commit 52062814643d214b621db1421f23402e2237e21f Author: ModelHub XC Date: Tue Jul 21 19:55:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Aurore-Reveil_Koto-Small-7B-IT-IQ2_M.gguf b/Aurore-Reveil_Koto-Small-7B-IT-IQ2_M.gguf new file mode 100644 index 0000000..5474cde --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a58edb1d38bf0fb22a07d7bace0ee08975564921b2317b9b434d245e1a4dfca0 +size 2867920192 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-IQ3_M.gguf b/Aurore-Reveil_Koto-Small-7B-IT-IQ3_M.gguf new file mode 100644 index 0000000..781ab4b --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6455975e5ae3da2160aad918a7b1e6a51d526a8c310cdb4bb213209fd15cb32 +size 3650063680 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-IQ3_XS.gguf b/Aurore-Reveil_Koto-Small-7B-IT-IQ3_XS.gguf new file mode 100644 index 0000000..11ed073 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d98b6e750d8cc031534e71b11a17a916c23cf3bfef6a8f38d3a9484b14fc4186 +size 3396373824 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-IQ3_XXS.gguf b/Aurore-Reveil_Koto-Small-7B-IT-IQ3_XXS.gguf new file mode 100644 index 0000000..85a29e1 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322c6e264ebb755c19b988b0a40b38ae78439423445d4c102f4d1edbebedcca6 +size 3152543040 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-IQ4_NL.gguf b/Aurore-Reveil_Koto-Small-7B-IT-IQ4_NL.gguf new file mode 100644 index 0000000..88fd559 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92890d21792a098cc57717fd71e2cf27b8e215eb06e195349d0d6fdcd726e6f0 +size 4474510656 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-IQ4_XS.gguf b/Aurore-Reveil_Koto-Small-7B-IT-IQ4_XS.gguf new file mode 100644 index 0000000..a4c11e0 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ce23d1a9a3bf77b05250c76ab235533c5bd434f82797dceb1cc12fabf0648eb +size 4260453696 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q2_K.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q2_K.gguf new file mode 100644 index 0000000..f47c012 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bbb393dff7a352dfe902200076050d3e4db21a0687193188a11e15d6c9ee67f +size 3076406592 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q2_K_L.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q2_K_L.gguf new file mode 100644 index 0000000..254a8f8 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9da332a2e88eab5e6b9ec4664e7b1b7cbb8440e1d6f583422b2026207673743a +size 3683126592 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_L.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_L.gguf new file mode 100644 index 0000000..5728cf7 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b349eb3d2be9427deb7c4041751d30e690000a5441de9f2631d1c950c535e04b +size 4138962240 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_M.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_M.gguf new file mode 100644 index 0000000..855108b --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:796e550cafc3d8b454eb2400ea420841d4635c75b3f229d57475f4ebc724b14b +size 3854011712 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_S.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_S.gguf new file mode 100644 index 0000000..0f50dd7 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7095573c331c97f5ea13944c5b159449f09a48da82cc0dfce500f82ca8a79fe0 +size 3525840192 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_XL.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_XL.gguf new file mode 100644 index 0000000..52f1e6b --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:305de438243018453a058b6788923275ecbcf418865e161eef6db11697d54c9f +size 4682583360 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q4_0.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q4_0.gguf new file mode 100644 index 0000000..af8171b --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:792ad810135795675e10265208386945ff5e4558da39dc480c18dafe5ab23aeb +size 4466908480 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q4_1.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q4_1.gguf new file mode 100644 index 0000000..a3d465e --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d57f85b9fe5ea2e09c04759178f3381b5ec818a5c2a9c047abbc77118f0afff +size 4893187392 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_L.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_L.gguf new file mode 100644 index 0000000..913b5b5 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:581e9acf92e7e22f26720e3c36938ad77c971cdebbe8c0ab90ff9f584ed13e37 +size 5145447744 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_M.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_M.gguf new file mode 100644 index 0000000..b79844a --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c38bfa5d8d5100e91a2e0050a0b2f3e082cd4bfd423cb527abc3b6f1ae180c +size 4684340544 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_S.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_S.gguf new file mode 100644 index 0000000..4cc6ead --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2005b3d55682b6f8c064af489019a1366456902c938fbc3a941e7a94011cc4 +size 4480277824 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_L.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_L.gguf new file mode 100644 index 0000000..ede869f --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:931a09aa5ff4af927ffa4bfd2b569c1e54e8adc58d03e9413fd16391046bb5f5 +size 5832002880 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_M.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_M.gguf new file mode 100644 index 0000000..9201340 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c2ac4b0cfa2aed85a8d73454065e9ac25ae2a24cad038263221a982ab67af6 +size 5448555840 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_S.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_S.gguf new file mode 100644 index 0000000..5131935 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a410e72c2e32c32f7b3ae804f87a42984e350e2c3921ef11e11488b12831aab +size 5330738496 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q6_K.