commit 762412361de33dd8521866a8dc4e0389d256938b Author: ModelHub XC Date: Mon Sep 21 03:46:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/PinkPixel_Crystal-Think-V2-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/PinkPixel_Crystal-Think-V2-IQ2_M.gguf b/PinkPixel_Crystal-Think-V2-IQ2_M.gguf new file mode 100644 index 0000000..6e0caac --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0434fd5c41be6a5143af7c50170e2bf38d212f2441595f15cc6641d6f07f9e93 +size 1512980128 diff --git a/PinkPixel_Crystal-Think-V2-IQ3_M.gguf b/PinkPixel_Crystal-Think-V2-IQ3_M.gguf new file mode 100644 index 0000000..6fb1adc --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2276db7847bf8150df767634993fbea4c5ea603e84c309284af14a2479f9a74a +size 1962892448 diff --git a/PinkPixel_Crystal-Think-V2-IQ3_XS.gguf b/PinkPixel_Crystal-Think-V2-IQ3_XS.gguf new file mode 100644 index 0000000..04c30ac --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76e3bbf5687918a99025086ed6754843138ab358db1db335536deadad17664a +size 1814371488 diff --git a/PinkPixel_Crystal-Think-V2-IQ3_XXS.gguf b/PinkPixel_Crystal-Think-V2-IQ3_XXS.gguf new file mode 100644 index 0000000..65322c1 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c54a3de8e2a01b287bbebfb621fff202c61b84c532760ae53f7c043f027e86 +size 1670184608 diff --git a/PinkPixel_Crystal-Think-V2-IQ4_NL.gguf b/PinkPixel_Crystal-Think-V2-IQ4_NL.gguf new file mode 100644 index 0000000..832b624 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f895cdc438c05746d5de42c70f1ead3c67cd50d3de0eed75a7e9b598b29e05c4 +size 2381339808 diff --git a/PinkPixel_Crystal-Think-V2-IQ4_XS.gguf b/PinkPixel_Crystal-Think-V2-IQ4_XS.gguf new file mode 100644 index 0000000..cbcf27c --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a65ee904797c387b3b18059b9fb02b1e8ae6c55c597c9cbf3b607f20a000cd0 +size 2270747808 diff --git a/PinkPixel_Crystal-Think-V2-Q2_K.gguf b/PinkPixel_Crystal-Think-V2-Q2_K.gguf new file mode 100644 index 0000000..8756bc6 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb6fe4ad40be5ca55eefc05ac930990b52a12fd50733d087d1fc323ffbdf47dc +size 1669495968 diff --git a/PinkPixel_Crystal-Think-V2-Q2_K_L.gguf b/PinkPixel_Crystal-Think-V2-Q2_K_L.gguf new file mode 100644 index 0000000..aa06ce4 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18aa3b1d170d5fb7cce663f3c8c74b079a57b25f5b5d0fee49a9996a74209be +size 1763696288 diff --git a/PinkPixel_Crystal-Think-V2-Q3_K_L.gguf b/PinkPixel_Crystal-Think-V2-Q3_K_L.gguf new file mode 100644 index 0000000..dbbe4a1 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7de5e20472bb944d50eb109f7f4ab1fefa70542c1d218de4149f6e0c30634cf4 +size 2239782048 diff --git a/PinkPixel_Crystal-Think-V2-Q3_K_M.gguf b/PinkPixel_Crystal-Think-V2-Q3_K_M.gguf new file mode 100644 index 0000000..50a341d --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d112c549bc3762ddaa85956946faaddffb62718593ba653f73e07f50fc357f3b +size 2075614368 diff --git a/PinkPixel_Crystal-Think-V2-Q3_K_S.gguf b/PinkPixel_Crystal-Think-V2-Q3_K_S.gguf new file mode 100644 index 0000000..0433b92 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa81559e592ad5d38d0e3a416f6edabc17d91db06001cbf08c95971049c9c2c4 +size 1886993568 diff --git a/PinkPixel_Crystal-Think-V2-Q3_K_XL.gguf b/PinkPixel_Crystal-Think-V2-Q3_K_XL.gguf new file mode 100644 index 0000000..b1979e8 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c972e706321505ab251ad47fed3db9165367d736f3844c77f631fedb44ee7649 +size 2333982368 diff --git a/PinkPixel_Crystal-Think-V2-Q4_0.gguf b/PinkPixel_Crystal-Think-V2-Q4_0.gguf new file mode 100644 index 0000000..8b41b1d --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51ecd04a759c7cf47c49074661e383c1f1b2bc935609ef066ab22a4f2ac514ba +size 2375769248 diff --git a/PinkPixel_Crystal-Think-V2-Q4_1.gguf b/PinkPixel_Crystal-Think-V2-Q4_1.gguf new file mode 100644 index 0000000..7b3457e --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d58accd6b1f99dfe6fcf50206361a9f4d9cd43e6d0ed53e3c175b44072e95220 +size 2596625568 