commit 7deb31142febaaf7d34af0b5da85e7caff94379d Author: ModelHub XC Date: Sat Jul 11 13:07:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Monarch-1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6170a86 --- /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 +*.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 +Monarch-1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Monarch-1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Monarch-1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Monarch-1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Monarch-1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Monarch-1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Monarch-1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Monarch-1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Monarch-1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Monarch-1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Monarch-1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Monarch-1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Monarch-1.IQ4_XS.gguf b/Monarch-1.IQ4_XS.gguf new file mode 100644 index 0000000..45b87e3 --- /dev/null +++ b/Monarch-1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d10dbe9c477d50748c907693ad275c04a0f322c10e40a3a313f9b4a8401384 +size 3948667776 diff --git a/Monarch-1.Q2_K.gguf b/Monarch-1.Q2_K.gguf new file mode 100644 index 0000000..2554e70 --- /dev/null +++ b/Monarch-1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87b56e7c60d6b68a6ceb13815d3862659cf6533b7608bf9a5c3da6b2e0aa54eb +size 2722882432 diff --git a/Monarch-1.Q3_K_L.gguf b/Monarch-1.Q3_K_L.gguf new file mode 100644 index 0000000..e655cfb --- /dev/null +++ b/Monarch-1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989c4c6842819f268a204e807745769f78e566c4921c123fe5636a866ef5dfcc +size 3825984384 diff --git a/Monarch-1.Q3_K_M.gguf b/Monarch-1.Q3_K_M.gguf new file mode 100644 index 0000000..85a6618 --- /dev/null +++ b/Monarch-1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97e48576d43ce1b971003a78a5289b71680086078b361a83951ec4073a8996da +size 3522945920 diff --git a/Monarch-1.Q3_K_S.gguf b/Monarch-1.Q3_K_S.gguf new file mode 100644 index 0000000..63a2d7f --- /dev/null +++ b/Monarch-1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:256d493bb3f7380472aeff52230a008c0e3f8598ff4acfff7c878458bf159778 +size 3168527232 diff --git a/Monarch-1.Q4_K_M.gguf b/Monarch-1.Q4_K_M.gguf new file mode 100644 index 0000000..38b8b63 --- /dev/null +++ b/Monarch-1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e96e6138db5748b02462a317ae3e7c3c57e987d3a5d8f266eca69dc96b27f52b +size 4372816768 diff --git a/Monarch-1.Q4_K_S.gguf b/Monarch-1.Q4_K_S.gguf new file mode 100644 index 0000000..3957df7 --- /dev/null +++ b/Monarch-1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c1dfd8faff01c9d7b95efe047418d2dd3aaca1a53aa937714dd313c311a565 +size 4144751488 diff --git a/Monarch-1.Q5_K_M.gguf b/Monarch-1.Q5_K_M.gguf new file mode 100644 index 0000000..599160b --- /dev/null +++ b/Monarch-1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c40fca5e4e3943cf1bff1738a84d713e85c2c5bb30d494ae7ad20a9a031b64fb +size 5136180096 diff --git a/Monarch-1.Q5_K_S.gguf b/Monarch-1.Q5_K_S.gguf new file mode 100644 index 0000000..c14a3cb --- /dev/null +++ b/Monarch-1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4132145dc800feab01e2390ccd5980aca1363adff992c3278896f17b642601bd +size 5002486656 diff --git a/Monarch-1.Q6_K.gguf b/Monarch-1.Q6_K.gguf new file mode 100644 index 0000000..08e5a13 --- /dev/null +++ b/Monarch-1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:594e1be5588d61b6ff6bd331a267de51faa590caa61db2bc0ee626ce75823864 +size 5947253632 diff --git a/Monarch-1.Q8_0.gguf b/Monarch-1.Q8_0.gguf new file mode 100644 index 0000000..ddbc350 --- /dev/null +++ b/Monarch-1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8eb7b201ababeb4efc6cc6b3efbe457d6767402139b17dc5586c38c6264244 +size 7702569856 diff --git a/Monarch-1.f16.gguf b/Monarch-1.f16.gguf new file mode 100644 index 0000000..d6204fa --- /dev/null +++ b/Monarch-1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6697e861099e03f67513811b889c91391a987e4e8384c598ab8ccd3d4fc66496 +size 14497342336 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0344b86 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: AfricaComputeFund/Monarch-1 +datasets: +- custom-curated-african-dataset +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- autotrain +- text-generation-inference +- text-generation +- peft +- africa +- monarch +- monarch-1 +- fine-tuning +--- +## About + + + + + + +static quants of https://huggingface.co/AfricaComputeFund/Monarch-1 + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Monarch-1-GGUF/resolve/main/Monarch-1.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Monarch-1-GGUF/resolve/main/Monarch-1.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Monarch-1-GGUF/resolve/main/Monarch-1.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Monarch-1-GGUF/resolve/main/Monarch-1.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Monarch-1-GGUF/resolve/main/Monarch-1.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Monarch-1-GGUF/resolve/main/Monarch-1.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Monarch-1-GGUF/resolve/main/Monarch-1.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Monarch-1-GGUF/resolve/main/Monarch-1.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Monarch-1-GGUF/resolve/main/Monarch-1.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Monarch-1-GGUF/resolve/main/Monarch-1.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Monarch-1-GGUF/resolve/main/Monarch-1.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Monarch-1-GGUF/resolve/main/Monarch-1.f16.gguf) | f16 | 14.6 | 16 bpw, overkill | + +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. + +