 3182393504

v2_Kunocchini-7b-128k-test-IQ3_XXS-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1a18df7bd4f47abe45a78b00c90e8cc057c43f97048770f1ed19c7f93dda51
+size 2827344032

v2_Kunocchini-7b-128k-test-IQ4_NL-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1acc86a04a995851982c49cb51a9a60ff76b22dc0c12319defece68dda957f9b
+size 4125694112

v2_Kunocchini-7b-128k-test-IQ4_XS-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcfc9b46d290ef8d2a0eee88f7d9fab8575ad2f8efdc55c4517a320a4e66dfc0
+size 3907688608

v2_Kunocchini-7b-128k-test-Q4_K_M-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ccec35392f56f66952f8eb2ded2d8aa9a6bb511e9518899d8096326e328edef
+size 4368439456

v2_Kunocchini-7b-128k-test-Q4_K_S-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e963727393579d5f0ce2dccca35ad8a83e6bf8766b2766cfb2e3e5f880fc46
+size 4140374176

v2_Kunocchini-7b-128k-test-Q5_K_M-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56040b0f615318206873540b35e6325a8aa62c80319f0776946218290071b4dc
+size 5131409568

v2_Kunocchini-7b-128k-test-Q5_K_S-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8257933753aee03e01e8471f4470ecf91e7b600a7409d207ed5a55d968fd5306
+size 4997716128

v2_Kunocchini-7b-128k-test-Q6_K-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1713013be486a84dba3353fa82578ffb742eb529e11e513b69a0e8dc81a17b20
+size 5942065312

v2_Kunocchini-7b-128k-test-Q8_0-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e4da5d56970832f046850ab7f0d64d8c47bc224b873b41b974038cf12d2dda
+size 7695857824

v2_imatrix-Kunocchini-7b-128k-test-F16.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6ae535970f146db57076e73a1d79529903c36e667085ff050e03a83a48dae8
+size 4988126