commit 95d7da6d24dbea315c5b425972f326f6409906ac Author: ModelHub XC Date: Mon May 25 17:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..05796e6 --- /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 +Bohdi-Qwen2.5-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Bohdi-Qwen2.5-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bohdi-Qwen2.5-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bohdi-Qwen2.5-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Bohdi-Qwen2.5-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Bohdi-Qwen2.5-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bohdi-Qwen2.5-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bohdi-Qwen2.5-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bohdi-Qwen2.5-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bohdi-Qwen2.5-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bohdi-Qwen2.5-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bohdi-Qwen2.5-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bohdi-Qwen2.5-7B-Instruct.IQ4_XS.gguf b/Bohdi-Qwen2.5-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..4f5c1da --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3c41a16c7f265ed24d09388c07597a719dd3b81cbcb46c096e42775cde635e0 +size 4250298784 diff --git a/Bohdi-Qwen2.5-7B-Instruct.Q2_K.gguf b/Bohdi-Qwen2.5-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..5f9b626 --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d9b9a79346ce2870b7701d3f87ce4ba8e7b2d47388e3d04ed7ea4ecbfac9cf2 +size 3015940512 diff --git a/Bohdi-Qwen2.5-7B-Instruct.Q3_K_L.gguf b/Bohdi-Qwen2.5-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..c4ec616 --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f888c4e77e2b7a27b01249e81cde25edb822ebce3d83e9a6736ee74f0645d4e7 +size 4088459680 diff --git a/Bohdi-Qwen2.5-7B-Instruct.Q3_K_M.gguf b/Bohdi-Qwen2.5-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..80b610b --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e525ed40cb071bd1903c0cbf49627833ace9eb78410040c24e4a027733b532b +size 3808391584 diff --git a/Bohdi-Qwen2.5-7B-Instruct.Q3_K_S.gguf b/Bohdi-Qwen2.5-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..90c4c02 --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:847b881409f1f697010e794e1c17263f22a3af2991681ad4976500276af519d0 +size 3492368800 diff --git a/Bohdi-Qwen2.5-7B-Instruct.Q4_K_M.gguf b/Bohdi-Qwen2.5-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..55ab98d --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a430a3619bf4f692457d44af0808ceea91f18ffed16a72e66480b5fa58b28ac7 +size 4683073952 diff --git a/Bohdi-Qwen2.5-7B-Instruct.Q4_K_S.gguf b/Bohdi-Qwen2.5-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..1eb974c --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81fc40ff32fb252b37f71f1addcf6476573d4764d2bf58597e5db1d92d60414d +size 4457769376 diff --git a/Bohdi-Qwen2.5-7B-Instruct.Q5_K_M.gguf b/Bohdi-Qwen2.5-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..7d65c10 --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2718b003e9ec8bc196d46d1217311ab7e9641879e427253e7e3d027f0cd428f5 +size 5444831648 diff --git a/Bohdi-Qwen2.5-7B-Instruct.Q5_K_S.gguf b/Bohdi-Qwen2.5-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..be88035 --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc9a085e87e1b05db0b4e56e9f57d460f4f291373e7fca7cb3ac975dd6db275d +size 5315176864 diff --git a/Bohdi-Qwen2.5-7B-Instruct.Q6_K.gguf b/Bohdi-Qwen2.5-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..2b3dc64 --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6855cc048f77fa98af9afdeb2fa93dc0dc510376a791fb53e98b7cd7f9a55e2 +size 6254199200 diff --git a/Bohdi-Qwen2.5-7B-Instruct.Q8_0.gguf b/Bohdi-Qwen2.5-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..19835cc --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f49a876a5421cee810d55070528cf41f182a9303672d23aa06af4374763ddc7 +size 8098525600 diff --git a/Bohdi-Qwen2.5-7B-Instruct.f16.gguf b/Bohdi-Qwen2.5-7B-Instruct.f16.gguf new file mode 100644 index 0000000..1176133 --- /dev/null +++ b/Bohdi-Qwen2.5-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:425c17c712b1c1506d784a6f8fa580f69bf8ec97c1e901357c2a053c91fff749 +size 15237853600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..89d535e --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: ChetKao/Bohdi-Qwen2.5-7B-Instruct +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ChetKao/Bohdi-Qwen2.5-7B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-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/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Bohdi-Qwen2.5-7B-Instruct-GGUF/resolve/main/Bohdi-Qwen2.5-7B-Instruct.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. + +