commit ee4aa8c24b2d5b49f1f549ccb8a2b75044481da5 Author: ModelHub XC Date: Fri Jun 26 11:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LightGPT-7B-Qwen2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2d0ae19 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +LightGPT-7B-Qwen2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.f16.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-7B-Qwen2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LightGPT-7B-Qwen2.IQ3_M.gguf b/LightGPT-7B-Qwen2.IQ3_M.gguf new file mode 100644 index 0000000..67e0cc7 --- /dev/null +++ b/LightGPT-7B-Qwen2.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11ce527f774ef95fe66460a0541b1c0540d06a1b795887593bc81d9cf4dee0b1 +size 3574010144 diff --git a/LightGPT-7B-Qwen2.IQ3_S.gguf b/LightGPT-7B-Qwen2.IQ3_S.gguf new file mode 100644 index 0000000..de375a3 --- /dev/null +++ b/LightGPT-7B-Qwen2.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8b6b9f7e537abdeac5613530788ade3e913f870cb170af4ba7368f0aadcdcb2 +size 3499190560 diff --git a/LightGPT-7B-Qwen2.IQ3_XS.gguf b/LightGPT-7B-Qwen2.IQ3_XS.gguf new file mode 100644 index 0000000..f4f2973 --- /dev/null +++ b/LightGPT-7B-Qwen2.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228b1548ad6f55dab2e6eaa652eca10d7253dfe73592a947fc194c4ef70bdc10 +size 3346254112 diff --git a/LightGPT-7B-Qwen2.IQ4_XS.gguf b/LightGPT-7B-Qwen2.IQ4_XS.gguf new file mode 100644 index 0000000..e3de60e --- /dev/null +++ b/LightGPT-7B-Qwen2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b082d83e83d286a07357f31ac08c18bde47ca7288f5ca2a38f2a9ceb25513736 +size 4250296608 diff --git a/LightGPT-7B-Qwen2.Q2_K.gguf b/LightGPT-7B-Qwen2.Q2_K.gguf new file mode 100644 index 0000000..ad285c6 --- /dev/null +++ b/LightGPT-7B-Qwen2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c397159bffe301ab50be5cc860c029455c338fba62714d319e8ce53eaea9331 +size 3015938336 diff --git a/LightGPT-7B-Qwen2.Q3_K_L.gguf b/LightGPT-7B-Qwen2.Q3_K_L.gguf new file mode 100644 index 0000000..289561f --- /dev/null +++ b/LightGPT-7B-Qwen2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af1aaac8abede28f950919a5a6e0343e7d2ecd427597cc8e7b7c553b5c37d9e1 +size 4088457504 diff --git a/LightGPT-7B-Qwen2.Q3_K_M.gguf b/LightGPT-7B-Qwen2.Q3_K_M.gguf new file mode 100644 index 0000000..d5bd505 --- /dev/null +++ b/LightGPT-7B-Qwen2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faa8f080704f72d67a104c440d3d44cdadf3ef70c886ad1f81c749720c37359a +size 3808389408 diff --git a/LightGPT-7B-Qwen2.Q3_K_S.gguf b/LightGPT-7B-Qwen2.Q3_K_S.gguf new file mode 100644 index 0000000..fff88f0 --- /dev/null +++ b/LightGPT-7B-Qwen2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66cea48c1eeb5727da12496a91918109e9cfbcb5caae2c530cff16d0593f07e0 +size 3492366624 diff --git a/LightGPT-7B-Qwen2.Q4_K_M.gguf b/LightGPT-7B-Qwen2.Q4_K_M.gguf new file mode 100644 index 0000000..5403aaa --- /dev/null +++ b/LightGPT-7B-Qwen2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3105aa30468251592d9904e9178becbb59996c0008040c8b2b6e1dcfe5f39a0 +size 4683071776 diff --git a/LightGPT-7B-Qwen2.Q4_K_S.gguf b/LightGPT-7B-Qwen2.Q4_K_S.gguf new file mode 100644 index 0000000..452c0f3 --- /dev/null +++ b/LightGPT-7B-Qwen2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:201f79c91b6f6cce5db3c470f58b848ee8e3a831d3a5152f5a38e839ccecf170 +size 4457767200 diff --git a/LightGPT-7B-Qwen2.Q5_K_M.gguf b/LightGPT-7B-Qwen2.Q5_K_M.gguf new file mode 100644 index 0000000..3210356 --- /dev/null +++ b/LightGPT-7B-Qwen2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb2702534453f3feecb84b235dfe93efc7dcdad9123e5a4a502079afab70623b +size 5444829472 diff --git a/LightGPT-7B-Qwen2.Q5_K_S.gguf b/LightGPT-7B-Qwen2.Q5_K_S.gguf new file mode 100644 index 0000000..658ccff --- /dev/null +++ b/LightGPT-7B-Qwen2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a8103bdc4c9de75917a0533f3753a28d1214590538388d153399f5b6482ac93 +size 5315174688 diff --git a/LightGPT-7B-Qwen2.Q6_K.gguf b/LightGPT-7B-Qwen2.Q6_K.gguf new file mode 100644 index 0000000..e96dc5b --- /dev/null +++ b/LightGPT-7B-Qwen2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a8298aebcb4d0cfa40563cdd192c8a037c4cf759f8c7222d79b09bcf7bb860 +size 6254197024 diff --git a/LightGPT-7B-Qwen2.Q8_0.gguf b/LightGPT-7B-Qwen2.Q8_0.gguf new file mode 100644 index 0000000..1d331fc --- /dev/null +++ b/LightGPT-7B-Qwen2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48c4bbd18752293fcd98381e351a891f8fe2816a9b44ebb7dc463258d16c5fa4 +size 8098523424 diff --git a/LightGPT-7B-Qwen2.f16.gguf b/LightGPT-7B-Qwen2.f16.gguf new file mode 100644 index 0000000..6b0b635 --- /dev/null +++ b/LightGPT-7B-Qwen2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f245a5556f2c2acb5427bffadacc9f28ac0934f695f87da35e687dec73ae6f2f +size 15237851424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b8aa4a2 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: lightgpt/LightGPT-7B-Qwen2 +extra_gated_heading: Access LLMLight-LightGPT on Hugging Face +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- pytorch +- llama-2 +- traffic signal control +- lightgpt +- llmlight +--- +## About + + + + + + +static quants of https://huggingface.co/lightgpt/LightGPT-7B-Qwen2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-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/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.IQ3_XS.gguf) | IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.IQ3_S.gguf) | IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.IQ3_M.gguf) | IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-7B-Qwen2-GGUF/resolve/main/LightGPT-7B-Qwen2.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. + +