commit a7767fe2743d56cef4d404e3d48f03e71ef5d4dd Author: ModelHub XC Date: Tue Jun 2 16:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6be97be --- /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-3.1-8B-nicefellow-reflection-r2-chatml.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-nicefellow-reflection-r2-chatml.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-nicefellow-reflection-r2-chatml.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.IQ4_XS.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.IQ4_XS.gguf new file mode 100644 index 0000000..4744ee3 --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15cef5bd02cff1b035441896242f13761579687d9bf3778667bd574a88aadc23 +size 4484363520 diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q2_K.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q2_K.gguf new file mode 100644 index 0000000..2407094 --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69eedcab6c1025118f3d56e056638ec407f4f982116a94c7455ff77d9fb64dda +size 3179132160 diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_L.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_L.gguf new file mode 100644 index 0000000..6c2c0e1 --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9375f64b6a465370294049541d955d3acc3523782dd96a58420df3460c5b6b30 +size 4321957120 diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_M.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_M.gguf new file mode 100644 index 0000000..021a59c --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba29188984861c8109f1bd9565f65613ff3c1ac5904c9debab414a6c3f561e48 +size 4018918656 diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_S.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_S.gguf new file mode 100644 index 0000000..bc5e928 --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e3c15f2096ea21810cd00adfff6b4f3d50afe399f252390181c5b6f444ed4c2 +size 3664499968 diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q4_K_M.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q4_K_M.gguf new file mode 100644 index 0000000..e6fbda2 --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:218ddd6cfcc49271471cb2dab751415c3b233d27b6bf43ce5317cd072efbca54 +size 4920734976 diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q4_K_S.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q4_K_S.gguf new file mode 100644 index 0000000..82d78f7 --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f37a85291a6056bf06ddd52e88a799ff7467518eeee1c34b791a1696ec3ae80e +size 4692669696 diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q5_K_M.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q5_K_M.gguf new file mode 100644 index 0000000..b2d38a5 --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be68a761ab4e8a5866850e7e318b8588b65fc9212569e193f55645f28c2c319 +size 5732988160 diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q5_K_S.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q5_K_S.gguf new file mode 100644 index 0000000..c792660 --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:626fdee0fa7deb410a491929638576b38a65a943bf525b93e56e03a6a9a52526 +size 5599294720 diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q6_K.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q6_K.gguf new file mode 100644 index 0000000..afc9c90 --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04633ef218cdca765906ab149759b2e80f5785ce4fdcf29e5e77c372c74df1de +size 6596007168 diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q8_0.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q8_0.gguf new file mode 100644 index 0000000..f3c4651 --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:269959c8d75c19433ae3235f410a2d56a5585c4f1d2631ff558aa885e861d00d +size 8540771584 diff --git a/Llama-3.1-8B-nicefellow-reflection-r2-chatml.f16.gguf b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.f16.gguf new file mode 100644 index 0000000..0e67853 --- /dev/null +++ b/Llama-3.1-8B-nicefellow-reflection-r2-chatml.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ae78401251a516955d7be0bace4cb6d0738364b51171e1f7b280735eaf1e16 +size 16068891904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..83e6082 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: DrNicefellow/Llama-3.1-8B-nicefellow-reflection-r2-chatml +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/DrNicefellow/Llama-3.1-8B-nicefellow-reflection-r2-chatml + + +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-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-nicefellow-reflection-r2-chatml-GGUF/resolve/main/Llama-3.1-8B-nicefellow-reflection-r2-chatml.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. + +