commit 06a4a5c648cbfd95b78da05f51c50bf6853060cf Author: ModelHub XC Date: Fri Jul 10 07:35:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e986527 --- /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 +Qwen2.5-Coder-Draft-1.5B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-Draft-1.5B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-Draft-1.5B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-Draft-1.5B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-Draft-1.5B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-Draft-1.5B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-Draft-1.5B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-Draft-1.5B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-Draft-1.5B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.IQ4_XS.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..028b2d4 --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:597020ddfbe6839d782a96a1f1289e12d81b9e614dd6870f3cf417507f90c3e2 +size 902347424 diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.Q2_K.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..b4e8261 --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5297a20098404e07e71a6fc86d5c4fbf4f75f44938155cc41eb27008a013b9d6 +size 676469408 diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_L.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..8bc4138 --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:969ff4c703768dfd20bb7528de6164d1c4a587b4754a5cb639980f1e8976bc88 +size 880327328 diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_M.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..63ce6a2 --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700371a463d84f425861ccb73b0ed9acb09bcc89ed69a218c0a8f581d41b68b8 +size 824343200 diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_S.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..652eb78 --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72dda984bca5302ad7b7a5c336808635276bb33d0ab0bad2f496290b538282d8 +size 761109152 diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.Q4_K_M.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..e956296 --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c264cd87d82dffe472131f16775e4ad88a41c611c5feda150ec0f4603e9717d4 +size 986213024 diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.Q4_K_S.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..03a90a2 --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7545b6e4b31e60f58d94f0a5ca6fec0b81b12ada0122a8077ae3eb35183d746e +size 940477088 diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.Q5_K_M.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..1cd9db2 --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87ae1aea25ead1fc16ada306e3b7b5652fa5e17f05a8ee93b203b3b57ee4d11 +size 1125214880 diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.Q5_K_S.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..c56c87f --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3201a3407c5a0512b4538c83e55bea03c4b1f736c05c47ea76a1b65a1f38016d +size 1098893984 diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.Q6_K.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..efb32ef --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcbf1798bf2420d9e6ec4055305e828869bbdddbe7b043742f8071284de7d0b8 +size 1272904352 diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.Q8_0.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..b37eb13 --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77080aa3fbd3e30c9127aa5d3a0f1966afeb31dee88d665d11d274af8d408200 +size 1646785184 diff --git a/Qwen2.5-Coder-Draft-1.5B-Instruct.f16.gguf b/Qwen2.5-Coder-Draft-1.5B-Instruct.f16.gguf new file mode 100644 index 0000000..6de41ba --- /dev/null +++ b/Qwen2.5-Coder-Draft-1.5B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c9d0817e04e8aa8093d1a61e4af41647235f758574976022880e05199fb1f63 +size 3094065824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..077fa0c --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: qingy2024/Qwen2.5-Coder-Draft-1.5B-Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/qingy2024/Qwen2.5-Coder-Draft-1.5B-Instruct + + +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/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-Draft-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-Coder-Draft-1.5B-Instruct.f16.gguf) | f16 | 3.2 | 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. + +