commit f6efed65b742991397a27ca609eba6ef405fe36a Author: ModelHub XC Date: Tue Sep 1 00:27:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/LatitudeGames_Wayfarer-2-12B-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/LatitudeGames_Wayfarer-2-12B-IQ2_M.gguf b/LatitudeGames_Wayfarer-2-12B-IQ2_M.gguf new file mode 100644 index 0000000..db56644 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33ecfe79d1ff7b7ddf2daadab59290f526bcfadb43fea1f22cb90e3dda3f654b +size 4435034880 diff --git a/LatitudeGames_Wayfarer-2-12B-IQ2_S.gguf b/LatitudeGames_Wayfarer-2-12B-IQ2_S.gguf new file mode 100644 index 0000000..76c8058 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ad663871f2363316610587b4cd9264f4747a6e1fdaea95d86dde51a8ec19a84 +size 4138484480 diff --git a/LatitudeGames_Wayfarer-2-12B-IQ3_M.gguf b/LatitudeGames_Wayfarer-2-12B-IQ3_M.gguf new file mode 100644 index 0000000..e071629 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3eb044a0063fec6f07ec44736e293abe51aea6bf042fe5bf1170ea11307584 +size 5722245216 diff --git a/LatitudeGames_Wayfarer-2-12B-IQ3_XS.gguf b/LatitudeGames_Wayfarer-2-12B-IQ3_XS.gguf new file mode 100644 index 0000000..1b4e9b0 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c10f45b3737bf9fa400e0c8bb4343446135a532fe5493e087e901f93533e2822 +size 5306501216 diff --git a/LatitudeGames_Wayfarer-2-12B-IQ3_XXS.gguf b/LatitudeGames_Wayfarer-2-12B-IQ3_XXS.gguf new file mode 100644 index 0000000..051cede --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51c0daaf8ed77e90d32fe4418dca6881e61c8d1f12b403f8fe13ac0500fee043 +size 4945396480 diff --git a/LatitudeGames_Wayfarer-2-12B-IQ4_NL.gguf b/LatitudeGames_Wayfarer-2-12B-IQ4_NL.gguf new file mode 100644 index 0000000..d962f07 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dc3a8335ec467544710c92c08b6db095498ae7858b2344ff128a7f6d5df3800 +size 7097929120 diff --git a/LatitudeGames_Wayfarer-2-12B-IQ4_XS.gguf b/LatitudeGames_Wayfarer-2-12B-IQ4_XS.gguf new file mode 100644 index 0000000..5d9ec89 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2227af939b938774b267e9677c898a60c33224e7ba6f85236dc386878c9e548b +size 6742723680 diff --git a/LatitudeGames_Wayfarer-2-12B-Q2_K.gguf b/LatitudeGames_Wayfarer-2-12B-Q2_K.gguf new file mode 100644 index 0000000..388322f --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:754986145abfc465e7ce60e714868110c0a04e52a0a165b1bd2da684cf7e15b6 +size 4791059520 diff --git a/LatitudeGames_Wayfarer-2-12B-Q2_K_L.gguf b/LatitudeGames_Wayfarer-2-12B-Q2_K_L.gguf new file mode 100644 index 0000000..ace42c7 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1bfaaac890332d75bf5327499fc8412d2e1fe5cda48e2d9448d5e4ee01d8e4b +size 5446429504 diff --git a/LatitudeGames_Wayfarer-2-12B-Q3_K_L.gguf b/LatitudeGames_Wayfarer-2-12B-Q3_K_L.gguf new file mode 100644 index 0000000..68fcef8 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf06d4255999f647dfd8d18e6aa2fbeda6008572d1b798d861b205539e99d66 +size 6561515616 diff --git a/LatitudeGames_Wayfarer-2-12B-Q3_K_M.gguf b/LatitudeGames_Wayfarer-2-12B-Q3_K_M.gguf new file mode 100644 index 0000000..a676d78 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36120023054d24b7359c8a23d89f3b39ef76fc49e4c7d26d72873d6ea4cfc03c +size 6083102816 diff --git a/LatitudeGames_Wayfarer-2-12B-Q3_K_S.gguf b/LatitudeGames_Wayfarer-2-12B-Q3_K_S.gguf new file mode 100644 index 0000000..e0e87a1 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff81184de108a9360106729baefccc2ed34aa2cde6c309c50b044b6d8dff6a71 +size 5534238816 diff --git a/LatitudeGames_Wayfarer-2-12B-Q3_K_XL.gguf b/LatitudeGames_Wayfarer-2-12B-Q3_K_XL.gguf new file mode 100644 index 0000000..5355167 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25c641b07116a2a78147bc725f0e0cf25a7b02be23049462882251c3d119e3ef +size 7148727104 diff --git a/LatitudeGames_Wayfarer-2-12B-Q4_0.gguf b/LatitudeGames_Wayfarer-2-12B-Q4_0.gguf new file mode 100644 index 0000000..c659c3a --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476af84bfc44590eade999eb3658323aea2658930156f63e489f15e18e629311 +size 7094652320 diff --git