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q6_K.gguf new file mode 100644 index 0000000..ad24546 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0da5296df352bc80efaee2b3f02a766032ed28288ccd5ba3df754884879388ca +size 6260534592 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q6_K_L.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q6_K_L.gguf new file mode 100644 index 0000000..de9ac6e --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc373fb8de4f505ecedd8d92ddafeb98777ea542fb32f0e6b5c8f582f59938e +size 6561467712 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-Q8_0.gguf b/Aurore-Reveil_Koto-Small-7B-IT-Q8_0.gguf new file mode 100644 index 0000000..d6e6878 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a93554796485d52b4e998097a44b5cf760bea5ddc2f4b494132d2e3c10feb931 +size 8106511680 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-bf16.gguf b/Aurore-Reveil_Koto-Small-7B-IT-bf16.gguf new file mode 100644 index 0000000..8eba185 --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8350bf50b379015bbdcdb033f21e6a0971f737d5bf46dcb5b00331f6b591d6 +size 15252229152 diff --git a/Aurore-Reveil_Koto-Small-7B-IT-imatrix.gguf b/Aurore-Reveil_Koto-Small-7B-IT-imatrix.gguf new file mode 100644 index 0000000..78faf4b --- /dev/null +++ b/Aurore-Reveil_Koto-Small-7B-IT-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd34d3fa952ce75f3a74a8bdf93662a108bb614f0ff5c7260dfca16618929f2b +size 5162880 diff --git a/README.md b/README.md new file mode 100644 index 0000000..831ec66 --- /dev/null +++ b/README.md @@ -0,0 +1,164 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: Aurore-Reveil/Koto-Small-7B-IT +--- + +## Llamacpp imatrix Quantizations of Koto-Small-7B-IT by Aurore-Reveil + +Using llama.cpp release b6317 for quantization. + +Original model: https://huggingface.co/Aurore-Reveil/Koto-Small-7B-IT + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project + +## Prompt format + +No prompt format found, check original model page + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Koto-Small-7B-IT-bf16.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-bf16.gguf) | bf16 | 15.25GB | false | Full BF16 weights. | +| [Koto-Small-7B-IT-Q8_0.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q8_0.gguf) | Q8_0 | 8.11GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Koto-Small-7B-IT-Q6_K_L.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q6_K_L.gguf) | Q6_K_L | 6.56GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Koto-Small-7B-IT-Q6_K.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q6_K.gguf) | Q6_K | 6.26GB | false | Very high quality, near perfect, *recommended*. | +| [Koto-Small-7B-IT-Q5_K_L.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_L.gguf) | Q5_K_L | 5.83GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Koto-Small-7B-IT-Q5_K_M.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_M.gguf) | Q5_K_M | 5.45GB | false | High quality, *recommended*. | +| [Koto-Small-7B-IT-Q5_K_S.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q5_K_S.gguf) | Q5_K_S | 5.33GB | false | High quality, *recommended*. | +| [Koto-Small-7B-IT-Q4_K_L.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_L.gguf) | Q4_K_L | 5.15GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Koto-Small-7B-IT-Q4_1.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q4_1.gguf) | Q4_1 | 4.89GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Koto-Small-7B-IT-Q4_K_M.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. | +| [Koto-Small-7B-IT-Q3_K_XL.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_XL.gguf) | Q3_K_XL | 4.68GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Koto-Small-7B-IT-Q4_K_S.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q4_K_S.gguf) | Q4_K_S | 4.48GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Koto-Small-7B-IT-Q4_0.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q4_0.gguf) | Q4_0 | 4.47GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Koto-Small-7B-IT-IQ4_NL.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-IQ4_NL.gguf) | IQ4_NL | 4.47GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Koto-Small-7B-IT-IQ4_XS.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-IQ4_XS.gguf) | IQ4_XS | 4.26GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Koto-Small-7B-IT-Q3_K_L.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_L.gguf) | Q3_K_L | 4.14GB | false | Lower quality but usable, good for low RAM availability. | +| [Koto-Small-7B-IT-Q3_K_M.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_M.gguf) | Q3_K_M | 3.85GB | false | Low quality. | +| [Koto-Small-7B-IT-Q2_K_L.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q2_K_L.gguf) | Q2_K_L | 3.68GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Koto-Small-7B-IT-IQ3_M.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-IQ3_M.gguf) | IQ3_M | 3.65GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Koto-Small-7B-IT-Q3_K_S.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q3_K_S.gguf) | Q3_K_S | 3.53GB | false | Low quality, not recommended. | +| [Koto-Small-7B-IT-IQ3_XS.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-IQ3_XS.gguf) | IQ3_XS | 3.40GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Koto-Small-7B-IT-IQ3_XXS.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-IQ3_XXS.gguf) | IQ3_XXS | 3.15GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Koto-Small-7B-IT-Q2_K.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-Q2_K.gguf) | Q2_K | 3.08GB | false | Very low quality but surprisingly usable. | +| [Koto-Small-7B-IT-IQ2_M.gguf](https://huggingface.co/bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF/blob/main/Aurore-Reveil_Koto-Small-7B-IT-IQ2_M.gguf) | IQ2_M | 2.87GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF --include "Aurore-Reveil_Koto-Small-7B-IT-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF --include "Aurore-Reveil_Koto-Small-7B-IT-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (Aurore-Reveil_Koto-Small-7B-IT-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file