commit 6d4dda8f37e5b0902fef999a93f3dd34a2eedefa Author: ModelHub XC Date: Fri Jun 26 11:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LightGPT-13B-Llama2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0bed4ae --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LightGPT-13B-Llama2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LightGPT-13B-Llama2.i1-IQ1_M.gguf b/LightGPT-13B-Llama2.i1-IQ1_M.gguf new file mode 100644 index 0000000..d0ad021 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad0b8503ec8e8a13c97dd6caf2dcb702f1882fc7352b20c64b73bc5697f1b2b +size 3138610272 diff --git a/LightGPT-13B-Llama2.i1-IQ1_S.gguf b/LightGPT-13B-Llama2.i1-IQ1_S.gguf new file mode 100644 index 0000000..112c878 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42e8c8e7f3f6366cfff4abd1b4cdd73b5ce04e50036eaf7a63eccc169e6806b4 +size 2898687072 diff --git a/LightGPT-13B-Llama2.i1-IQ2_M.gguf b/LightGPT-13B-Llama2.i1-IQ2_M.gguf new file mode 100644 index 0000000..a9be383 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27952915466692984363c4d503ad3f79adced350bf32b53aa57cd3d774966788 +size 4517579872 diff --git a/LightGPT-13B-Llama2.i1-IQ2_S.gguf b/LightGPT-13B-Llama2.i1-IQ2_S.gguf new file mode 100644 index 0000000..4e787c3 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41094b75b95c5c5e68f98cb47719530980a5c6886b2cd75b9fe5aec118b34508 +size 4197682272 diff --git a/LightGPT-13B-Llama2.i1-IQ2_XS.gguf b/LightGPT-13B-Llama2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..60968bd --- /dev/null +++ b/LightGPT-13B-Llama2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86b2ded6cdd1940c87df9bf38a36303e1b30141ab5ddcb46066187ae068ff8f +size 3891147872 diff --git a/LightGPT-13B-Llama2.i1-IQ2_XXS.gguf b/LightGPT-13B-Llama2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..06816a2 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d7b79e973f2b68de747096d5c2c84fd0dd7c8def33a51f25019103ac9403871 +size 3538482272 diff --git a/LightGPT-13B-Llama2.i1-IQ3_M.gguf b/LightGPT-13B-Llama2.i1-IQ3_M.gguf new file mode 100644 index 0000000..54f5f72 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19c43bcf6953e796abeb0d0c377aa3f3c22540100bf908ae2209a33ba2191ca0 +size 5984511072 diff --git a/LightGPT-13B-Llama2.i1-IQ3_S.gguf b/LightGPT-13B-Llama2.i1-IQ3_S.gguf new file mode 100644 index 0000000..778cd26 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffcd5565d74ad42c1ef88e61b8c8c028ec44c344b7137ab0e03b36fecd0f2787 +size 5658981472 diff --git a/LightGPT-13B-Llama2.i1-IQ3_XS.gguf b/LightGPT-13B-Llama2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..fe65ff4 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e5fba061d54073d48e14132a8975f2f7539110f8ed916e6796e5ee6b97779e +size 5361611872 diff --git a/LightGPT-13B-Llama2.i1-IQ3_XXS.gguf b/LightGPT-13B-Llama2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..9a73448 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:139f8b2c73e1d9209de6e667dcb8608f0a9e9bef65424a308d35aea6539b9454 +size 4960562272 diff --git a/LightGPT-13B-Llama2.i1-IQ4_XS.gguf b/LightGPT-13B-Llama2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1975c32 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5420634fea7c7a708e3e66009b54cbb3c72f2076a73929d97d49764560f54a1 +size 6964223072 diff --git a/LightGPT-13B-Llama2.i1-Q2_K.gguf b/LightGPT-13B-Llama2.i1-Q2_K.gguf new file mode 100644 index 0000000..7192f48 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1a281ac3f3220abc287f877933370b2cdafbf980a980310586c3dc7f669972 +size 4854271072 diff --git a/LightGPT-13B-Llama2.i1-Q3_K_L.gguf b/LightGPT-13B-Llama2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ddcd864 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476cb4e29205be66c358c450ef3554df77d4dabdd4a8931d036aa7c721b3bf50 +size 6929560672 diff --git a/LightGPT-13B-Llama2.i1-Q3_K_M.gguf b/LightGPT-13B-Llama2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4794755 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350b3e9a6b77b170019aace5bbc000b3289624baeb46141eddac3e51aa64b824 +size 6337770592 diff --git a/LightGPT-13B-Llama2.i1-Q3_K_S.gguf b/LightGPT-13B-Llama2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b503038 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1342ac444d6ce15d5721fcee35293b9ee0493f31f007589a7ad0e789ec952635 +size 5658981472 diff --git a/LightGPT-13B-Llama2.i1-Q4_0.gguf b/LightGPT-13B-Llama2.i1-Q4_0.gguf new file mode 100644 index 0000000..df1baad --- /dev/null +++ b/LightGPT-13B-Llama2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ad0fe753ed34626a3c50db69194a98bb4c264edd215885ab7ccef7f312e669 +size 7387954272 diff --git a/LightGPT-13B-Llama2.i1-Q4_K_M.gguf b/LightGPT-13B-Llama2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..cce00ef --- /dev/null +++ b/LightGPT-13B-Llama2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c5fa74b3e2f7022ba66a4934472719ef1ce9de730c8b1ac0a2ec7d17faaa56 +size 7865957472 diff --git a/LightGPT-13B-Llama2.i1-Q4_K_S.gguf b/LightGPT-13B-Llama2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..dead024 --- /dev/null +++ b/LightGPT-13B-Llama2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f4bf1ff9e66281e95026a58b2800dfbe4c08ede21da9234b2aa99a2ea1cd68b +size 7423179872 diff --git a/LightGPT-13B-Llama2.i1-Q5_K_M.gguf b/LightGPT-13B-Llama2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7ff51fb --- /dev/null +++ b/LightGPT-13B-Llama2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c9a11c93cf74c2bb5f11a84eee1a1368bd0276625f4eac3c0a03e91d76c8672 +size 9229925472 diff --git a/LightGPT-13B-Llama2.i1-Q5_K_S.gguf b/LightGPT-13B-Llama2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6ab25ea --- /dev/null +++ b/LightGPT-13B-Llama2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5da6e14bb9ba12e5b3ac71e9c23a27c7d0fc78665ca9a746d8ea2543f50123 +size 8972287072 diff --git a/LightGPT-13B-Llama2.i1-Q6_K.gguf b/LightGPT-13B-Llama2.i1-Q6_K.gguf new file mode 100644 index 0000000..381a6cc --- /dev/null +++ b/LightGPT-13B-Llama2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31ca328dafcc66924207377f0bea49ea55c38b342598fc2e28c8c2527fdf4035 +size 10679141472 diff --git a/README.md b/README.md new file mode 100644 index 0000000..39fb3f0 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: lightgpt/LightGPT-13B-Llama2 +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 + + + + + + +weighted/imatrix quants of https://huggingface.co/lightgpt/LightGPT-13B-Llama2 + + +static quants are available at https://huggingface.co/mradermacher/LightGPT-13B-Llama2-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-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-IQ1_S.gguf) | i1-IQ1_S | 3.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-IQ1_M.gguf) | i1-IQ1_M | 3.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-IQ2_S.gguf) | i1-IQ2_S | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-IQ2_M.gguf) | i1-IQ2_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-IQ3_S.gguf) | i1-IQ3_S | 5.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-IQ3_M.gguf) | i1-IQ3_M | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-Q4_0.gguf) | i1-Q4_0 | 7.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.3 | | +| [GGUF](https://huggingface.co/mradermacher/LightGPT-13B-Llama2-i1-GGUF/resolve/main/LightGPT-13B-Llama2.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..f584bb8 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa9c46cb51cd1d06b3584ac6b431bc33a4783a589c35ad0e651024e4ad20e8cd +size 7136325