commit a930315d70a7e923e4a75aae4205fa2fa70d7a6f Author: ModelHub XC Date: Sun Jun 14 17:08:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-7b-LongCot-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5091c46 --- /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-7b-LongCot.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7b-LongCot.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7b-LongCot.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7b-LongCot.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7b-LongCot.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7b-LongCot.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7b-LongCot.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7b-LongCot.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7b-LongCot.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7b-LongCot.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7b-LongCot.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7b-LongCot.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-7b-LongCot.IQ4_XS.gguf b/Qwen-7b-LongCot.IQ4_XS.gguf new file mode 100644 index 0000000..bf7ae12 --- /dev/null +++ b/Qwen-7b-LongCot.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58ea091af70a29dfaa124e6a274a8bdc6b74e8af333e2205573b46c6729aa9ff +size 4250298816 diff --git a/Qwen-7b-LongCot.Q2_K.gguf b/Qwen-7b-LongCot.Q2_K.gguf new file mode 100644 index 0000000..2305703 --- /dev/null +++ b/Qwen-7b-LongCot.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e2bea140fdd0b3cdf46c2ab78e9210e1aa6bd0d8a1c9b0400d53fdec2c6253a +size 3015940544 diff --git a/Qwen-7b-LongCot.Q3_K_L.gguf b/Qwen-7b-LongCot.Q3_K_L.gguf new file mode 100644 index 0000000..7eaeb17 --- /dev/null +++ b/Qwen-7b-LongCot.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e753b475d359227ceba3c5fee8dfc2c82c2a32cdd5f7d129afa9bc6a1f3d45f +size 4088459712 diff --git a/Qwen-7b-LongCot.Q3_K_M.gguf b/Qwen-7b-LongCot.Q3_K_M.gguf new file mode 100644 index 0000000..c959f63 --- /dev/null +++ b/Qwen-7b-LongCot.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19bd459f043ec51a5660b7146288cf339f09f49fdb9c951c2475adeef949e48e +size 3808391616 diff --git a/Qwen-7b-LongCot.Q3_K_S.gguf b/Qwen-7b-LongCot.Q3_K_S.gguf new file mode 100644 index 0000000..d605ff9 --- /dev/null +++ b/Qwen-7b-LongCot.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c17e828336bb4aa1395a7f70a767d1e4eec6f97846e623dd5d4b20b4b1252ff +size 3492368832 diff --git a/Qwen-7b-LongCot.Q4_K_M.gguf b/Qwen-7b-LongCot.Q4_K_M.gguf new file mode 100644 index 0000000..32e52d4 --- /dev/null +++ b/Qwen-7b-LongCot.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbff42c95217aa18b491a4b759d3379ba4319cbf4b0993af9d55090e1b7d091b +size 4683073984 diff --git a/Qwen-7b-LongCot.Q4_K_S.gguf b/Qwen-7b-LongCot.Q4_K_S.gguf new file mode 100644 index 0000000..e291cee --- /dev/null +++ b/Qwen-7b-LongCot.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a089a95e1450457ee392466229f6ad3cf8a2008876d865d7711b8a82f9952408 +size 4457769408 diff --git a/Qwen-7b-LongCot.Q5_K_M.gguf b/Qwen-7b-LongCot.Q5_K_M.gguf new file mode 100644 index 0000000..12727a8 --- /dev/null +++ b/Qwen-7b-LongCot.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c45de6522fc369b42cd9bf37ece228bf309f71e48e6f6265983bf49d65b82a48 +size 5444831680 diff --git a/Qwen-7b-LongCot.Q5_K_S.gguf b/Qwen-7b-LongCot.Q5_K_S.gguf new file mode 100644 index 0000000..ef71568 --- /dev/null +++ b/Qwen-7b-LongCot.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9031806d6ca16f0d67f008ca8657f8a5cd6bfe3c3c30b2042f1a53bc0f7d32dc +size 5315176896 diff --git a/Qwen-7b-LongCot.Q6_K.gguf b/Qwen-7b-LongCot.Q6_K.gguf new file mode 100644 index 0000000..9b8e3d9 --- /dev/null +++ b/Qwen-7b-LongCot.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c692ebbc2c2e03aa978877c506b98a85e118ef94c9f61f4aedaa193bdf0d4b +size 6254199232 diff --git a/Qwen-7b-LongCot.Q8_0.gguf b/Qwen-7b-LongCot.Q8_0.gguf new file mode 100644 index 0000000..f6d239e --- /dev/null +++ b/Qwen-7b-LongCot.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66b829610e8d1d22070660fb594d3f103cafb58e47f7f5fa1088f59bda98fd99 +size 8098525632 diff --git a/Qwen-7b-LongCot.f16.gguf b/Qwen-7b-LongCot.f16.gguf new file mode 100644 index 0000000..23c60c3 --- /dev/null +++ b/Qwen-7b-LongCot.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9457e859e5c9bd78df0540c004ea5d73f0494419504d95c794a08d8024309ebf +size 15237853632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f18f9d6 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: fhai50032/Qwen-7b-LongCot +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/fhai50032/Qwen-7b-LongCot + + +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-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7b-LongCot-GGUF/resolve/main/Qwen-7b-LongCot.f16.gguf) | f16 | 15.3 | 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. + +