commit a9559492eb09ad821cf5393e68eab1fca48fb7d0 Author: ModelHub XC Date: Fri Jun 5 03:54:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fc9460a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-1B-v2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ1_M.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ1_M.gguf new file mode 100644 index 0000000..bb40fa2 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f03fa715ffc300815c625975d380cb75d1f926016196c98e9e7e77c9250e53a6 +size 413608320 diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ1_S.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ1_S.gguf new file mode 100644 index 0000000..647f56a --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:596a268b68e84a23b9621d100a630bb0f0ebfa2d087f79325651293d1edd4e4c +size 393554304 diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ2_M.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ2_M.gguf new file mode 100644 index 0000000..db885c3 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60eabc610910656557346366a4438894df8f466f2885065579015eab1dd67e8 +size 515451264 diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ2_S.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ2_S.gguf new file mode 100644 index 0000000..c5bc903 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8644d696aff50c37bd8d692ea476b5e3e3257e4a1dc09c8088a05eee3f62739c +size 488712576 diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ2_XS.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a234838 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8817b6660ca49853f9875127860a66d4a8905d2ae52db0418b10b4354b7abb9 +size 475867520 diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ2_XXS.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..0ebb7ef --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6909f2d8a08f03e6f4229871cc0c348d380ca9268252f12a095f87be7de3024c +size 447031680 diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ3_M.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ3_M.gguf new file mode 100644 index 0000000..3f1d4bc --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee10bf85c1b066e29405260377cf31c385905ea652cabec7d8f683327f22c8e7 +size 657291648 diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ3_S.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ3_S.gguf new file mode 100644 index 0000000..5426e79 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fea23637b4bc42ff445210168d0c37fb314d577e2c28d9c2f8ae53467e33fd53 +size 643922304 diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ3_XS.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e23cb41 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d37a9bc17ad01f8fc98fd5b96f136ce11c4125d6b643e866045b5d31ce125b9 +size 621115776 diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ3_XXS.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3abd562 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dc0fa5671b784a46e984e5604035f1ee3119d89fccf3c66a27510bb5e4885f6 +size 562112896 diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ4_NL.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ4_NL.gguf new file mode 100644 index 0000000..7e11694 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a0370c952af2b2b7227731b4ebf5588a5f854502adcd30d68c56017719b934a +size 773028224 diff --git a/Bellatrix-Tiny-1B-v2.i1-IQ4_XS.gguf b/Bellatrix-Tiny-1B-v2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9d20ced --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa8bc0c5fa5756da4515f886ba69fd9d5cdfa64a05479c4249da5e3be33051f8 +size 743143808 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q2_K.gguf b/Bellatrix-Tiny-1B-v2.i1-Q2_K.gguf new file mode 100644 index 0000000..e5565f3 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc668ef94fb781eb0f9757886b174d52e9b7b71691e9370aa889192173011ed +size 580876672 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q2_K_S.gguf b/Bellatrix-Tiny-1B-v2.i1-Q2_K_S.gguf new file mode 100644 index 0000000..11075dc --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a246eb0c02a0c38a669a6c413d1bfa2366d206902d15e03ba1ded6d499249e +size 554662272 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q3_K_L.gguf b/Bellatrix-Tiny-1B-v2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..a7e9661 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09b08d755a3ac030a00a0b47febc5f67344ebbb53d94b2580a846e6bc3139b16 +size 732526976 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q3_K_M.gguf b/Bellatrix-Tiny-1B-v2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..5d810d1 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bbb8a535b3bc26e287249e7376b93a57829aabeef67d4c6696f05c03bd2aca3 +size 690846080 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q3_K_S.gguf b/Bellatrix-Tiny-1B-v2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..9e68a36 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb79428c673ffa730b90faed8d3a80322dbb7b2701cbdc78b4f147cf53980f47 +size 641694080 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q4_0.gguf b/Bellatrix-Tiny-1B-v2.i1-Q4_0.gguf new file mode 100644 index 0000000..bc877c5 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b032ea49284a623e96d44c0b2c277a93453ae8a6d4058588e2b94b407eee716 +size 773028224 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q4_1.gguf b/Bellatrix-Tiny-1B-v2.i1-Q4_1.gguf new file mode 100644 index 0000000..c563438 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:188d6ab5f72e1ee0f0f8e8d377857ea8bef73675e9b7d3ffd8fa17717162fd67 +size 831748480 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q4_K_M.gguf b/Bellatrix-Tiny-1B-v2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..42dc262 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43720e8416cd3308c7d734279544cf76e3aaeff6528d9a4fd9a40a0cb9e256aa +size 807696768 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q4_K_S.gguf b/Bellatrix-Tiny-1B-v2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..99d34b3 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce14b1143ce8ed923a410b59425aa9b39faccc5f97792e5ffe3b315ba72dc5c +size 775649664 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q5_K_M.gguf b/Bellatrix-Tiny-1B-v2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a1dc92a --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dcbb0aa9c7868e67e41ca156244d473358881fa43de6d7785c19fd521b4d401 +size 911505792 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q5_K_S.gguf b/Bellatrix-Tiny-1B-v2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8123c56 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bed3b52cd94cb70f8e7a6aa9f22ea75db1a40e15137b04930a7200fb0bf7c1ec +size 892565888 diff --git a/Bellatrix-Tiny-1B-v2.i1-Q6_K.gguf b/Bellatrix-Tiny-1B-v2.i1-Q6_K.gguf new file mode 100644 index 0000000..937f1d7 --- /dev/null +++ b/Bellatrix-Tiny-1B-v2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce2d2fd8045f1dc734e35f53dd74768d41994d81ee195d8e21231ec1e6dc17e +size 1021802880 diff --git a/README.md b/README.md new file mode 100644 index 0000000..66dd827 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: prithivMLmods/Bellatrix-Tiny-1B-v2 +datasets: +- Magpie-Align/Magpie-Reasoning-V2-250K-CoT-QwQ +- ngxson/MiniThinky-dataset +- prithivMLmods/Deepthink-Reasoning +- Magpie-Align/Magpie-Reasoning-V1-150K-CoT-QwQ +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +tags: +- reason +- tiny +- llama3.2 +- cot +- bellatrix +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Bellatrix-Tiny-1B-v2 + + +static quants are available at https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ1_M.gguf) | i1-IQ1_M | 0.5 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ2_S.gguf) | i1-IQ2_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q2_K.gguf) | i1-Q2_K | 0.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ3_S.gguf) | i1-IQ3_S | 0.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q4_0.gguf) | i1-Q4_0 | 0.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q4_1.gguf) | i1-Q4_1 | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-1B-v2-i1-GGUF/resolve/main/Bellatrix-Tiny-1B-v2.i1-Q6_K.gguf) | i1-Q6_K | 1.1 | practically like static Q6_K | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..00d1e64 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aad4e44f0629d6a5d0915a13fa65036e26957edc65fe7db5f7cb2dbb2eb69a3a +size 1314413