commit 07b4da80d3b4dc62e72aacef7c89da0585a0975e Author: ModelHub XC Date: Sun Jul 5 19:07:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MentalChat-16K-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..539002a --- /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 +MentalChat-16K.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MentalChat-16K.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MentalChat-16K.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MentalChat-16K.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MentalChat-16K.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MentalChat-16K.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MentalChat-16K.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MentalChat-16K.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MentalChat-16K.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MentalChat-16K.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MentalChat-16K.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MentalChat-16K.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MentalChat-16K.IQ4_XS.gguf b/MentalChat-16K.IQ4_XS.gguf new file mode 100644 index 0000000..0f46d21 --- /dev/null +++ b/MentalChat-16K.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cff068ae93bad91442513d53b5bb7c9d1e499613fd1e908f0bb267cc2bd067e7 +size 748385152 diff --git a/MentalChat-16K.Q2_K.gguf b/MentalChat-16K.Q2_K.gguf new file mode 100644 index 0000000..d95aab2 --- /dev/null +++ b/MentalChat-16K.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52d45b31f194915c7ab7e0d733e5cae6dbfd8d6516f9b1fe2d523b8ab2cc3717 +size 580875136 diff --git a/MentalChat-16K.Q3_K_L.gguf b/MentalChat-16K.Q3_K_L.gguf new file mode 100644 index 0000000..a642d35 --- /dev/null +++ b/MentalChat-16K.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce6662e0ce7842a9d3335220ac2a075507551eab06004cce3d9cb5382925954 +size 732525440 diff --git a/MentalChat-16K.Q3_K_M.gguf b/MentalChat-16K.Q3_K_M.gguf new file mode 100644 index 0000000..4bb2169 --- /dev/null +++ b/MentalChat-16K.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ddd0d88115b918f49b53190be0812e670fb8f08d11865616f7c4d14e1aa2f87 +size 690844544 diff --git a/MentalChat-16K.Q3_K_S.gguf b/MentalChat-16K.Q3_K_S.gguf new file mode 100644 index 0000000..87eb734 --- /dev/null +++ b/MentalChat-16K.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c90709c5286c01f83c963e8f55a30ca39684f67c54280496c69cd3c56ea12522 +size 641692544 diff --git a/MentalChat-16K.Q4_K_M.gguf b/MentalChat-16K.Q4_K_M.gguf new file mode 100644 index 0000000..b364f58 --- /dev/null +++ b/MentalChat-16K.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf4dc06d0216c0fbc31be21ae3042259f5050ed3e5a99f087962d9b21b04cda0 +size 807695232 diff --git a/MentalChat-16K.Q4_K_S.gguf b/MentalChat-16K.Q4_K_S.gguf new file mode 100644 index 0000000..a323277 --- /dev/null +++ b/MentalChat-16K.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2549d1f7dd586a744eb80faa51c8630499c35f4bc0f70062dd6bb1876f2e7329 +size 775648128 diff --git a/MentalChat-16K.Q5_K_M.gguf b/MentalChat-16K.Q5_K_M.gguf new file mode 100644 index 0000000..f0f5f4e --- /dev/null +++ b/MentalChat-16K.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d979047037c94360399555053246a62d110082aae36ca57565546acacd0a5041 +size 911504256 diff --git a/MentalChat-16K.Q5_K_S.gguf b/MentalChat-16K.Q5_K_S.gguf new file mode 100644 index 0000000..bc34ec8 --- /dev/null +++ b/MentalChat-16K.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95bc2924f682c8e9b0ee56cc3725bf89328786a89c2c492b733e0c66bceabf69 +size 892564352 diff --git a/MentalChat-16K.Q6_K.gguf b/MentalChat-16K.Q6_K.gguf new file mode 100644 index 0000000..289593d --- /dev/null +++ b/MentalChat-16K.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b3549924c76c9d0fa85a8d3864c2e0f811d799033fb0c5eef533084c07236d4 +size 1021801344 diff --git a/MentalChat-16K.Q8_0.gguf b/MentalChat-16K.Q8_0.gguf new file mode 100644 index 0000000..30eb515 --- /dev/null +++ b/MentalChat-16K.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad3f08c0801b0f1849bfca8fb7be9745c285751a400d2f937718596be705e7b2 +size 1321083776 diff --git a/MentalChat-16K.f16.gguf b/MentalChat-16K.f16.gguf new file mode 100644 index 0000000..b0a41d7 --- /dev/null +++ b/MentalChat-16K.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbc6ddaa78f58937a70736e0d017be56db038b1a87884ee69153fc69b3260229 +size 2479596416 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1c70fe9 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: khazarai/MentalChat-16K +datasets: +- ShenLab/MentalChat16K +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- sft +- unsloth +- trl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/khazarai/MentalChat-16K + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MentalChat-16K-GGUF).*** + +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/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MentalChat-16K-GGUF/resolve/main/MentalChat-16K.f16.gguf) | f16 | 2.6 | 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. + +