commit a0ecc2868a0c3cfbc14f2a650e774e878aedba38 Author: ModelHub XC Date: Sat Oct 10 21:05:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0ee4664 --- /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 +NeuralsirkrishnaShadow_Experiment26Yam.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralsirkrishnaShadow_Experiment26Yam.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralsirkrishnaShadow_Experiment26Yam.f16.gguf filter=lfs diff=lfs merge=lfs -text +NeuralsirkrishnaShadow_Experiment26Yam.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralsirkrishnaShadow_Experiment26Yam.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralsirkrishnaShadow_Experiment26Yam.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralsirkrishnaShadow_Experiment26Yam.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralsirkrishnaShadow_Experiment26Yam.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralsirkrishnaShadow_Experiment26Yam.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.IQ4_XS.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.IQ4_XS.gguf new file mode 100644 index 0000000..a6d41f6 --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:059d2025603e8624eff57e3061bd763799876cb4a4beb18f9ecf389b981045d7 +size 3944389824 diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.Q2_K.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.Q2_K.gguf new file mode 100644 index 0000000..5d16043 --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8caa9bf04de68ec3372caa0370db7b32841caa07cba9db03727505149ffded07 +size 2719243456 diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_L.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_L.gguf new file mode 100644 index 0000000..61b3ebb --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8d7d0cf4178e1ab315043e760772a54f10cd8631ed656b862b56fb4f1164926 +size 3822025920 diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_M.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_M.gguf new file mode 100644 index 0000000..02a0c45 --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c64cc62b27ecfeba0b19184a3b8e5b8dab09d02ca43c18d14f32d869fed09fa6 +size 3518987456 diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_S.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_S.gguf new file mode 100644 index 0000000..97e7067 --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0abb537957ddeacff0d16de6e741e66ef7a2615419139c5e1c8b7bdeabc668ec +size 3164568768 diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.Q4_K_M.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.Q4_K_M.gguf new file mode 100644 index 0000000..694e9fc --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccbbde3e6c5a81d0fc0445819996d2098429b604ffdef5e42098053cfeb8750d +size 4368440512 diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.Q4_K_S.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.Q4_K_S.gguf new file mode 100644 index 0000000..baec138 --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1045df3bb561d5ae0bc6e579b3edfc28f4baef2758f4da64efad8613bd58856a +size 4140375232 diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.Q5_K_M.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.Q5_K_M.gguf new file mode 100644 index 0000000..c4d7b3a --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06aeef7ba6e9f1fbed90ba2965b773ccbf503222f3fa64987e70abf15207f36c +size 5131410624 diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.Q5_K_S.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.Q5_K_S.gguf new file mode 100644 index 0000000..a7d6308 --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:694e96f1dc4b9fec2189de5ca4e1c75ca307fff11ce95a7903ff31e96391aff5 +size 4997717184 diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.Q6_K.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.Q6_K.gguf new file mode 100644 index 0000000..a9109f9 --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af58bfed233cd7811c7cdc5ee629655dfca4a9b9e10d420dc87b165b8d627f20 +size 5942066368 diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.Q8_0.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.Q8_0.gguf new file mode 100644 index 0000000..03cb380 --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:806b96a06a85359edb827517c2064c1c82beb7d1853d90be846458772d1f1e1d +size 7695858880 diff --git a/NeuralsirkrishnaShadow_Experiment26Yam.f16.gguf b/NeuralsirkrishnaShadow_Experiment26Yam.f16.gguf new file mode 100644 index 0000000..7c22b31 --- /dev/null +++ b/NeuralsirkrishnaShadow_Experiment26Yam.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b631fe344999a71156e6a5681a6bc5113eca33df080fa09d78a6c9c84fff2ff4 +size 14484733120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4156a87 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: MaziyarPanahi/NeuralsirkrishnaShadow_Experiment26Yam +language: +- en +library_name: transformers +license: apache-2.0 +model_creator: MaziyarPanahi +model_name: NeuralsirkrishnaShadow_Experiment26Yam +quantized_by: mradermacher +tags: +- Safetensors +- text-generation-inference +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/MaziyarPanahi/NeuralsirkrishnaShadow_Experiment26Yam + + +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/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralsirkrishnaShadow_Experiment26Yam-GGUF/resolve/main/NeuralsirkrishnaShadow_Experiment26Yam.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. 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. + +