commit 1b2ef22946e390366a7c22485b400b0f4f1a2e71 Author: ModelHub XC Date: Thu Oct 22 15:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GPT2XL-RLFC-24B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5483617 --- /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 +GPT2XL-RLFC-24B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GPT2XL-RLFC-24B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT2XL-RLFC-24B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GPT2XL-RLFC-24B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2XL-RLFC-24B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2XL-RLFC-24B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2XL-RLFC-24B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2XL-RLFC-24B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT2XL-RLFC-24B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT2XL-RLFC-24B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT2XL-RLFC-24B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GPT2XL-RLFC-24B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GPT2XL-RLFC-24B.IQ4_XS.gguf b/GPT2XL-RLFC-24B.IQ4_XS.gguf new file mode 100644 index 0000000..425bbcf --- /dev/null +++ b/GPT2XL-RLFC-24B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b6cb22eecd823b4afc26ef4a0edc316c4316db4df5fd622b3a2357a5bfbd0a +size 966708256 diff --git a/GPT2XL-RLFC-24B.Q2_K.gguf b/GPT2XL-RLFC-24B.Q2_K.gguf new file mode 100644 index 0000000..ec33e3f --- /dev/null +++ b/GPT2XL-RLFC-24B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e26f7a6ca2d789c8fd1ac085ba19c3e3750b3362a364cc7f280cd7994e3535d +size 907188256 diff --git a/GPT2XL-RLFC-24B.Q3_K_L.gguf b/GPT2XL-RLFC-24B.Q3_K_L.gguf new file mode 100644 index 0000000..bc6f81a --- /dev/null +++ b/GPT2XL-RLFC-24B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e314316744e88fe0a3bcb6241376a907008f3cc1ba87c2ac8872c348c8675312 +size 1103028256 diff --git a/GPT2XL-RLFC-24B.Q3_K_M.gguf b/GPT2XL-RLFC-24B.Q3_K_M.gguf new file mode 100644 index 0000000..32f966a --- /dev/null +++ b/GPT2XL-RLFC-24B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81679769616df8b1d1fa097f48e9706ad573c08b4893805f45d3b92078476d9e +size 1037748256 diff --git a/GPT2XL-RLFC-24B.Q3_K_S.gguf b/GPT2XL-RLFC-24B.Q3_K_S.gguf new file mode 100644 index 0000000..3272ac0 --- /dev/null +++ b/GPT2XL-RLFC-24B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4af575e5e160abbcac3881edca6cd33ca1113961571b575411c49222c82f439f +size 907188256 diff --git a/GPT2XL-RLFC-24B.Q4_K_M.gguf b/GPT2XL-RLFC-24B.Q4_K_M.gguf new file mode 100644 index 0000000..84b3629 --- /dev/null +++ b/GPT2XL-RLFC-24B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aba08c7fe23bd0139ef693b7f151825220ebeb53a0f8c6bb3f3733a1a56efa8 +size 1191799648 diff --git a/GPT2XL-RLFC-24B.Q4_K_S.gguf b/GPT2XL-RLFC-24B.Q4_K_S.gguf new file mode 100644 index 0000000..b1894f3 --- /dev/null +++ b/GPT2XL-RLFC-24B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afab31491e74f5c6a7a3d82e2e73cc7c7babf20e2f2a10ea1fcb8168d3e0c5d9 +size 1113079648 diff --git a/GPT2XL-RLFC-24B.Q5_K_M.gguf b/GPT2XL-RLFC-24B.Q5_K_M.gguf new file mode 100644 index 0000000..e0ed28b --- /dev/null +++ b/GPT2XL-RLFC-24B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d8c9186566838603e53f53e40c1969c968c7499db6bdacd2cee1a2c99b1c44 +size 1381145344 diff --git a/GPT2XL-RLFC-24B.Q5_K_S.gguf b/GPT2XL-RLFC-24B.Q5_K_S.gguf new file mode 100644 index 0000000..a6406e9 --- /dev/null +++ b/GPT2XL-RLFC-24B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed07481d176db4c7cf1adfec9a423db9aa0a6c0ccc8f69e3494b565c77a05a32 +size 1233305344 diff --git a/GPT2XL-RLFC-24B.Q6_K.gguf b/GPT2XL-RLFC-24B.Q6_K.gguf new file mode 100644 index 0000000..4ecfebc --- /dev/null +++ b/GPT2XL-RLFC-24B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ec2454ee0a6d728b9109a172e73a910711a33e9995626ab5dacf995f93e24d +size 1630913856 diff --git a/GPT2XL-RLFC-24B.Q8_0.gguf b/GPT2XL-RLFC-24B.Q8_0.gguf new file mode 100644 index 0000000..ce56b9f --- /dev/null +++ b/GPT2XL-RLFC-24B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:352f9ae0ff176801423ceb5053790827f43d9cc3ae34402cb0799a6e4357bda1 +size 1749953856 diff --git a/GPT2XL-RLFC-24B.f16.gguf b/GPT2XL-RLFC-24B.f16.gguf new file mode 100644 index 0000000..670a6c4 --- /dev/null +++ b/GPT2XL-RLFC-24B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0122cd6f6fdf88f538550e56173055fd055b78b1efc1b2d124800e6466d96ae +size 3283124800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..79cb084 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: migueldeguzmandev/GPT2XL-RLFC-24B +language: +- en +library_name: transformers +license: bigscience-openrail-m +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/migueldeguzmandev/GPT2XL-RLFC-24B + + +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/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.Q2_K.gguf) | Q2_K | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.Q5_K_M.gguf) | Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.Q8_0.gguf) | Q8_0 | 1.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GPT2XL-RLFC-24B-GGUF/resolve/main/GPT2XL-RLFC-24B.f16.gguf) | f16 | 3.4 | 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. + +