commit 80c45d157928337886b277d32abc7ec42429c782 Author: ModelHub XC Date: Tue Apr 21 09:35:46 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5-1.8B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4252d32 --- /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 +Qwen1.5-1.8B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-1.8B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5-1.8B-Chat.IQ4_XS.gguf b/Qwen1.5-1.8B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..cacaa89 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cfba628e3f487546670168386b6dda6162c3973a350f6eb83571af50f8e572f +size 1087361920 diff --git a/Qwen1.5-1.8B-Chat.Q2_K.gguf b/Qwen1.5-1.8B-Chat.Q2_K.gguf new file mode 100644 index 0000000..835883a --- /dev/null +++ b/Qwen1.5-1.8B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28c25bc4299ae1105b3bad3cea1b379f6b7aa8cd8a3358ccb3e05d689d3d82db +size 846570368 diff --git a/Qwen1.5-1.8B-Chat.Q3_K_L.gguf b/Qwen1.5-1.8B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..cdf1275 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:766a165d79ab82ffdb68ae8809627597c49774ff1c9f90599c41a6b462d5cb87 +size 1056201600 diff --git a/Qwen1.5-1.8B-Chat.Q3_K_M.gguf b/Qwen1.5-1.8B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..75285f2 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1481e447527f3f869a57042a151e66d9c6531c00bf4bd47ba84cc071600bb524 +size 1015880576 diff --git a/Qwen1.5-1.8B-Chat.Q3_K_S.gguf b/Qwen1.5-1.8B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..1e3fe42 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db9b52fb2bf66602362be8333be6dd42cf4d5b29b49f72cb51d1071d9cd83d32 +size 953572224 diff --git a/Qwen1.5-1.8B-Chat.Q4_K_M.gguf b/Qwen1.5-1.8B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..3e8563b --- /dev/null +++ b/Qwen1.5-1.8B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa1580f1ae6a6ae902f721e84df7e69d45b22d7a2009bec921da498ce259d798 +size 1217753984 diff --git a/Qwen1.5-1.8B-Chat.Q4_K_S.gguf b/Qwen1.5-1.8B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..cc7a603 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f051da74ac122fd60d3686e999017e3c7c93a854b1652cd9603c19ad1806abd3 +size 1158263680 diff --git a/Qwen1.5-1.8B-Chat.Q5_K_M.gguf b/Qwen1.5-1.8B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..aaae167 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f222b27e00e1b8241cbe986ca286a98bb6443c93e6687fd007a9a3ab9d6d4f +size 1376777088 diff --git a/Qwen1.5-1.8B-Chat.Q5_K_S.gguf b/Qwen1.5-1.8B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..fd2c88f --- /dev/null +++ b/Qwen1.5-1.8B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76a32e3a0a11394af1b8603f992fcf971d213dd56cc90a3cfbafde81fdd1a76a +size 1327821696 diff --git a/Qwen1.5-1.8B-Chat.Q6_K.gguf b/Qwen1.5-1.8B-Chat.Q6_K.gguf new file mode 100644 index 0000000..3d70ed1 --- /dev/null +++ b/Qwen1.5-1.8B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fe0540e1226d1ad9eb80e1d8dfe62e55b2d1b1c49927bf23ad87e09c111c858 +size 1579027328 diff --git a/Qwen1.5-1.8B-Chat.Q8_0.gguf b/Qwen1.5-1.8B-Chat.Q8_0.gguf new file mode 100644 index 0000000..6e44b7b --- /dev/null +++ b/Qwen1.5-1.8B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77433fd810ed0351638dc782a690e13b770c8ac91c34a234ff631e30918ed4a3 +size 1958304640 diff --git a/Qwen1.5-1.8B-Chat.f16.gguf b/Qwen1.5-1.8B-Chat.f16.gguf new file mode 100644 index 0000000..590196d --- /dev/null +++ b/Qwen1.5-1.8B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5e53dc0f540aaaa7cd2415854e353cf651d6f87faaabfdce9865f82e92f3bca +size 3680099200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b08bc94 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: Qwen/Qwen1.5-1.8B-Chat +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat/blob/main/LICENSE +license_name: tongyi-qianwen-research +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-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/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.IQ4_XS.gguf) | IQ4_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.Q5_K_M.gguf) | Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.Q8_0.gguf) | Q8_0 | 2.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-1.8B-Chat-GGUF/resolve/main/Qwen1.5-1.8B-Chat.f16.gguf) | f16 | 3.8 | 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. + +