初始化项目，由ModelHub XC社区提供模型

Model: qwp4w3hyb/gemma-2-9b-it-iMat-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,66 @@
+*.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
+gemma-2-9b-it-f32.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it.imatrix filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q4_0_XL.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q4_0_L.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q8_0_XL.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-Q8_0_L.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-9b-it-imat-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,33 @@
+---
+license: gemma
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- google
+- gemma
+- gguf
+- imatrix
+base_model: google/gemma-2-9b-it
+---
+
+# Quant Infos
+
+## Updated for all recent llama.cpp fixes (final logit soft capping+sliding window+tokenizer)
+
+- quants done with an importance matrix for improved quantization loss
+- Requantized ggufs & imatrix from hf bf16
+  - initial version was based on f32 gguf provided by google, which had various issues
+  - also updated for all recent llama.cpp fixes (final logit soft capping+sliding window+tokenizer)
+- Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S
+  - experimental custom quant types
+    - `_L` with `--output-tensor-type f16 --token-embedding-type f16` (same as bartowski's)
+- Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [5fac350b9cc49d0446fc291b9c4ad53666c77591](https://github.com/ggerganov/llama.cpp/commit/5fac350b9cc49d0446fc291b9c4ad53666c77591) (master from 2024-07-02)
+- Imatrix generated with [this](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) multi-purpose dataset by [bartowski](https://huggingface.co/bartowski).
+  ```
+  ./imatrix -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix
+  ```
+
+# Original Model Card
+
+TODO

gemma-2-9b-it-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5242bb21b8acf213f5b6994caed53ffca93c6f6630cdf6831f3944a36284f3a
+size 18490680960

gemma-2-9b-it-imat-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b41e29d45861c4ce78bb01494b198f941e1edffddb63a70d3b4a97d54f67d7
+size 2378565568

gemma-2-9b-it-imat-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2547d288a6997bc921ddc0fa0199ee83665121b62740af411f8237482a937a60
+size 2824931264

gemma-2-9b-it-imat-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a4412fe71355430a90bf1d17f1f9df759fda58e1120aedcc6790aff6e57e9b
+size 3796740032

gemma-2-9b-it-imat-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c171349f4fc134c9ec202ea194ad9f434757f660a4011637bb6670d807d2713e
+size 5183031232

gemma-2-9b-it-imat-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebaac9b6cda0aa407066ad3c1edbdab7b2a565462fc6a5a35aa548b396bd79c
+size 6843426752

gemma-2-9b-it-imat-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6450fde221ba3716ed33941866293db22d4ba210d44f9e9a874d188974132a5b
+size 7729735616

gemma-2-9b-it-imat-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e64b87bf3ca95d03fc1c0b87bcd35314ceb6f87dd75330fa30d3521cfcfd05d
+size 8671438784

gemma-2-9b-it-imat-Q8_0_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e845e46765d46498700814d89b9a611830857a0e427e35371100b58854c6e133
+size 10687309760

gemma-2-9b-it.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ecff7a70e121ec748ac465bacf0f355b0aef1b3546930d17d22d0e238c5c1c
+size 6116920