commit e7fdf74e7c229ceafaa12c137c61371f6bfedd8d Author: ModelHub XC Date: Sun May 10 01:15:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f485184 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Bellatrix-Tiny-0.5B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bellatrix-Tiny-0.5B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bellatrix-Tiny-0.5B.i1-IQ1_M.gguf b/Bellatrix-Tiny-0.5B.i1-IQ1_M.gguf new file mode 100644 index 0000000..98cc162 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:651af75f8fbcb9bb1289e553cb5c004b2817c165ca8fb9e3f662451549fcbf05 +size 317974944 diff --git a/Bellatrix-Tiny-0.5B.i1-IQ1_S.gguf b/Bellatrix-Tiny-0.5B.i1-IQ1_S.gguf new file mode 100644 index 0000000..cd1e1d0 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cda3c4ac4302800ddedbd9cdfef481924f978470418488b1f21a396c52c324d1 +size 315829920 diff --git a/Bellatrix-Tiny-0.5B.i1-IQ2_M.gguf b/Bellatrix-Tiny-0.5B.i1-IQ2_M.gguf new file mode 100644 index 0000000..c75a4ae --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efad9b1bba44af47c63630ddc33bf1cc3fc18cf830180e4234859dd08428c4e1 +size 328597920 diff --git a/Bellatrix-Tiny-0.5B.i1-IQ2_S.gguf b/Bellatrix-Tiny-0.5B.i1-IQ2_S.gguf new file mode 100644 index 0000000..18d2070 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a52dca35261bfb5a0c4cf0f16a7b79669ea75ff64b1340a5abd25005b8de6df +size 325737888 diff --git a/Bellatrix-Tiny-0.5B.i1-IQ2_XS.gguf b/Bellatrix-Tiny-0.5B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..196aa2b --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93dfa179d084abc2cd1823c93ae75dd7f41ba3afbf998d2575d8e469cfad659a +size 324410016 diff --git a/Bellatrix-Tiny-0.5B.i1-IQ2_XXS.gguf b/Bellatrix-Tiny-0.5B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..223e891 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:609c3a9096e8935b1d33475a3ca1cdc8ab17c7be894ea77f99f29966e2a3a389 +size 321549984 diff --git a/Bellatrix-Tiny-0.5B.i1-IQ3_M.gguf b/Bellatrix-Tiny-0.5B.i1-IQ3_M.gguf new file mode 100644 index 0000000..c829256 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc8374a9f426c9da230b7cbf6718c6a03bbce3cf6dfcac1e2a2f07d145777cc +size 342752928 diff --git a/Bellatrix-Tiny-0.5B.i1-IQ3_S.gguf b/Bellatrix-Tiny-0.5B.i1-IQ3_S.gguf new file mode 100644 index 0000000..e7bfffb --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264cb4e6ad574048c13f576d64c01462a0f1fa2235b4ad5d083bc7cf616b0b92 +size 338608032 diff --git a/Bellatrix-Tiny-0.5B.i1-IQ3_XS.gguf b/Bellatrix-Tiny-0.5B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..308220b --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec41dfe40960e5c0663e83d76e02f58c46dc6a9409ce09074a55be0aef082fa6 +size 338608032 diff --git a/Bellatrix-Tiny-0.5B.i1-IQ3_XXS.gguf b/Bellatrix-Tiny-0.5B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..31a8e66 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc5c2539f443bbef8fda9bac6162971e75276336f5f22f5496f8dcea576aad48 +size 333705120 diff --git a/Bellatrix-Tiny-0.5B.i1-IQ4_NL.gguf b/Bellatrix-Tiny-0.5B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..8708c2d --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fcddfbd16a8988bf81d84af14651a93b89182214085a3099b6957ab5b2db5ba +size 352671648 diff --git a/Bellatrix-Tiny-0.5B.i1-IQ4_XS.gguf b/Bellatrix-Tiny-0.5B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..87c1d9b --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee6039c932ba11f5ccb9be3065d8d554cd5f81513fb75eb6d98b1e41693eda4a +size 349403040 diff --git a/Bellatrix-Tiny-0.5B.i1-Q2_K.gguf b/Bellatrix-Tiny-0.5B.i1-Q2_K.gguf new file mode 100644 index 0000000..33a9255 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6047732fb46af404e3b48e3332dfe95a5f4df32a858b6b965ddb7c8c2c02e9ea +size 338608032 diff --git a/Bellatrix-Tiny-0.5B.i1-Q2_K_S.gguf b/Bellatrix-Tiny-0.5B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..a18284a --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a65f481dd678b9865936b6264f1e39808151f10138994d70f03ee59fee2540e6 +size 331049376 diff --git a/Bellatrix-Tiny-0.5B.i1-Q3_K_L.gguf b/Bellatrix-Tiny-0.5B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..200f336 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4afcf2d6faf1f7168bc3e46e3860d176484f99e4a9f80feee94d2025c15d93a5 +size 369358752 diff --git a/Bellatrix-Tiny-0.5B.i1-Q3_K_M.gguf b/Bellatrix-Tiny-0.5B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..7aeca84 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65df67b982cc3bd044d223c1774417addb033c953f376047ff418453950d717b +size 355467168 diff --git a/Bellatrix-Tiny-0.5B.i1-Q3_K_S.gguf b/Bellatrix-Tiny-0.5B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..41b6d58 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d524e43b5927c8d1a9f87eab07dc9b7d653ac49c9f8b58dc244a6912016bfcc +size 338263968 diff --git a/Bellatrix-Tiny-0.5B.i1-Q4_0.gguf b/Bellatrix-Tiny-0.5B.i1-Q4_0.gguf new file mode 100644 index 0000000..402d5e7 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b19f8d6bbaeed18eeb5b038132ff7728c9d1e4c26a0b24b7461168dc7ea48a3 +size 352972704 diff --git a/Bellatrix-Tiny-0.5B.i1-Q4_1.gguf b/Bellatrix-Tiny-0.5B.i1-Q4_1.gguf new file mode 100644 index 0000000..8502088 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb7887df238ed7b3f85f0dbb156cfa6d1a95dac953376c51f248e7f9cdd447d3 +size 374519712 diff --git a/Bellatrix-Tiny-0.5B.i1-Q4_K_M.gguf b/Bellatrix-Tiny-0.5B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..699e053 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:808e7b94d51e54126f4a6be13be709b7a4688528973907f5eb34db36957f9bf6 +size 397808544 diff --git a/Bellatrix-Tiny-0.5B.i1-Q4_K_S.gguf b/Bellatrix-Tiny-0.5B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0a06803 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8a324429efe1e49ee99fba45cf8220f75c0c47b8d6b2b77230c5ef96a672aaf +size 385472416 diff --git a/Bellatrix-Tiny-0.5B.i1-Q5_K_M.gguf b/Bellatrix-Tiny-0.5B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c72f813 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9fb2f8ae949213be4a168685592d68d6373540292d1a13de0f8c0829118ae8 +size 420086688 diff --git a/Bellatrix-Tiny-0.5B.i1-Q5_K_S.gguf b/Bellatrix-Tiny-0.5B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..c221532 --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b5630b932bcab231b7824894cc99cf5d5e1f1475db5bc693446eee7f8594786 +size 412710816 diff --git a/Bellatrix-Tiny-0.5B.i1-Q6_K.gguf b/Bellatrix-Tiny-0.5B.i1-Q6_K.gguf new file mode 100644 index 0000000..73221fb --- /dev/null +++ b/Bellatrix-Tiny-0.5B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd97898cb67511b450fcd182420462775732d9054babd61722b51355edc24d1 +size 505737120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d8bd9d2 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: prithivMLmods/Bellatrix-Tiny-0.5B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- reasoner +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Bellatrix-Tiny-0.5B + + +static quants are available at https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-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-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Bellatrix-Tiny-0.5B-i1-GGUF/resolve/main/Bellatrix-Tiny-0.5B.i1-Q6_K.gguf) | i1-Q6_K | 0.6 | 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..d6d47f9 Binary files /dev/null and b/imatrix.dat differ