commit 9ba340aba9d03fa6ebde143b3a3d14b458bbc52a Author: ModelHub XC Date: Thu Jul 30 18:19:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/POLARIS-Project_Polaris-7B-Preview-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/POLARIS-Project_Polaris-7B-Preview-IQ2_M.gguf b/POLARIS-Project_Polaris-7B-Preview-IQ2_M.gguf new file mode 100644 index 0000000..fce1c28 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4121a48ba4d9a146db4e91ad047214ed71353172fa64fbd41073c86b7475daec +size 2780342592 diff --git a/POLARIS-Project_Polaris-7B-Preview-IQ3_M.gguf b/POLARIS-Project_Polaris-7B-Preview-IQ3_M.gguf new file mode 100644 index 0000000..13d3126 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b1843d131e7eac895879fc0b76c7c32277dea47f8f12d773011470d59d4dca4 +size 3574012224 diff --git a/POLARIS-Project_Polaris-7B-Preview-IQ3_XS.gguf b/POLARIS-Project_Polaris-7B-Preview-IQ3_XS.gguf new file mode 100644 index 0000000..98bdcf9 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8dc0461fa86c95e63694aa638b44c887f0f7ce858914e7ea714bd5c76903f2f +size 3346256192 diff --git a/POLARIS-Project_Polaris-7B-Preview-IQ3_XXS.gguf b/POLARIS-Project_Polaris-7B-Preview-IQ3_XXS.gguf new file mode 100644 index 0000000..c062b4d --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9be5cdbf660877542e6b0af45966626ca43e6f807d520cfceb6004fd4f51b8a5 +size 3114514752 diff --git a/POLARIS-Project_Polaris-7B-Preview-IQ4_NL.gguf b/POLARIS-Project_Polaris-7B-Preview-IQ4_NL.gguf new file mode 100644 index 0000000..96dbbbb --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1107290b1496a06f4850a21552a5dac05cd46417f406e6937c372eb9c88a9ce +size 4437813568 diff --git a/POLARIS-Project_Polaris-7B-Preview-IQ4_XS.gguf b/POLARIS-Project_Polaris-7B-Preview-IQ4_XS.gguf new file mode 100644 index 0000000..dd2286d --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ca70c1f44634f5c6ab357ab030a78e01d5e06d7056aea42222208eb3f520e04 +size 4218472768 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q2_K.gguf b/POLARIS-Project_Polaris-7B-Preview-Q2_K.gguf new file mode 100644 index 0000000..6e0276b --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f83b64e2f25cd04ba6a84a4616ad57a358aba1a9ab1941344952c5ccabfc8d7 +size 3015940416 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q2_K_L.gguf b/POLARIS-Project_Polaris-7B-Preview-Q2_K_L.gguf new file mode 100644 index 0000000..5d2a1aa --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4e7c1b27d03390fc92ad785ff701a0d154750dfa8e953a8c9e50d5872c14f9d +size 3548164416 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q3_K_L.gguf b/POLARIS-Project_Polaris-7B-Preview-Q3_K_L.gguf new file mode 100644 index 0000000..35145dc --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be40eb344aaa7ce4359bc221ed9c7ee315639bc9d067d0511916ddb06ae8fe6 +size 4088459584 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q3_K_M.gguf b/POLARIS-Project_Polaris-7B-Preview-Q3_K_M.gguf new file mode 100644 index 0000000..b14f19b --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0fe7076382d72cec88e656e5adbf789577a51e0d15ec26413c4d7521d8cc17 +size 3808391488 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q3_K_S.gguf b/POLARIS-Project_Polaris-7B-Preview-Q3_K_S.gguf new file mode 100644 index 0000000..de67ae1 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:163b911bbf5b8331bcc5ee134e82d9da0a4d8a1c56b6fde04842ef483270993b +size 3492368704 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q3_K_XL.gguf b/POLARIS-Project_Polaris-7B-Preview-Q3_K_XL.gguf new file mode 100644 index 0000000..2ed2e13 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c542d483189beda75651c25cde3acf2b3965aa8525bbcb2ab03dadedc6a68927 +size 4565332288 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q4_0.gguf b/POLARIS-Project_Polaris-7B-Preview-Q4_0.gguf new file mode 100644 index 0000000..8504c2d --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:494cddf494afe4cba0367d379d7ba23b515bf1eb58e20ab5943826794b561eeb +size 4444121408 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q4_1.gguf b/POLARIS-Project_Polaris-7B-Preview-Q4_1.gguf new file mode 100644 index 0000000..fc0b46d --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f829fe421c8db725c6ca15f6dc9e3c18a4baf91bc34830b5416b1da21e04321b +size 4873283904 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q4_K_L.gguf b/POLARIS-Project_Polaris-7B-Preview-Q4_K_L.gguf new file mode 100644 index 0000000..af33051 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1d1c62b199f2d486c57c2c0b323982244eb816686f554186e3e08f5a5df162f +size 5087564096 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q4_K_M.gguf b/POLARIS-Project_Polaris-7B-Preview-Q4_K_M.gguf new file mode 100644 index 0000000..7f54c15 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4c0f7b98472bacf01df64459db9234b512ae607b3a48f1c017429133ac0de81 +size 4683073856 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q4_K_S.gguf b/POLARIS-Project_Polaris-7B-Preview-Q4_K_S.gguf new file mode 100644 index 0000000..090b775 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1306bec7afcd29597d5dc2b4b5ffe7a71fc068629efc1f9d938ebdcb7052cc3d +size 4457769280 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q5_K_L.gguf b/POLARIS-Project_Polaris-7B-Preview-Q5_K_L.gguf new file mode 100644 index 0000000..dbad309 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:857dada71323546ef57bf29f0e04090bc132c3b5eb9852e235e5d529f4c287b4 +size 5781197120 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q5_K_M.gguf b/POLARIS-Project_Polaris-7B-Preview-Q5_K_M.gguf new file mode 100644 index 0000000..1fe48c3 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:408d5ad28b5b37fa91dcc698f8ad0d7f0322b4eb37d6a352d56525075ef85525 +size 5444831552 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q5_K_S.gguf b/POLARIS-Project_Polaris-7B-Preview-Q5_K_S.gguf new file mode 100644 index 0000000..18ab75e --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6180d8faa1d43fe39f83a35b121238a0fb0b3c63cfbdfa61d286514c63a0deb8 +size 5315176768 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q6_K.gguf b/POLARIS-Project_Polaris-7B-Preview-Q6_K.gguf new file mode 100644 index 0000000..5744458 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016867ccd28c2fcaae547656d326fe880b1019c262415a04e08185c973903ec8 +size 6254199104 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q6_K_L.gguf b/POLARIS-Project_Polaris-7B-Preview-Q6_K_L.gguf new file mode 100644 index 0000000..4534850 --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b3819f9b82cbcd4c67cfdef981044e0aedeb0470e435a1318933cdebe3de5c2 +size 6518182208 diff --git a/POLARIS-Project_Polaris-7B-Preview-Q8_0.gguf b/POLARIS-Project_Polaris-7B-Preview-Q8_0.gguf new file mode 100644 index 0000000..b54153c --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e90da8d5fbb7cbdeff1e4591c9581cb521ee475bf525b09f9ecc23eca562537 +size 8098525504 diff --git a/POLARIS-Project_Polaris-7B-Preview-bf16.gguf b/POLARIS-Project_Polaris-7B-Preview-bf16.gguf new file mode 100644 index 0000000..dc68a2a --- /dev/null +++ b/POLARIS-Project_Polaris-7B-Preview-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a81e220ecc768e81440820fce88838b6a0505493748e0a7a932ad33b426f11 +size 15237853216 diff --git a/POLARIS-Project_Polaris-7B-Preview.imatrix b/POLARIS-Project_Polaris-7B-Preview.imatrix new file mode 100644 index 0000000..5f64a06 Binary files /dev/null and b/POLARIS-Project_Polaris-7B-Preview.imatrix differ diff --git a/README.md b/README.md new file mode 100644 index 0000000..ab2d54c --- /dev/null +++ b/README.md @@ -0,0 +1,169 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: POLARIS-Project/Polaris-7B-Preview +base_model_relation: quantized +metrics: +- accuracy +license: apache-2.0 +--- + +## Llamacpp imatrix Quantizations of Polaris-7B-Preview by POLARIS-Project + +Using llama.cpp release b5697 for quantization. + +Original model: https://huggingface.co/POLARIS-Project/Polaris-7B-Preview + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<｜begin▁of▁sentence｜>{system_prompt}<｜User｜>{prompt}<｜Assistant｜><｜end▁of▁sentence｜><｜Assistant｜> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Polaris-7B-Preview-bf16.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-bf16.gguf) | bf16 | 15.24GB | false | Full BF16 weights. | +| [Polaris-7B-Preview-Q8_0.