diff --git a/PinkPixel_Crystal-Think-V2-Q4_K_L.gguf b/PinkPixel_Crystal-Think-V2-Q4_K_L.gguf new file mode 100644 index 0000000..628e51a --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe83fc6d2b06659b655e638ca3708857c4b783514e900ecbada81c273e03d366 +size 2591477408 diff --git a/PinkPixel_Crystal-Think-V2-Q4_K_M.gguf b/PinkPixel_Crystal-Think-V2-Q4_K_M.gguf new file mode 100644 index 0000000..86b7ab0 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10f2558089c90bc9ef8036ac0b1142ad8991902ec83840a00710fd654df19aaa +size 2497277088 diff --git a/PinkPixel_Crystal-Think-V2-Q4_K_S.gguf b/PinkPixel_Crystal-Think-V2-Q4_K_S.gguf new file mode 100644 index 0000000..b459aeb --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46b4eda34adb8c4a6e3db6d5423bb6f328d84c58d5161fff48de6515eaeb8d8d +size 2383305888 diff --git a/PinkPixel_Crystal-Think-V2-Q5_K_L.gguf b/PinkPixel_Crystal-Think-V2-Q5_K_L.gguf new file mode 100644 index 0000000..8000d34 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81dadce5abe0a754b60c28972c108e3c4b3e84458e1623e4a4dfa43eaae3fc8c +size 2983710368 diff --git a/PinkPixel_Crystal-Think-V2-Q5_K_M.gguf b/PinkPixel_Crystal-Think-V2-Q5_K_M.gguf new file mode 100644 index 0000000..3a627f3 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:145c08279142afb9a27ee1f6761b4501de8a2b1f5cd4b3a4e23929254a0bc1a6 +size 2889510048 diff --git a/PinkPixel_Crystal-Think-V2-Q5_K_S.gguf b/PinkPixel_Crystal-Think-V2-Q5_K_S.gguf new file mode 100644 index 0000000..80ec086 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:824bb79950145bdb20aeab7773c74bbf21f43a1677e12fd394db1305ae81ed21 +size 2823707808 diff --git a/PinkPixel_Crystal-Think-V2-Q6_K.gguf b/PinkPixel_Crystal-Think-V2-Q6_K.gguf new file mode 100644 index 0000000..bd8d358 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:494a00d0cd8f31e5cc18f7aa1aa2e4e62c71c528fc6d1a138facf6141cb4ebf8 +size 3306257568 diff --git a/PinkPixel_Crystal-Think-V2-Q6_K_L.gguf b/PinkPixel_Crystal-Think-V2-Q6_K_L.gguf new file mode 100644 index 0000000..52d0592 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a9b22b54fbb146241e858db50c3c0adec8bbef2594bf94ac82107c5ec5724c +size 3400457888 diff --git a/PinkPixel_Crystal-Think-V2-Q8_0.gguf b/PinkPixel_Crystal-Think-V2-Q8_0.gguf new file mode 100644 index 0000000..ccf8743 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dfcd3f17609dd346654c994644a9cfda963e1793d146791a6fc9f3e3ef7dd00 +size 4280401568 diff --git a/PinkPixel_Crystal-Think-V2-bf16.gguf b/PinkPixel_Crystal-Think-V2-bf16.gguf new file mode 100644 index 0000000..66500d2 --- /dev/null +++ b/PinkPixel_Crystal-Think-V2-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98fabc7e38283a3ddf4e60b3defbf6be05d26eea87355ba4596e14769d319915 +size 8051281280 diff --git a/PinkPixel_Crystal-Think-V2.imatrix b/PinkPixel_Crystal-Think-V2.imatrix new file mode 100644 index 0000000..3fa8cfe Binary files /dev/null and b/PinkPixel_Crystal-Think-V2.imatrix differ diff --git a/README.md b/README.md new file mode 100644 index 0000000..e2fcc97 --- /dev/null +++ b/README.md @@ -0,0 +1,181 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: PinkPixel/Crystal-Think-V2 +base_model_relation: quantized +license: apache-2.0 +language: +- en +tags: +- mathematical-reasoning +- qwen3 +- lora +- grpo +- math +- reasoning +- fine-tuned +datasets: +- nvidia/OpenMathReasoning +--- + +## Llamacpp imatrix Quantizations of Crystal-Think-V2 by PinkPixel + +Using llama.cpp release b5760 for quantization. + +Original model: https://huggingface.co/PinkPixel/Crystal-Think-V2 + +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 + +No chat template specified so default is used. This may be incorrect, check original model card for details. + +``` +{system_prompt}<|endoftext|>{prompt}<|endoftext|> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Crystal-Think-V2-bf16.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-bf16.gguf) | bf16 | 8.05GB | false | Full BF16 weights. | +| [Crystal-Think-V2-Q8_0.