commit 76d494e85e71fb7d604fcbf508ad49636130ef9c Author: ModelHub XC Date: Tue Jun 16 01:04:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PLLuM-4B-chat-2512-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f53db29 --- /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 +PLLuM-4B-chat-2512.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-chat-2512.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-chat-2512.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-chat-2512.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-chat-2512.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-chat-2512.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-chat-2512.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-chat-2512.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-chat-2512.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-chat-2512.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-chat-2512.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-chat-2512.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PLLuM-4B-chat-2512.IQ4_XS.gguf b/PLLuM-4B-chat-2512.IQ4_XS.gguf new file mode 100644 index 0000000..cac4c07 --- /dev/null +++ b/PLLuM-4B-chat-2512.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7c934da0d4df977c4fa2db5948dfdef85bdc5ff5285718035b48b16f5ea0187 +size 2279496032 diff --git a/PLLuM-4B-chat-2512.Q2_K.gguf b/PLLuM-4B-chat-2512.Q2_K.gguf new file mode 100644 index 0000000..d34db07 --- /dev/null +++ b/PLLuM-4B-chat-2512.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:293e3630dc8a97f0120361871a1d956b54c2ca7c08ba416bdf9b1d523073e126 +size 1729034592 diff --git a/PLLuM-4B-chat-2512.Q3_K_L.gguf b/PLLuM-4B-chat-2512.Q3_K_L.gguf new file mode 100644 index 0000000..beb514d --- /dev/null +++ b/PLLuM-4B-chat-2512.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d47c874f3314fcd3bda8bb0f6baa189e0869bfe8f8d02ce3e86b1e951f9ef6b +size 2235955552 diff --git a/PLLuM-4B-chat-2512.Q3_K_M.gguf b/PLLuM-4B-chat-2512.Q3_K_M.gguf new file mode 100644 index 0000000..107ba21 --- /dev/null +++ b/PLLuM-4B-chat-2512.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55d7e3bce4917487b15436d50e3d9aaa4e004be7b9f0e75ce9793aa6fba024ae +size 2098329952 diff --git a/PLLuM-4B-chat-2512.Q3_K_S.gguf b/PLLuM-4B-chat-2512.Q3_K_S.gguf new file mode 100644 index 0000000..40af003 --- /dev/null +++ b/PLLuM-4B-chat-2512.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f91b8a10cc987a756a7e0d6ad0e070b359aeeb91005bba47185e46858b1826d +size 1937234272 diff --git a/PLLuM-4B-chat-2512.Q4_K_M.gguf b/PLLuM-4B-chat-2512.Q4_K_M.gguf new file mode 100644 index 0000000..90f94a8 --- /dev/null +++ b/PLLuM-4B-chat-2512.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f492ce188e5240db0187e30ccf12d6c7f8d46d3bf5e04598253b8ebc22af8fa +size 2489764192 diff --git a/PLLuM-4B-chat-2512.Q4_K_S.gguf b/PLLuM-4B-chat-2512.Q4_K_S.gguf new file mode 100644 index 0000000..5bbb9a4 --- /dev/null +++ b/PLLuM-4B-chat-2512.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:843f1b639f24b5c44602f8ed531b477734ff4abc773b16680bdd865f4964bae2 +size 2377800032 diff --git a/PLLuM-4B-chat-2512.Q5_K_M.gguf b/PLLuM-4B-chat-2512.Q5_K_M.gguf new file mode 100644 index 0000000..a84198f --- /dev/null +++ b/PLLuM-4B-chat-2512.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8127703252c9191558a85a79f978707fe093e9aaaf7606ea5c049b5923888661 +size 2829568352 diff --git a/PLLuM-4B-chat-2512.Q5_K_S.gguf b/PLLuM-4B-chat-2512.Q5_K_S.gguf new file mode 100644 index 0000000..a3f1b44 --- /dev/null +++ b/PLLuM-4B-chat-2512.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f358349b34b3a234026dd9a42ec407125913a40f15d036eef095f1c2b2583eee +size 2764462432 diff --git a/PLLuM-4B-chat-2512.Q6_K.gguf b/PLLuM-4B-chat-2512.Q6_K.gguf new file mode 100644 index 0000000..ca273ef --- /dev/null +++ b/PLLuM-4B-chat-2512.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c671efa917ce652a5477bb788fd6fb4b6d9f6a46eaaa800c205bc666afeca86c +size 3190610272 diff --git a/PLLuM-4B-chat-2512.Q8_0.gguf b/PLLuM-4B-chat-2512.Q8_0.gguf new file mode 100644 index 0000000..b670f44 --- /dev/null +++ b/PLLuM-4B-chat-2512.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e04f27d284fc83d8664fcafc9d1f08bc74b562d7fe4fd9ef8045c6a35c61353 +size 4130234528 diff --git a/PLLuM-4B-chat-2512.f16.gguf b/PLLuM-4B-chat-2512.f16.gguf new file mode 100644 index 0000000..f852482 --- /dev/null +++ b/PLLuM-4B-chat-2512.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:930d7a8a3e24d2cf482de1cced1a2e563069e8e83a382d9d5b07ad7641eb34f0 +size 7767489728 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0ebf0e5 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: CYFRAGOVPL/PLLuM-4B-chat-2512 +language: +- pl +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/CYFRAGOVPL/PLLuM-4B-chat-2512 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PLLuM-4B-chat-2512-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-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/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-chat-2512-GGUF/resolve/main/PLLuM-4B-chat-2512.f16.gguf) | f16 | 7.9 | 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. + +