commit 6acfd19ec46f011f3fa3cecf4bbebc4aa4df7c50 Author: ModelHub XC Date: Fri Jun 26 14:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CaptainNemo-ChatML-12B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2586b3a --- /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 +CaptainNemo-ChatML-12B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +CaptainNemo-ChatML-12B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CaptainNemo-ChatML-12B.i1-IQ1_M.gguf b/CaptainNemo-ChatML-12B.i1-IQ1_M.gguf new file mode 100644 index 0000000..62067a5 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:198e9dc37a98082b12edbc50ce929a85113a9dbfadff8a3284a7f4436860bada +size 3221626176 diff --git a/CaptainNemo-ChatML-12B.i1-IQ1_S.gguf b/CaptainNemo-ChatML-12B.i1-IQ1_S.gguf new file mode 100644 index 0000000..e6aad1d --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19053617d750a78702029898746610a9d0b41347c9222da59d20a13e8b4191a8 +size 2999213376 diff --git a/CaptainNemo-ChatML-12B.i1-IQ2_M.gguf b/CaptainNemo-ChatML-12B.i1-IQ2_M.gguf new file mode 100644 index 0000000..123a2d4 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8dcbbd82bf90b86a265e1413cc7eb49b588aaaa325e82665c67a6d8b82995dc +size 4435025216 diff --git a/CaptainNemo-ChatML-12B.i1-IQ2_S.gguf b/CaptainNemo-ChatML-12B.i1-IQ2_S.gguf new file mode 100644 index 0000000..de36696 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:274a5a9c45920b6d0c5b16d777a351d8223a1d94d51767b0686bf89b646fd6a9 +size 4138474816 diff --git a/CaptainNemo-ChatML-12B.i1-IQ2_XS.gguf b/CaptainNemo-ChatML-12B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..8ba239d --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80a8fc03c11cb6f903844f790b76fcf59fea339df809c389844711c8d0a36c2e +size 3915078976 diff --git a/CaptainNemo-ChatML-12B.i1-IQ2_XXS.gguf b/CaptainNemo-ChatML-12B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8d364ee --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64f38c6c46e4f2279b468c9849ee54cd6ad5bf22ad2243db548e542fa750b4f1 +size 3592314176 diff --git a/CaptainNemo-ChatML-12B.i1-IQ3_M.gguf b/CaptainNemo-ChatML-12B.i1-IQ3_M.gguf new file mode 100644 index 0000000..5cc5f67 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea841696e62723ae713ad7b97682387f03b66bcd5e44c4ff1c1f328e92b0fb0c +size 5722234176 diff --git a/CaptainNemo-ChatML-12B.i1-IQ3_S.gguf b/CaptainNemo-ChatML-12B.i1-IQ3_S.gguf new file mode 100644 index 0000000..3b46397 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:359d7d11d43807be7298b34a6b38a037232a92909ced9e9f16924865d15f8b1d +size 5562080576 diff --git a/CaptainNemo-ChatML-12B.i1-IQ3_XS.gguf b/CaptainNemo-ChatML-12B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8ec38cc --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20138231e7597db2768f3f8f41911e295096fc605016f837a641cd4fd32b46a8 +size 5306490176 diff --git a/CaptainNemo-ChatML-12B.i1-IQ3_XXS.gguf b/CaptainNemo-ChatML-12B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..281afea --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fefe21bb710973e1274403b3f1af4842cd28f11a84184a806bd505e1f067269 +size 4945386816 diff --git a/CaptainNemo-ChatML-12B.i1-IQ4_NL.gguf b/CaptainNemo-ChatML-12B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..3d57088 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4420812e0956b62ef3b5823960cfaa452bd872828acfe435ff6f7473b987536 +size 7097916736 diff --git a/CaptainNemo-ChatML-12B.i1-IQ4_XS.gguf b/CaptainNemo-ChatML-12B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6e2ac9b --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f78e035687c6e89c2d0541ca7ccabe719f0ee87f25a145edf45fbc2e93fc81e1 +size 6742711616 diff --git a/CaptainNemo-ChatML-12B.i1-Q2_K.gguf b/CaptainNemo-ChatML-12B.i1-Q2_K.gguf new file mode 100644 index 0000000..a358058 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b0f6f74e9fcafb864c14f04a43d0cc17fabeef42797e5a20b798f840656ef1 +size 4791049536 