commit 1850439e9bb5bc0f1d5f38c553305688784586f6 Author: ModelHub XC Date: Thu Jul 16 20:44:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-SophiaAI-Finetune-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cfb54bf --- /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 +Qwen-SophiaAI-Finetune.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-SophiaAI-Finetune.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-SophiaAI-Finetune.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-SophiaAI-Finetune.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-SophiaAI-Finetune.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-SophiaAI-Finetune.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-SophiaAI-Finetune.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-SophiaAI-Finetune.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-SophiaAI-Finetune.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-SophiaAI-Finetune.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-SophiaAI-Finetune.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-SophiaAI-Finetune.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-SophiaAI-Finetune.IQ4_XS.gguf b/Qwen-SophiaAI-Finetune.IQ4_XS.gguf new file mode 100644 index 0000000..90aa125 --- /dev/null +++ b/Qwen-SophiaAI-Finetune.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c134a05b014125614e224677014454bebfe6ec74a5874294115d1bb89d3a3985 +size 1752724096 diff --git a/Qwen-SophiaAI-Finetune.Q2_K.gguf b/Qwen-SophiaAI-Finetune.Q2_K.gguf new file mode 100644 index 0000000..7a254c3 --- /dev/null +++ b/Qwen-SophiaAI-Finetune.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20c5d07cc7f7dd4b7b91ca047f8ba710f512fb1591d035432d5f3c990997e64e +size 1274294912 diff --git a/Qwen-SophiaAI-Finetune.Q3_K_L.gguf b/Qwen-SophiaAI-Finetune.Q3_K_L.gguf new file mode 100644 index 0000000..287997b --- /dev/null +++ b/Qwen-SophiaAI-Finetune.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c115d930c835dce25e12926834c4c34262ede6b172e2fa19becc8134ab287f83 +size 1706930816 diff --git a/Qwen-SophiaAI-Finetune.Q3_K_M.gguf b/Qwen-SophiaAI-Finetune.Q3_K_M.gguf new file mode 100644 index 0000000..557955f --- /dev/null +++ b/Qwen-SophiaAI-Finetune.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b2bbceb9c4739636afb03171199374a1bbb212d2ae6ef068f53cf74597e6c56 +size 1590014592 diff --git a/Qwen-SophiaAI-Finetune.Q3_K_S.gguf b/Qwen-SophiaAI-Finetune.Q3_K_S.gguf new file mode 100644 index 0000000..1fdbf62 --- /dev/null +++ b/Qwen-SophiaAI-Finetune.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1598f0e6d9843f3bd77832e8f87f16a2f88eeb44c3dffa2a5a42ad99a29cd2f8 +size 1453896320 diff --git a/Qwen-SophiaAI-Finetune.Q4_K_M.gguf b/Qwen-SophiaAI-Finetune.Q4_K_M.gguf new file mode 100644 index 0000000..bdd573e --- /dev/null +++ b/Qwen-SophiaAI-Finetune.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98628b75ea6cf7f896a5b4c9221af38c415a57d8a5b69c5fee4fc530df978748 +size 1929441920 diff --git a/Qwen-SophiaAI-Finetune.Q4_K_S.gguf b/Qwen-SophiaAI-Finetune.Q4_K_S.gguf new file mode 100644 index 0000000..f87d03e --- /dev/null +++ b/Qwen-SophiaAI-Finetune.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fa9178a200e990d9541066984da4b8383ae16373879895e04a9f3146296c8d9 +size 1833923200 diff --git a/Qwen-SophiaAI-Finetune.Q5_K_M.gguf b/Qwen-SophiaAI-Finetune.Q5_K_M.gguf new file mode 100644 index 0000000..a8589b9 --- /dev/null +++ b/Qwen-SophiaAI-Finetune.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8957a5c60ddb223c10e7b9f309bc7888bc865506a3f2589b4df6fae6e64a61f +size 2224353920 diff --git a/Qwen-SophiaAI-Finetune.Q5_K_S.gguf b/Qwen-SophiaAI-Finetune.Q5_K_S.gguf new file mode 100644 index 0000000..f1a8f4e --- /dev/null +++ b/Qwen-SophiaAI-Finetune.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:446b2c4c51af8022092bb73b12a604235644fe6ab99f556944ed7c4e6862de5f +size 2169205376 diff --git a/Qwen-SophiaAI-Finetune.Q6_K.gguf b/Qwen-SophiaAI-Finetune.Q6_K.gguf new file mode 100644 index 0000000..9d11fc7 --- /dev/null +++ b/Qwen-SophiaAI-Finetune.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a40911f0ba96c32bd61e697e1f222c472d223a5b2fa2745631cc42e13b21dd03 +size 2537697920 diff --git a/Qwen-SophiaAI-Finetune.Q8_0.gguf b/Qwen-SophiaAI-Finetune.Q8_0.gguf new file mode 100644 index 0000000..ba612d7 --- /dev/null +++ b/Qwen-SophiaAI-Finetune.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4828633dddb8a557dfc74adced62e3b1ce3c49abdad2164107599b85a1853d +size 3284880736 diff --git a/Qwen-SophiaAI-Finetune.f16.gguf b/Qwen-SophiaAI-Finetune.f16.gguf new file mode 100644 index 0000000..700f98b --- /dev/null +++ b/Qwen-SophiaAI-Finetune.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad122485ecd36f67c26b9c2084ca33911acf9310a48bb4a56dc9208f9eed4f05 +size 6177201376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fa2f31e --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: scott12355/Qwen-SophiaAI-Finetune +datasets: +- Amod/mental_health_counseling_conversations +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/scott12355/Qwen-SophiaAI-Finetune + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen-SophiaAI-Finetune-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/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-SophiaAI-Finetune-GGUF/resolve/main/Qwen-SophiaAI-Finetune.f16.gguf) | f16 | 6.3 | 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. + +