commit 2e7cf6e66d49a82e9d3012e87fdbd4233cc757f8 Author: ModelHub XC Date: Mon May 25 12:06:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DRT-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7e14d69 --- /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 +DRT-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +DRT-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DRT-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DRT-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DRT-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DRT-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DRT-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DRT-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DRT-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DRT-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DRT-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DRT-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DRT-7B.IQ4_XS.gguf b/DRT-7B.IQ4_XS.gguf new file mode 100644 index 0000000..a6db945 --- /dev/null +++ b/DRT-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1db8aef2c39a5607acfab06f3a27d0a59eba49bea6701b7edee8d0cf0a127c0b +size 4250299136 diff --git a/DRT-7B.Q2_K.gguf b/DRT-7B.Q2_K.gguf new file mode 100644 index 0000000..42c9280 --- /dev/null +++ b/DRT-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be54c26ba732cd6a6a6c6ab509ae99bde3982dc0af4f9bea7500fdcfd3a2fd0f +size 3015940864 diff --git a/DRT-7B.Q3_K_L.gguf b/DRT-7B.Q3_K_L.gguf new file mode 100644 index 0000000..527a826 --- /dev/null +++ b/DRT-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ccf9306d1d47306c9ba3422dd1f52dd45e20ee2fb7e4a897801a7379df22aba +size 4088460032 diff --git a/DRT-7B.Q3_K_M.gguf b/DRT-7B.Q3_K_M.gguf new file mode 100644 index 0000000..793c02d --- /dev/null +++ b/DRT-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8409f56eb068d508f825b7e0ed7f5c6359d8e8c7c128940628fb4b6a68367f97 +size 3808391936 diff --git a/DRT-7B.Q3_K_S.gguf b/DRT-7B.Q3_K_S.gguf new file mode 100644 index 0000000..1484b6e --- /dev/null +++ b/DRT-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cff0f06f790b11a4eaebcabb80ae627fd7e23dea458f2c630a546512189c9c50 +size 3492369152 diff --git a/DRT-7B.Q4_K_M.gguf b/DRT-7B.Q4_K_M.gguf new file mode 100644 index 0000000..bf99f79 --- /dev/null +++ b/DRT-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8788958d3d71864c372952e010eac3474b2fa5b27c523e4bad1c3ea25ac90811 +size 4683074304 diff --git a/DRT-7B.Q4_K_S.gguf b/DRT-7B.Q4_K_S.gguf new file mode 100644 index 0000000..199f06c --- /dev/null +++ b/DRT-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e4d7f0e5496a68f3f9cf4e8fb73e5ab5e5502404a491bde159882959427e661 +size 4457769728 diff --git a/DRT-7B.Q5_K_M.gguf b/DRT-7B.Q5_K_M.gguf new file mode 100644 index 0000000..25116c9 --- /dev/null +++ b/DRT-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1027c470275854a4d294dc972c8e035c8291d8a4ce8732cc19a468762e7682 +size 5444832000 diff --git a/DRT-7B.Q5_K_S.gguf b/DRT-7B.Q5_K_S.gguf new file mode 100644 index 0000000..ba53dcf --- /dev/null +++ b/DRT-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:781b6c60585808ec8558b7261fe4a9728c38b876e84da9575b95da5cbd2ed727 +size 5315177216 diff --git a/DRT-7B.Q6_K.gguf b/DRT-7B.Q6_K.gguf new file mode 100644 index 0000000..633bdfa --- /dev/null +++ b/DRT-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aa3df7c2a9eef2e38f447adde01b84e3f8bb78a06968f1293fd2a77b10d1e0d +size 6254199552 diff --git a/DRT-7B.Q8_0.gguf b/DRT-7B.Q8_0.gguf new file mode 100644 index 0000000..4b4d74d --- /dev/null +++ b/DRT-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24696300e7eeec5240c8a58c025731370e9015593babf0dc14646d9ffd8f734f +size 8098525952 diff --git a/DRT-7B.f16.gguf b/DRT-7B.f16.gguf new file mode 100644 index 0000000..b684062 --- /dev/null +++ b/DRT-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd1adc34c064355a2d7efb81cf4768cb457b671082240e228db25403d4d11e7e +size 15237853952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bf6ae1b --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Krystalan/DRT-7B +language: +- en +- zh +library_name: transformers +license: cc-by-nc-sa-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- machine tranlsation +- O1-like model +- Chat +--- +## About + + + + + + +static quants of https://huggingface.co/Krystalan/DRT-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DRT-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DRT-7B-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/DRT-7B-GGUF/resolve/main/DRT-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-7B-GGUF/resolve/main/DRT-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-7B-GGUF/resolve/main/DRT-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DRT-7B-GGUF/resolve/main/DRT-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-7B-GGUF/resolve/main/DRT-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-7B-GGUF/resolve/main/DRT-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DRT-7B-GGUF/resolve/main/DRT-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DRT-7B-GGUF/resolve/main/DRT-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-7B-GGUF/resolve/main/DRT-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/DRT-7B-GGUF/resolve/main/DRT-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DRT-7B-GGUF/resolve/main/DRT-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DRT-7B-GGUF/resolve/main/DRT-7B.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. + +