diff --git a/CaptainNemo-ChatML-12B.i1-Q2_K_S.gguf b/CaptainNemo-ChatML-12B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..48c7259 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1eddf4053d3ce8cfa83ac3ca8d53a582022228089e7a0c0384db607d2fcf2d +size 4493679936 diff --git a/CaptainNemo-ChatML-12B.i1-Q3_K_L.gguf b/CaptainNemo-ChatML-12B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..52f3c5f --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:032e70627a381c4014c4fffeab0ceadd1086f8af6e502a18888cdf36a0882607 +size 6561504576 diff --git a/CaptainNemo-ChatML-12B.i1-Q3_K_M.gguf b/CaptainNemo-ChatML-12B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..bd3f618 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4dabacdcd6f5ae324c272bed43a06f81fe50abb37d70ced2194ce4ce4898e7 +size 6083091776 diff --git a/CaptainNemo-ChatML-12B.i1-Q3_K_S.gguf b/CaptainNemo-ChatML-12B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..916ba8e --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e903e1a5ffbafdc846513a063a9b66fb6c7787ba3589ba804ecda9fbefb5ead +size 5534227776 diff --git a/CaptainNemo-ChatML-12B.i1-Q4_0.gguf b/CaptainNemo-ChatML-12B.i1-Q4_0.gguf new file mode 100644 index 0000000..1228267 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e268f00e94756a4557c98efd02fc7abb856a9c5c3cbd147b00f6720bc354722 +size 7094639936 diff --git a/CaptainNemo-ChatML-12B.i1-Q4_1.gguf b/CaptainNemo-ChatML-12B.i1-Q4_1.gguf new file mode 100644 index 0000000..3868ce7 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:593d752ee19f42da19de8cf4837a5e1cf6b50cd7331579d9807ae966f714f201 +size 7795219776 diff --git a/CaptainNemo-ChatML-12B.i1-Q4_K_M.gguf b/CaptainNemo-ChatML-12B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..3cf5300 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28963f9a03316315f95a9c4280281f83aa0a6e405ae73c0679b21a4874a087e +size 7477206336 diff --git a/CaptainNemo-ChatML-12B.i1-Q4_K_S.gguf b/CaptainNemo-ChatML-12B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..627cb0f --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0becbedb50b0400f588ea94e112cb4efb88eea5032b2d32501d3edc4ab232de5 +size 7120198976 diff --git a/CaptainNemo-ChatML-12B.i1-Q5_K_M.gguf b/CaptainNemo-ChatML-12B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..0786c49 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:914c64fd5f2418d25d07aaacaf64147f1eabe6e5fd2a1a7b2818d93c79407d96 +size 8727633216 diff --git a/CaptainNemo-ChatML-12B.i1-Q5_K_S.gguf b/CaptainNemo-ChatML-12B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..f1bd736 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c36c1adc6a761b4684edf93266f245337c1c92e23b708d364cca98f3d948b202 +size 8518737216 diff --git a/CaptainNemo-ChatML-12B.i1-Q6_K.gguf b/CaptainNemo-ChatML-12B.i1-Q6_K.gguf new file mode 100644 index 0000000..b8f8ec8 --- /dev/null +++ b/CaptainNemo-ChatML-12B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cca0ff3d79e7005eb4b9cbb7df88698d34f01718594892e1867226658999fcf +size 10056211776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1294b08 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: nbeerbower/CaptainNemo-ChatML-12B +datasets: +- Atsunori/HelpSteer2-DPO +- nbeerbower/Schule-DPO +- nbeerbower/Purpura-DPO +- nbeerbower/Arkhaios-DPO +- jondurbin/truthy-dpo-v0.1 +- antiven0m/physical-reasoning-dpo +- flammenai/Date-DPO-NoAsterisks +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/nbeerbower/CaptainNemo-ChatML-12B + + +static quants are available at https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-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/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q4_1.gguf) | i1-Q4_1 | 7.9 | | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/CaptainNemo-ChatML-12B-i1-GGUF/resolve/main/CaptainNemo-ChatML-12B.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | 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. + +