commit 94ead8ffd2c2abaebf13fa707c86c756897653b8 Author: ModelHub XC Date: Sat Jun 27 07:00:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Maestro-R1-Llama-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7881f90 --- /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 +Maestro-R1-Llama-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Maestro-R1-Llama-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Maestro-R1-Llama-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Maestro-R1-Llama-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Maestro-R1-Llama-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Maestro-R1-Llama-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Maestro-R1-Llama-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Maestro-R1-Llama-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Maestro-R1-Llama-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Maestro-R1-Llama-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Maestro-R1-Llama-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Maestro-R1-Llama-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Maestro-R1-Llama-8B.IQ4_XS.gguf b/Maestro-R1-Llama-8B.IQ4_XS.gguf new file mode 100644 index 0000000..e7dd0fd --- /dev/null +++ b/Maestro-R1-Llama-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33333594ceafeb31cdf1a90e338cf6d4dd67e175a72490bfe86cd7dfd4982974 +size 4484366272 diff --git a/Maestro-R1-Llama-8B.Q2_K.gguf b/Maestro-R1-Llama-8B.Q2_K.gguf new file mode 100644 index 0000000..3a6d489 --- /dev/null +++ b/Maestro-R1-Llama-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16b979381cc4d7c83c3e3f2cd21b85e9347694242697fe98720207f3de9b4bb3 +size 3179134912 diff --git a/Maestro-R1-Llama-8B.Q3_K_L.gguf b/Maestro-R1-Llama-8B.Q3_K_L.gguf new file mode 100644 index 0000000..6cc4705 --- /dev/null +++ b/Maestro-R1-Llama-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5fad11e6e0a67f44ef9f347aa47bc63647865a3613acdb03e7f5e0de3123048 +size 4321959872 diff --git a/Maestro-R1-Llama-8B.Q3_K_M.gguf b/Maestro-R1-Llama-8B.Q3_K_M.gguf new file mode 100644 index 0000000..e247ff1 --- /dev/null +++ b/Maestro-R1-Llama-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a685cd1008b1865865ace11a7919f5e12ff65a1226a0d2528d40afe13a353009 +size 4018921408 diff --git a/Maestro-R1-Llama-8B.Q3_K_S.gguf b/Maestro-R1-Llama-8B.Q3_K_S.gguf new file mode 100644 index 0000000..ba15eba --- /dev/null +++ b/Maestro-R1-Llama-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8aa7a06719183b71c36ffc1ed8f07354b6bc68a0d42d884f1fa19d8758867b0 +size 3664502720 diff --git a/Maestro-R1-Llama-8B.Q4_K_M.gguf b/Maestro-R1-Llama-8B.Q4_K_M.gguf new file mode 100644 index 0000000..390fdc7 --- /dev/null +++ b/Maestro-R1-Llama-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cfd06191d04a5d6aca892b7e70017fef6d0128b264f7c18f7cc4419684bbad2 +size 4920737728 diff --git a/Maestro-R1-Llama-8B.Q4_K_S.gguf b/Maestro-R1-Llama-8B.Q4_K_S.gguf new file mode 100644 index 0000000..97b8571 --- /dev/null +++ b/Maestro-R1-Llama-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8265d462a79944b8200b0e365f8dcd4975acb8c6da118b2da68cf37f19c7061f +size 4692672448 diff --git a/Maestro-R1-Llama-8B.Q5_K_M.gguf b/Maestro-R1-Llama-8B.Q5_K_M.gguf new file mode 100644 index 0000000..0afda60 --- /dev/null +++ b/Maestro-R1-Llama-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9593d50e4d8f03771ab20bc5db3d525c487df578cdeeee8beafd49f84818c6d9 +size 5732990912 diff --git a/Maestro-R1-Llama-8B.Q5_K_S.gguf b/Maestro-R1-Llama-8B.Q5_K_S.gguf new file mode 100644 index 0000000..5c0da01 --- /dev/null +++ b/Maestro-R1-Llama-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb46e57e1069d0b7093c6b19bd4bfa6d59f4b6d05834093cd04012b61cf703e +size 5599297472 diff --git a/Maestro-R1-Llama-8B.Q6_K.gguf b/Maestro-R1-Llama-8B.Q6_K.gguf new file mode 100644 index 0000000..937f16d --- /dev/null +++ b/Maestro-R1-Llama-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38b0ad3c64a8067ba4236d80bab9474cabf8a49a08e0d149bedc8b4684e38cbd +size 6596009920 diff --git a/Maestro-R1-Llama-8B.Q8_0.gguf b/Maestro-R1-Llama-8B.Q8_0.gguf new file mode 100644 index 0000000..7a1a849 --- /dev/null +++ b/Maestro-R1-Llama-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cb94636f8cd0a2594a16df3d794831448e9852996b70bc5d238d8b553bc0d77 +size 8540774336 diff --git a/Maestro-R1-Llama-8B.f16.gguf b/Maestro-R1-Llama-8B.f16.gguf new file mode 100644 index 0000000..99f72af --- /dev/null +++ b/Maestro-R1-Llama-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:939bb8f7aad22265f0c56edf8d93124863f6c850b36136f6ff2b92fc90a7d103 +size 16068894656 diff --git a/README.md b/README.md new file mode 100644 index 0000000..93d0ab4 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: suayptalha/Maestro-R1-Llama-8B +datasets: +- ServiceNow-AI/R1-Distill-SFT +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/suayptalha/Maestro-R1-Llama-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-i1-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/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.f16.gguf) | f16 | 16.2 | 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. + +