commit 99cefda7a7a60150e7d6c8a47e0bfebf557d37b5 Author: ModelHub XC Date: Wed Jul 29 20:20:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Lewdiculous/mistral-7b-v0.1-layla-v4-GGUF-IQ-Imatrix Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ef2f0b1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +mistral-7b-v0.1-layla-v4-IQ3_M-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-IQ3_S-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-IQ3_XS-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-IQ3_XXS-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-IQ4_NL-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-IQ4_XS-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-Q4_K_M-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-Q4_K_S-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-Q5_K_M-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-Q5_K_S-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-Q6_K-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-Q8_0-imat.gguf filter=lfs diff=lfs merge=lfs -text +mistral-7b-v0.1-layla-v4-F16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1e30f7b --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +license: apache-2.0 +library_name: transformers +tags: +- mistral +- quantized +- text-generation-inference +- roleplay +# - rp +# - uncensored +pipeline_tag: text-generation +inference: false +# language: +# - en +# FILL THE INFORMATION: +# Reference: l3utterfly/mistral-7b-v0.1-layla-v4 +# Author: l3utterfly +# Model: mistral-7b-v0.1-layla-v4 +# Llama.cpp version: b2321 +--- + +## GGUF-Imatrix quantizations for [l3utterfly/mistral-7b-v0.1-layla-v4](https://huggingface.co/l3utterfly/mistral-7b-v0.1-layla-v4/). + +All credits belong to the author. + +If you like these also check out [FantasiaFoundry's GGUF-Quantization-Script](https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script). + +## 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 performance, 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-b2321](https://github.com/ggerganov/llama.cpp/releases/tag/b2321/): + +``` +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 image: + +![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/2ZlUf8FBkp2PSVvNMWmjJ.jpeg) + +## Original model information: + + +# Model Card + +### Model Description + +Mistral 7B fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation. + +The dataset has been pre-processed by doing the following: +1. remove all refusals +2. remove any mention of AI assistant +3. split any multi-turn dialog generated in the dataset into multi-turn conversations records +4. added nfsw generated conversations from the Teatime dataset + +- **Developed by:** l3utterfly +- **Funded by:** Layla Network +- **Model type:** Mistral +- **Language(s) (NLP):** English +- **License:** Apache-2.0 +- **Finetuned from model:** Mistral 7B + +## Uses + +Base model used by Layla - the offline personal assistant: https://www.layla-network.ai + +Help & support: https://discord.gg/x546YJ6nYC + +Prompt: +``` +USER: +ASSISTANT: +``` + +[Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) \ No newline at end of file diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..551bef3 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1577f99db51a6d80ade9c46fbb32461998c0598a7c28fe67fe414303b6bfd04c +size 4988126 diff --git a/mistral-7b-v0.1-layla-v4-F16.gguf b/mistral-7b-v0.1-layla-v4-F16.gguf new file mode 100644 index 0000000..08705da --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:726332d0e9936c33a75475d44f4c82965d4e17de1bc146b4f8dee097ebb5724e +size 14484731552 diff --git a/mistral-7b-v0.1-layla-v4-IQ3_M-imat.gguf b/mistral-7b-v0.1-layla-v4-IQ3_M-imat.gguf new file mode 100644 index 0000000..1fae74b --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-IQ3_M-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae9552e5f90a689c0c0c70de9a9c26e2b401aafd4b05eb1587e366459cc4b229 +size 3284891360 diff --git a/mistral-7b-v0.1-layla-v4-IQ3_S-imat.gguf b/mistral-7b-v0.1-layla-v4-IQ3_S-imat.gguf new file mode 100644 index 0000000..93db423 --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-IQ3_S-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88be4ae0c73b98d87bef8aa43e8189e295b36db45857262158d346397171f31e +size 3182393056 diff --git a/mistral-7b-v0.1-layla-v4-IQ3_XS-imat.gguf b/mistral-7b-v0.1-layla-v4-IQ3_XS-imat.gguf new file mode 100644 index 0000000..39bee15 --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-IQ3_XS-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e29bb21d935a2d50d002cd61ceeca3c8b27c1e7bddf023d813f255666b2d7b +size 3000989408 diff --git a/mistral-7b-v0.1-layla-v4-IQ3_XXS-imat.gguf b/mistral-7b-v0.1-layla-v4-IQ3_XXS-imat.gguf new file mode 100644 index 0000000..4f25cd9 --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-IQ3_XXS-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e33179847f71b689fdf2b6e3a6d1a700dc3c73e8f38ceb3bde9d6196fcc5a26 +size 2827343584 diff --git a/mistral-7b-v0.1-layla-v4-IQ4_NL-imat.gguf b/mistral-7b-v0.1-layla-v4-IQ4_NL-imat.gguf new file mode 100644 index 0000000..c935515 --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-IQ4_NL-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c96cec5d258c53936f90db6971b719c02cba7cfb32d389224ce74f93a5269973 +size 4125693664 diff --git a/mistral-7b-v0.1-layla-v4-IQ4_XS-imat.gguf b/mistral-7b-v0.1-layla-v4-IQ4_XS-imat.gguf new file mode 100644 index 0000000..65b7e6f --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-IQ4_XS-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a22fb5d49cff39b2186b8b0b5c68b025036e8e02388808123846c60ebd1689 +size 3907688160 diff --git a/mistral-7b-v0.1-layla-v4-Q4_K_M-imat.gguf b/mistral-7b-v0.1-layla-v4-Q4_K_M-imat.gguf new file mode 100644 index 0000000..fb55f68 --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-Q4_K_M-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:688b9728c08ebbda67186e35410f76607c46fee5ec1e2dccd69c7775d25d7cbe +size 4368439008 diff --git a/mistral-7b-v0.1-layla-v4-Q4_K_S-imat.gguf b/mistral-7b-v0.1-layla-v4-Q4_K_S-imat.gguf new file mode 100644 index 0000000..f758c9d --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-Q4_K_S-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2402b5b1d599aa9444493eb803f8b6b124ff36de2e8da7d28a79ae9fd1b2f3f +size 4140373728 diff --git a/mistral-7b-v0.1-layla-v4-Q5_K_M-imat.gguf b/mistral-7b-v0.1-layla-v4-Q5_K_M-imat.gguf new file mode 100644 index 0000000..bbf1f35 --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-Q5_K_M-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ce75a48af55b908a18cf6232d8cb466b6bfcf44420e82d17a4c8c6fa88dd24c +size 5131409120 diff --git a/mistral-7b-v0.1-layla-v4-Q5_K_S-imat.gguf b/mistral-7b-v0.1-layla-v4-Q5_K_S-imat.gguf new file mode 100644 index 0000000..e4a3580 --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-Q5_K_S-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d992976487517db91590f64c59ff5b89b26e7b7f3187e26476d75b1c7f9f1c1 +size 4997715680 diff --git a/mistral-7b-v0.1-layla-v4-Q6_K-imat.gguf b/mistral-7b-v0.1-layla-v4-Q6_K-imat.gguf new file mode 100644 index 0000000..35e5a83 --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-Q6_K-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eef5bb376191f942d26dadd82b2d9539d898fa5a289c7c4bddbfda34a4186a96 +size 5942064864 diff --git a/mistral-7b-v0.1-layla-v4-Q8_0-imat.gguf b/mistral-7b-v0.1-layla-v4-Q8_0-imat.gguf new file mode 100644 index 0000000..111d485 --- /dev/null +++ b/mistral-7b-v0.1-layla-v4-Q8_0-imat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:002ca8f09394703f35fe7d6da08634bbce024123d3f0497a41f58890500f7704 +size 7695857376