commit d55c3e5740b13c69870900d4904d80630867559d Author: ModelHub XC Date: Fri May 22 16:36:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Megatron-Opus-14B-2.0-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8d7ed4e --- /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 +Megatron-Opus-14B-2.0.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Megatron-Opus-14B-2.0.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Megatron-Opus-14B-2.0.i1-IQ1_M.gguf b/Megatron-Opus-14B-2.0.i1-IQ1_M.gguf new file mode 100644 index 0000000..94e2a77 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e178e31c59cdbb8737130cff56940f1be8788320940e5bf56409dbbe6a3236 +size 3690188992 diff --git a/Megatron-Opus-14B-2.0.i1-IQ1_S.gguf b/Megatron-Opus-14B-2.0.i1-IQ1_S.gguf new file mode 100644 index 0000000..b6cf360 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8275f05dbcc1d2408776bc51ff9c925f0501993853ef3957d8dc6000c36e7dc0 +size 3412172992 diff --git a/Megatron-Opus-14B-2.0.i1-IQ2_M.gguf b/Megatron-Opus-14B-2.0.i1-IQ2_M.gguf new file mode 100644 index 0000000..a733ecd --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77bd90a2e5b0556aa091e1e159703ccc79f402ffd21e20b845cb17421c682a50 +size 5173924032 diff --git a/Megatron-Opus-14B-2.0.i1-IQ2_S.gguf b/Megatron-Opus-14B-2.0.i1-IQ2_S.gguf new file mode 100644 index 0000000..4764e4f --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47f631effa3232b44c91c62a37dabfdf21db0302d88c4496ef32515ddd31ca7c +size 4803236032 diff --git a/Megatron-Opus-14B-2.0.i1-IQ2_XS.gguf b/Megatron-Opus-14B-2.0.i1-IQ2_XS.gguf new file mode 100644 index 0000000..f4af087 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27374f284bef1b4ca9bf3ac139fc31b5f0c40d9ca2e623ded92e2f2c6c03ab58 +size 4557004992 diff --git a/Megatron-Opus-14B-2.0.i1-IQ2_XXS.gguf b/Megatron-Opus-14B-2.0.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c335391 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a9a778ac63c593f47acadabc4a8f306ff29b4fdc49e4c2742ef5ff9df3609bb +size 4153548992 diff --git a/Megatron-Opus-14B-2.0.i1-IQ3_M.gguf b/Megatron-Opus-14B-2.0.i1-IQ3_M.gguf new file mode 100644 index 0000000..838f29a --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:106f56b6fe66f706e6fd611e461e0772a9e42c082aef9f3fc6b657a13211774a +size 6739763392 diff --git a/Megatron-Opus-14B-2.0.i1-IQ3_S.gguf b/Megatron-Opus-14B-2.0.i1-IQ3_S.gguf new file mode 100644 index 0000000..5dc7c71 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:778de8dc4b312cdd7747e0056103ae0e8ed66be8c2c50f85100eeb1985ae16fa +size 6539571392 diff --git a/Megatron-Opus-14B-2.0.i1-IQ3_XS.gguf b/Megatron-Opus-14B-2.0.i1-IQ3_XS.gguf new file mode 100644 index 0000000..79cb167 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f520b064e18126d259e1bb851354fe73433a065f6c87f5f9ec121be15c32ef6c +size 6220083392 diff --git a/Megatron-Opus-14B-2.0.i1-IQ3_XXS.gguf b/Megatron-Opus-14B-2.0.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a3202f4 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:784a455aae2842fe19d462e9e28dffd72cd5235c4f9c962fd6b93ef7f5028809 +size 5811876032 diff --git a/Megatron-Opus-14B-2.0.i1-IQ4_NL.gguf b/Megatron-Opus-14B-2.0.i1-IQ4_NL.gguf new file mode 100644 index 0000000..cc9c2a1 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24de624231e38216d27907be1f0d9f598c0b34e5f24d03f755ae41a92af8f43d +size 8416194752 diff --git a/Megatron-Opus-14B-2.0.i1-IQ4_XS.gguf b/Megatron-Opus-14B-2.0.i1-IQ4_XS.gguf new file mode 100644 index 0000000..68fc309 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f533e66d68c707fbbfa309f37c787f5eafbc65f152692773e8fdfee30649dd4 +size 7982346432 diff --git a/Megatron-Opus-14B-2.0.i1-Q2_K.gguf b/Megatron-Opus-14B-2.0.i1-Q2_K.gguf new file mode 100644 index 0000000..86fc110 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aa62cb8a369ffa4960da365065d047a146f82976e4028459c70df9752b40aa3 +size 5608796352 diff --git a/Megatron-Opus-14B-2.0.i1-Q2_K_S.gguf b/Megatron-Opus-14B-2.0.i1-Q2_K_S.gguf new file mode 100644 index 0000000..ab18cf5 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dadfaabf9ecaa382c7d55cfaffb8d48bb939a57ebe2bf0416a0b7abbca548c5 +size 5237084352 diff --git a/Megatron-Opus-14B-2.0.i1-Q3_K_L.gguf b/Megatron-Opus-14B-2.0.