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q8_0.gguf) | Q8_0 | 8.10GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Polaris-7B-Preview-Q6_K_L.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q6_K_L.gguf) | Q6_K_L | 6.52GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Polaris-7B-Preview-Q6_K.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q6_K.gguf) | Q6_K | 6.25GB | false | Very high quality, near perfect, *recommended*. | +| [Polaris-7B-Preview-Q5_K_L.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q5_K_L.gguf) | Q5_K_L | 5.78GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Polaris-7B-Preview-Q5_K_M.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q5_K_M.gguf) | Q5_K_M | 5.44GB | false | High quality, *recommended*. | +| [Polaris-7B-Preview-Q5_K_S.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q5_K_S.gguf) | Q5_K_S | 5.32GB | false | High quality, *recommended*. | +| [Polaris-7B-Preview-Q4_K_L.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q4_K_L.gguf) | Q4_K_L | 5.09GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Polaris-7B-Preview-Q4_1.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q4_1.gguf) | Q4_1 | 4.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Polaris-7B-Preview-Q4_K_M.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. | +| [Polaris-7B-Preview-Q3_K_XL.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q3_K_XL.gguf) | Q3_K_XL | 4.57GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Polaris-7B-Preview-Q4_K_S.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q4_K_S.gguf) | Q4_K_S | 4.46GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Polaris-7B-Preview-Q4_0.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q4_0.gguf) | Q4_0 | 4.44GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Polaris-7B-Preview-IQ4_NL.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ4_NL.gguf) | IQ4_NL | 4.44GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Polaris-7B-Preview-IQ4_XS.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ4_XS.gguf) | IQ4_XS | 4.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Polaris-7B-Preview-Q3_K_L.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. | +| [Polaris-7B-Preview-Q3_K_M.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q3_K_M.gguf) | Q3_K_M | 3.81GB | false | Low quality. | +| [Polaris-7B-Preview-IQ3_M.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ3_M.gguf) | IQ3_M | 3.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Polaris-7B-Preview-Q2_K_L.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q2_K_L.gguf) | Q2_K_L | 3.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Polaris-7B-Preview-Q3_K_S.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q3_K_S.gguf) | Q3_K_S | 3.49GB | false | Low quality, not recommended. | +| [Polaris-7B-Preview-IQ3_XS.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ3_XS.gguf) | IQ3_XS | 3.35GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Polaris-7B-Preview-IQ3_XXS.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ3_XXS.gguf) | IQ3_XXS | 3.11GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Polaris-7B-Preview-Q2_K.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-Q2_K.gguf) | Q2_K | 3.02GB | false | Very low quality but surprisingly usable. | +| [Polaris-7B-Preview-IQ2_M.gguf](https://huggingface.co/bartowski/POLARIS-Project_Polaris-7B-Preview-GGUF/blob/main/POLARIS-Project_Polaris-7B-Preview-IQ2_M.gguf) | IQ2_M | 2.78GB | 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/POLARIS-Project_Polaris-7B-Preview-GGUF --include "POLARIS-Project_Polaris-7B-Preview-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/POLARIS-Project_Polaris-7B-Preview-GGUF --include "POLARIS-Project_Polaris-7B-Preview-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (POLARIS-Project_Polaris-7B-Preview-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/ggerganov/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/ggerganov/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/ggerganov/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/ggerganov/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