a/LatitudeGames_Wayfarer-2-12B-Q4_1.gguf b/LatitudeGames_Wayfarer-2-12B-Q4_1.gguf new file mode 100644 index 0000000..8d476df --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ecf314222b6caf98f2c3de72acf34e5615beb92df61e19d195a375bfd4d4fee +size 7795232800 diff --git a/LatitudeGames_Wayfarer-2-12B-Q4_K_L.gguf b/LatitudeGames_Wayfarer-2-12B-Q4_K_L.gguf new file mode 100644 index 0000000..a911dee --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b3118aa5a97e6b40a35336f264cf29d846b310d7c5886515727f3b3bab79ed1 +size 7975299904 diff --git a/LatitudeGames_Wayfarer-2-12B-Q4_K_M.gguf b/LatitudeGames_Wayfarer-2-12B-Q4_K_M.gguf new file mode 100644 index 0000000..3fbb692 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddec1e6fa3b98afcbd44caa479f1a2afb26bee88381f89b5b4b8e7ed6f60db03 +size 7477218720 diff --git a/LatitudeGames_Wayfarer-2-12B-Q4_K_S.gguf b/LatitudeGames_Wayfarer-2-12B-Q4_K_S.gguf new file mode 100644 index 0000000..2903a21 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee17a706748fd108f3abad9abb37ff361e46aef6fac0f098467f70ea5a17aec4 +size 7120211360 diff --git a/LatitudeGames_Wayfarer-2-12B-Q5_K_L.gguf b/LatitudeGames_Wayfarer-2-12B-Q5_K_L.gguf new file mode 100644 index 0000000..7322ff0 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04dbe2b515bae44d91d39af8eadc796d5d07e4b3638c76ec015a3fd56136394 +size 9141840704 diff --git a/LatitudeGames_Wayfarer-2-12B-Q5_K_M.gguf b/LatitudeGames_Wayfarer-2-12B-Q5_K_M.gguf new file mode 100644 index 0000000..d8fea94 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:689ce5f5e2f0449e68441614b64da0c7bbe19c9c4cb26c0927765a27766df03c +size 8727646880 diff --git a/LatitudeGames_Wayfarer-2-12B-Q5_K_S.gguf b/LatitudeGames_Wayfarer-2-12B-Q5_K_S.gguf new file mode 100644 index 0000000..e598e39 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:116ee968ede409e396d2f71ef7f8bc5ee295b143fcfe630bfc7c6bf3ff51b0ec +size 8518750880 diff --git a/LatitudeGames_Wayfarer-2-12B-Q6_K.gguf b/LatitudeGames_Wayfarer-2-12B-Q6_K.gguf new file mode 100644 index 0000000..fda5be4 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ee848f02081301051461c9d79ed240c02808a19ce12beea46bf1fe733ad5ac +size 10056226816 diff --git a/LatitudeGames_Wayfarer-2-12B-Q6_K_L.gguf b/LatitudeGames_Wayfarer-2-12B-Q6_K_L.gguf new file mode 100644 index 0000000..02a250c --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc1adc53bc66f223ad5f65a737316fbd3c87b48874fb693af8c0233940af590e +size 10381290304 diff --git a/LatitudeGames_Wayfarer-2-12B-Q8_0.gguf b/LatitudeGames_Wayfarer-2-12B-Q8_0.gguf new file mode 100644 index 0000000..f93d929 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ae9b1c4090fa8d1be79f6867fc533cdf372425be714d2c38208500fc1b6abcf +size 13022391104 diff --git a/LatitudeGames_Wayfarer-2-12B-bf16.gguf b/LatitudeGames_Wayfarer-2-12B-bf16.gguf new file mode 100644 index 0000000..1bc85bf --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08cec90d4390ed6de924da186b119d04dd9f30a6115f76683a3d82eb94324138 +size 24504317216 diff --git a/LatitudeGames_Wayfarer-2-12B-imatrix.gguf b/LatitudeGames_Wayfarer-2-12B-imatrix.gguf new file mode 100644 index 0000000..4053fb1 --- /dev/null +++ b/LatitudeGames_Wayfarer-2-12B-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:598b0345a934aed4ff2a6965393749c78417c2b8af87b18c1af71f1ec352492f +size 7088224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cebf631 --- /dev/null +++ b/README.md @@ -0,0 +1,165 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: LatitudeGames/Wayfarer-2-12B +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of Wayfarer-2-12B by LatitudeGames + +Using llama.cpp release b6317 for quantization. + +Original model: https://huggingface.co/LatitudeGames/Wayfarer-2-12B + +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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [Wayfarer-2-12B-bf16.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-bf16.gguf) | bf16 | 24.50GB | false | Full BF16 weights. | +| [Wayfarer-2-12B-Q8_0.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q8_0.gguf) | Q8_0 | 13.02GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Wayfarer-2-12B-Q6_K_L.