commit bc39562cda9479a7cd126a8fdd8aa0249eaadda6 Author: ModelHub XC Date: Mon Jul 6 15:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-AFT-Off-Policy-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cdf410e --- /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 +Llama-AFT-Off-Policy.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-AFT-Off-Policy.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-AFT-Off-Policy.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-AFT-Off-Policy.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-AFT-Off-Policy.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-AFT-Off-Policy.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-AFT-Off-Policy.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-AFT-Off-Policy.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-AFT-Off-Policy.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-AFT-Off-Policy.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-AFT-Off-Policy.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-AFT-Off-Policy.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-AFT-Off-Policy.IQ4_XS.gguf b/Llama-AFT-Off-Policy.IQ4_XS.gguf new file mode 100644 index 0000000..1bd5e9a --- /dev/null +++ b/Llama-AFT-Off-Policy.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a42d957e568e2f61ae2701b5c9b921d188b887ea6dd147bceaec7f0af09fea04 +size 4484363744 diff --git a/Llama-AFT-Off-Policy.Q2_K.gguf b/Llama-AFT-Off-Policy.Q2_K.gguf new file mode 100644 index 0000000..0be2995 --- /dev/null +++ b/Llama-AFT-Off-Policy.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3eb899012dd240ca89d41e4a54bab73f6713eb49827261ff358a1da3755860c +size 3179132384 diff --git a/Llama-AFT-Off-Policy.Q3_K_L.gguf b/Llama-AFT-Off-Policy.Q3_K_L.gguf new file mode 100644 index 0000000..94b66b2 --- /dev/null +++ b/Llama-AFT-Off-Policy.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33153d92ff0f9bc521e2bbb795ac51d5a4907f7b10791cc9837692d4de542def +size 4321957344 diff --git a/Llama-AFT-Off-Policy.Q3_K_M.gguf b/Llama-AFT-Off-Policy.Q3_K_M.gguf new file mode 100644 index 0000000..ed3f053 --- /dev/null +++ b/Llama-AFT-Off-Policy.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bac8aca8872d0cb42ece3137b0607401e2bcd6831242b88cfee7727cc54e59bc +size 4018918880 diff --git a/Llama-AFT-Off-Policy.Q3_K_S.gguf b/Llama-AFT-Off-Policy.Q3_K_S.gguf new file mode 100644 index 0000000..0e72a3e --- /dev/null +++ b/Llama-AFT-Off-Policy.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b17a706ca15abcf9f87a92a517cdda2742354adc6c507cd71a722c464c291b0d +size 3664500192 diff --git a/Llama-AFT-Off-Policy.Q4_K_M.gguf b/Llama-AFT-Off-Policy.Q4_K_M.gguf new file mode 100644 index 0000000..c25c97f --- /dev/null +++ b/Llama-AFT-Off-Policy.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fcf7c42f51ca105e6528e4fb0b5672aef39cdff1381d001ccb98d203ae520bf +size 4920735200 diff --git a/Llama-AFT-Off-Policy.Q4_K_S.gguf b/Llama-AFT-Off-Policy.Q4_K_S.gguf new file mode 100644 index 0000000..4cfd6da --- /dev/null +++ b/Llama-AFT-Off-Policy.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a1ee4d027ac5d4d1b073460b1cd0fb2dacff363d266366e590ea6a4d1f6c89 +size 4692669920 diff --git a/Llama-AFT-Off-Policy.Q5_K_M.gguf b/Llama-AFT-Off-Policy.Q5_K_M.gguf new file mode 100644 index 0000000..44b3e11 --- /dev/null +++ b/Llama-AFT-Off-Policy.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d92b17ae33e704d01478460a7e65850700fe5cd22f4f69ebf0f15c80a157ba8 +size 5732988384 diff --git a/Llama-AFT-Off-Policy.Q5_K_S.gguf b/Llama-AFT-Off-Policy.Q5_K_S.gguf new file mode 100644 index 0000000..4505d08 --- /dev/null +++ b/Llama-AFT-Off-Policy.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e26e9ddfbe79efdd8a62c0b4583c1a3918c0eb0df1015a7f5434cba85ef214b1 +size 5599294944 diff --git a/Llama-AFT-Off-Policy.Q6_K.gguf b/Llama-AFT-Off-Policy.Q6_K.gguf new file mode 100644 index 0000000..1525012 --- /dev/null +++ b/Llama-AFT-Off-Policy.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac8c0136992a54d6d9a26b167f49faa720963292fa3367c6ad5d7529c96b562f +size 6596007392 diff --git a/Llama-AFT-Off-Policy.Q8_0.gguf b/Llama-AFT-Off-Policy.Q8_0.gguf new file mode 100644 index 0000000..6861098 --- /dev/null +++ b/Llama-AFT-Off-Policy.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a53cd6536f1aaffdcf15a230b96d2d09016897792513b49864016c1ce9432ff4 +size 8540771808 diff --git a/Llama-AFT-Off-Policy.f16.gguf b/Llama-AFT-Off-Policy.f16.gguf new file mode 100644 index 0000000..123da36 --- /dev/null +++ b/Llama-AFT-Off-Policy.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d84ab39b212ee7df979ff4e36e82d6684cdb08042be7b48648c20f9dd5183231 +size 16068892128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a87dbb --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: linzw/Llama-AFT-Off-Policy +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/linzw/Llama-AFT-Off-Policy + + +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/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-AFT-Off-Policy-GGUF/resolve/main/Llama-AFT-Off-Policy.f16.gguf) | f16 | 16.2 | 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. + +