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4aec8aa --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8894f901f4a2488d783d576c895b060e804773b2d1dcefe9e94d57024da8308e +size 7788851392 diff --git a/Megatron-Opus-14B-2.0.i1-Q3_K_M.gguf b/Megatron-Opus-14B-2.0.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4676c6d --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d5f000a628c53ffbefd92839b1d877ddd9896e19f20448583326eb24d6f725 +size 7190835392 diff --git a/Megatron-Opus-14B-2.0.i1-Q3_K_S.gguf b/Megatron-Opus-14B-2.0.i1-Q3_K_S.gguf new file mode 100644 index 0000000..18f18b5 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc22232f653ef0ceb03ba8f34af1c6efd79967cc3ee9e5bd79a81a25e06f046 +size 6504755392 diff --git a/Megatron-Opus-14B-2.0.i1-Q4_0.gguf b/Megatron-Opus-14B-2.0.i1-Q4_0.gguf new file mode 100644 index 0000000..b1f2710 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4a52c90fef941c473681dba31ec4df294391831713ba8933dbc641c557c5e58 +size 8412098752 diff --git a/Megatron-Opus-14B-2.0.i1-Q4_1.gguf b/Megatron-Opus-14B-2.0.i1-Q4_1.gguf new file mode 100644 index 0000000..b14ae43 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0808163ca0008271baf87952c95c4b62dbc940d15e7f72989144c183daa1df3b +size 9267507392 diff --git a/Megatron-Opus-14B-2.0.i1-Q4_K_M.gguf b/Megatron-Opus-14B-2.0.i1-Q4_K_M.gguf new file mode 100644 index 0000000..41b7b82 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f561f2288b7340faa86044b96fc749fcbcdb9de51dab233d96b31ae0e9195d4 +size 8890306752 diff --git a/Megatron-Opus-14B-2.0.i1-Q4_K_S.gguf b/Megatron-Opus-14B-2.0.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b51d8e3 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9502472a5631c9ebb32e9fa662d0af5591257dc0cd8f5053ec7c322fe015549f +size 8444047552 diff --git a/Megatron-Opus-14B-2.0.i1-Q5_K_M.gguf b/Megatron-Opus-14B-2.0.i1-Q5_K_M.gguf new file mode 100644 index 0000000..86c4ed5 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f808496db7a08a9043dbf9eea3c016ed2638b108a5e6ac997d22343d554168 +size 10412708032 diff --git a/Megatron-Opus-14B-2.0.i1-Q5_K_S.gguf b/Megatron-Opus-14B-2.0.i1-Q5_K_S.gguf new file mode 100644 index 0000000..1948139 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e149b102e2713e6cbaac1fd6ebf7a89e747c9188d163aebbcb235d15c1277b +size 10151588032 diff --git a/Megatron-Opus-14B-2.0.i1-Q6_K.gguf b/Megatron-Opus-14B-2.0.i1-Q6_K.gguf new file mode 100644 index 0000000..ffbca23 --- /dev/null +++ b/Megatron-Opus-14B-2.0.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe068e60d73ef3fa98a8e67c52531b5454a60d59b9e00653f345e1ddc73c5ad6 +size 12030259392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..40adb07 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: prithivMLmods/Megatron-Opus-14B-2.0 +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- text-generation-inference +- llama3.1 +- phi4 +- LlamaForCausalLM +- Corpus +- trl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Megatron-Opus-14B-2.0 + + +static quants are available at https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-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/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ1_S.gguf) | i1-IQ1_S | 3.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ1_M.gguf) | i1-IQ1_M | 3.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ2_S.gguf) | i1-IQ2_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ2_M.gguf) | i1-IQ2_M | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q2_K.gguf) | i1-Q2_K | 5.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ3_S.gguf) | i1-IQ3_S | 6.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ3_M.gguf) | i1-IQ3_M | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.1 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q4_0.gguf) | i1-Q4_0 | 8.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q4_1.gguf) | i1-Q4_1 | 9.4 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.3 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/Megatron-Opus-14B-2.0-i1-GGUF/resolve/main/Megatron-Opus-14B-2.0.i1-Q6_K.gguf) | i1-Q6_K | 12.1 | 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..007adc6 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d640370c35a2e600f87343df94d7491a7c12c302451c8836d539047ad2b125 +size 7791685