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q6_K_L.gguf) | Q6_K_L | 10.38GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Wayfarer-2-12B-Q6_K.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q6_K.gguf) | Q6_K | 10.06GB | false | Very high quality, near perfect, *recommended*. | +| [Wayfarer-2-12B-Q5_K_L.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q5_K_L.gguf) | Q5_K_L | 9.14GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Wayfarer-2-12B-Q5_K_M.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q5_K_M.gguf) | Q5_K_M | 8.73GB | false | High quality, *recommended*. | +| [Wayfarer-2-12B-Q5_K_S.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q5_K_S.gguf) | Q5_K_S | 8.52GB | false | High quality, *recommended*. | +| [Wayfarer-2-12B-Q4_K_L.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q4_K_L.gguf) | Q4_K_L | 7.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Wayfarer-2-12B-Q4_1.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q4_1.gguf) | Q4_1 | 7.80GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Wayfarer-2-12B-Q4_K_M.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q4_K_M.gguf) | Q4_K_M | 7.48GB | false | Good quality, default size for most use cases, *recommended*. | +| [Wayfarer-2-12B-Q3_K_XL.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q3_K_XL.gguf) | Q3_K_XL | 7.15GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Wayfarer-2-12B-Q4_K_S.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q4_K_S.gguf) | Q4_K_S | 7.12GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Wayfarer-2-12B-IQ4_NL.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ4_NL.gguf) | IQ4_NL | 7.10GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Wayfarer-2-12B-Q4_0.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q4_0.gguf) | Q4_0 | 7.09GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Wayfarer-2-12B-IQ4_XS.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ4_XS.gguf) | IQ4_XS | 6.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Wayfarer-2-12B-Q3_K_L.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q3_K_L.gguf) | Q3_K_L | 6.56GB | false | Lower quality but usable, good for low RAM availability. | +| [Wayfarer-2-12B-Q3_K_M.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q3_K_M.gguf) | Q3_K_M | 6.08GB | false | Low quality. | +| [Wayfarer-2-12B-IQ3_M.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ3_M.gguf) | IQ3_M | 5.72GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Wayfarer-2-12B-Q3_K_S.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q3_K_S.gguf) | Q3_K_S | 5.53GB | false | Low quality, not recommended. | +| [Wayfarer-2-12B-Q2_K_L.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q2_K_L.gguf) | Q2_K_L | 5.45GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Wayfarer-2-12B-IQ3_XS.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ3_XS.gguf) | IQ3_XS | 5.31GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Wayfarer-2-12B-IQ3_XXS.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ3_XXS.gguf) | IQ3_XXS | 4.95GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Wayfarer-2-12B-Q2_K.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-Q2_K.gguf) | Q2_K | 4.79GB | false | Very low quality but surprisingly usable. | +| [Wayfarer-2-12B-IQ2_M.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ2_M.gguf) | IQ2_M | 4.44GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Wayfarer-2-12B-IQ2_S.gguf](https://huggingface.co/bartowski/LatitudeGames_Wayfarer-2-12B-GGUF/blob/main/LatitudeGames_Wayfarer-2-12B-IQ2_S.gguf) | IQ2_S | 4.14GB | false | Low quality, uses SOTA techniques to be 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/LatitudeGames_Wayfarer-2-12B-GGUF --include "LatitudeGames_Wayfarer-2-12B-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/LatitudeGames_Wayfarer-2-12B-GGUF --include "LatitudeGames_Wayfarer-2-12B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (LatitudeGames_Wayfarer-2-12B-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