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q8_0.gguf) | Q8_0 | 4.28GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Crystal-Think-V2-Q6_K_L.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q6_K_L.gguf) | Q6_K_L | 3.40GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Crystal-Think-V2-Q6_K.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q6_K.gguf) | Q6_K | 3.31GB | false | Very high quality, near perfect, *recommended*. | +| [Crystal-Think-V2-Q5_K_L.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q5_K_L.gguf) | Q5_K_L | 2.98GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Crystal-Think-V2-Q5_K_M.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q5_K_M.gguf) | Q5_K_M | 2.89GB | false | High quality, *recommended*. | +| [Crystal-Think-V2-Q5_K_S.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q5_K_S.gguf) | Q5_K_S | 2.82GB | false | High quality, *recommended*. | +| [Crystal-Think-V2-Q4_1.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q4_1.gguf) | Q4_1 | 2.60GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Crystal-Think-V2-Q4_K_L.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q4_K_L.gguf) | Q4_K_L | 2.59GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Crystal-Think-V2-Q4_K_M.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q4_K_M.gguf) | Q4_K_M | 2.50GB | false | Good quality, default size for most use cases, *recommended*. | +| [Crystal-Think-V2-Q4_K_S.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q4_K_S.gguf) | Q4_K_S | 2.38GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Crystal-Think-V2-Q4_0.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q4_0.gguf) | Q4_0 | 2.38GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Crystal-Think-V2-IQ4_NL.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-IQ4_NL.gguf) | IQ4_NL | 2.38GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Crystal-Think-V2-Q3_K_XL.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q3_K_XL.gguf) | Q3_K_XL | 2.33GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Crystal-Think-V2-IQ4_XS.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-IQ4_XS.gguf) | IQ4_XS | 2.27GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Crystal-Think-V2-Q3_K_L.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q3_K_L.gguf) | Q3_K_L | 2.24GB | false | Lower quality but usable, good for low RAM availability. | +| [Crystal-Think-V2-Q3_K_M.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q3_K_M.gguf) | Q3_K_M | 2.08GB | false | Low quality. | +| [Crystal-Think-V2-IQ3_M.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-IQ3_M.gguf) | IQ3_M | 1.96GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Crystal-Think-V2-Q3_K_S.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q3_K_S.gguf) | Q3_K_S | 1.89GB | false | Low quality, not recommended. | +| [Crystal-Think-V2-IQ3_XS.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-IQ3_XS.gguf) | IQ3_XS | 1.81GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Crystal-Think-V2-Q2_K_L.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q2_K_L.gguf) | Q2_K_L | 1.76GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Crystal-Think-V2-IQ3_XXS.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-IQ3_XXS.gguf) | IQ3_XXS | 1.67GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Crystal-Think-V2-Q2_K.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-Q2_K.gguf) | Q2_K | 1.67GB | false | Very low quality but surprisingly usable. | +| [Crystal-Think-V2-IQ2_M.gguf](https://huggingface.co/bartowski/PinkPixel_Crystal-Think-V2-GGUF/blob/main/PinkPixel_Crystal-Think-V2-IQ2_M.gguf) | IQ2_M | 1.51GB | 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/PinkPixel_Crystal-Think-V2-GGUF --include "PinkPixel_Crystal-Think-V2-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/PinkPixel_Crystal-Think-V2-GGUF --include "PinkPixel_Crystal-Think-V2-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (PinkPixel_Crystal-Think-V2-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