commit 397b1a853bbbff641167943a7bca3286dd63080e Author: ModelHub XC Date: Tue Jun 2 16:32:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..972cbe8 --- /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 +Qwen2.5-7B-Instruct-Lambda1.75-402.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Lambda1.75-402.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Lambda1.75-402.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Lambda1.75-402.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Lambda1.75-402.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Lambda1.75-402.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Lambda1.75-402.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Lambda1.75-402.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Lambda1.75-402.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.IQ4_XS.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.IQ4_XS.gguf new file mode 100644 index 0000000..ef63ebc --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7745cbc8a899a0aa2fcf86abf0e6ac16370b61546b86aebef77168248a94c4ee +size 4250298816 diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.Q2_K.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q2_K.gguf new file mode 100644 index 0000000..3283bc5 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f92bf54245b36d699065c7343fa97b8789cd039fb82698b336d9a60c0626c4 +size 3015940544 diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_L.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_L.gguf new file mode 100644 index 0000000..975e655 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee5b1021146d093ae8e00835e9b5b36c8f175be3d6462e26cb036dbecd9d216c +size 4088459712 diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_M.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_M.gguf new file mode 100644 index 0000000..576a06a --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ab7e0f36caec80bb6d9771b2e8fa7213a110856f542ce83abe54d354cf88d8e +size 3808391616 diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_S.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_S.gguf new file mode 100644 index 0000000..2718b0d --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1e982929b9140b9ae44604720930d13696e73691dd4ab27c6374e6b1df67a75 +size 3492368832 diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.Q4_K_M.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q4_K_M.gguf new file mode 100644 index 0000000..041d5e3 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60ca5af1cf98a1a90022ff89bc5e1f8fc65b95d4c14074d3186f6a968039cd25 +size 4683073984 diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.Q4_K_S.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q4_K_S.gguf new file mode 100644 index 0000000..e265071 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d4c437b19b36f2ca0e4df46af7a77da0f86599fed07dfc15fa4a9e917fd5834 +size 4457769408 diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.Q5_K_M.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q5_K_M.gguf new file mode 100644 index 0000000..d283383 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fe1547ef1813acb2ddcfcc666d00773008defccdda765d4fb8851d22b20e1bc +size 5444831680 diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.Q5_K_S.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q5_K_S.gguf new file mode 100644 index 0000000..39b8bab --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b077dfa715018de16a8f3c9db97f02501a7c80cfd9c65d2873a28e305b37dfb +size 5315176896 diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.Q6_K.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q6_K.gguf new file mode 100644 index 0000000..abf6958 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48e4fc7a5c372fbfbfafb48f37715b5549186a983d1393b0e9bb0679be27df24 +size 6254199232 diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.Q8_0.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q8_0.gguf new file mode 100644 index 0000000..9e2efac --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd02eb45cbadf7fe647fed5b0d14d485f1c451929ab68bdafa4604e7daa93990 +size 8098525632 diff --git a/Qwen2.5-7B-Instruct-Lambda1.75-402.f16.gguf b/Qwen2.5-7B-Instruct-Lambda1.75-402.f16.gguf new file mode 100644 index 0000000..69905d5 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Lambda1.75-402.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3fb377ce2774e581c94b4bc3e6c404b9a9f4143362a26ee5cfc2c286ad7f08e +size 15237853632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..760cd2b --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: rd211/Qwen2.5-7B-Instruct-Lambda1.75-402 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/rd211/Qwen2.5-7B-Instruct-Lambda1.75-402 + + +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/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Lambda1.75-402-GGUF/resolve/main/Qwen2.5-7B-Instruct-Lambda1.75-402.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. + +