commit 9005cc8621a8cc0b447945e79619a258bf01cac5 Author: ModelHub XC Date: Fri Sep 25 19:23:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RajLlama-3.1-8B-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f7ed40a --- /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 +RajLlama-3.1-8B-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RajLlama-3.1-8B-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RajLlama-3.1-8B-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +RajLlama-3.1-8B-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RajLlama-3.1-8B-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RajLlama-3.1-8B-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RajLlama-3.1-8B-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RajLlama-3.1-8B-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RajLlama-3.1-8B-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RajLlama-3.1-8B-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RajLlama-3.1-8B-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RajLlama-3.1-8B-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d6348ef --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: rm8630/RajLlama-3.1-8B-v2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/rm8630/RajLlama-3.1-8B-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#RajLlama-3.1-8B-v2-GGUF).*** + +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/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RajLlama-3.1-8B-v2-GGUF/resolve/main/RajLlama-3.1-8B-v2.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. + + diff --git a/RajLlama-3.1-8B-v2.IQ4_XS.gguf b/RajLlama-3.1-8B-v2.IQ4_XS.gguf new file mode 100644 index 0000000..6bfed4f --- /dev/null +++ b/RajLlama-3.1-8B-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:602986a641110ac002e5271122ff11bf1ac5d24cb92eb78f04740469caf42185 +size 4484364064 diff --git a/RajLlama-3.1-8B-v2.Q2_K.gguf b/RajLlama-3.1-8B-v2.Q2_K.gguf new file mode 100644 index 0000000..33f0256 --- /dev/null +++ b/RajLlama-3.1-8B-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f789598566e4e4de6df60f2e42cbcc8b1c6bfd226c68243bf2f480156133dfc +size 3179132704 diff --git a/RajLlama-3.1-8B-v2.Q3_K_L.gguf b/RajLlama-3.1-8B-v2.Q3_K_L.gguf new file mode 100644 index 0000000..b27c613 --- /dev/null +++ b/RajLlama-3.1-8B-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54549ac3e362457e7d01f3e4455be1e0bcb24b0c3adf4a83ea55710adeac5c7e +size 4321957664 diff --git a/RajLlama-3.1-8B-v2.Q3_K_M.gguf b/RajLlama-3.1-8B-v2.Q3_K_M.gguf new file mode 100644 index 0000000..946dd9f --- /dev/null +++ b/RajLlama-3.1-8B-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ce69b9c2021d95b31cc2407560abb2f9868bf65dc40afb0e6dd0eaea0d83db +size 4018919200 diff --git a/RajLlama-3.1-8B-v2.Q3_K_S.gguf b/RajLlama-3.1-8B-v2.Q3_K_S.gguf new file mode 100644 index 0000000..69fbc09 --- /dev/null +++ b/RajLlama-3.1-8B-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e633d7a1d111d16490112d0ce2b2311d1013e865fe5f28fc5b50d87be0555b +size 3664500512 diff --git a/RajLlama-3.1-8B-v2.Q4_K_M.gguf b/RajLlama-3.1-8B-v2.Q4_K_M.gguf new file mode 100644 index 0000000..f958b32 --- /dev/null +++ b/RajLlama-3.1-8B-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ac9a12b8be288a2776f690a408b200fd77dc04e0ea43221cd8a46ab0629c98 +size 4920735520 diff --git a/RajLlama-3.1-8B-v2.Q4_K_S.gguf b/RajLlama-3.1-8B-v2.Q4_K_S.gguf new file mode 100644 index 0000000..6882aca --- /dev/null +++ b/RajLlama-3.1-8B-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdb3ebdec9f5832b4299e89df32f466748d7b05c0c792aac51b64477ae81c9a0 +size 4692670240 diff --git a/RajLlama-3.1-8B-v2.Q5_K_M.gguf b/RajLlama-3.1-8B-v2.Q5_K_M.gguf new file mode 100644 index 0000000..dda2938 --- /dev/null +++ b/RajLlama-3.1-8B-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed93a068fb0f3968286f11d18caee32f1a74127af3a08ae522332b7b1fa2f4b1 +size 5732988704 diff --git a/RajLlama-3.1-8B-v2.Q5_K_S.gguf b/RajLlama-3.1-8B-v2.Q5_K_S.gguf new file mode 100644 index 0000000..612ee84 --- /dev/null +++ b/RajLlama-3.1-8B-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016916697d9ebc0ed4e72504ecf4719ea790334ed2f7eab40d5844e92c9861c6 +size 5599295264 diff --git a/RajLlama-3.1-8B-v2.Q6_K.gguf b/RajLlama-3.1-8B-v2.Q6_K.gguf new file mode 100644 index 0000000..9c86274 --- /dev/null +++ b/RajLlama-3.1-8B-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94c33bf1ef8ba8432a6ec051568eee27b4ddf31d1a3c509d041fdaed7497e652 +size 6596007712 diff --git a/RajLlama-3.1-8B-v2.Q8_0.gguf b/RajLlama-3.1-8B-v2.Q8_0.gguf new file mode 100644 index 0000000..4d1cb3d --- /dev/null +++ b/RajLlama-3.1-8B-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d31ced9ad63763f8f166e334e358abd8beea15ade3b9e421fde8de88a8a9c96b +size 8540772128 diff --git a/RajLlama-3.1-8B-v2.f16.gguf b/RajLlama-3.1-8B-v2.f16.gguf new file mode 100644 index 0000000..03f207e --- /dev/null +++ b/RajLlama-3.1-8B-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c6c42fd5e5cd4e69ab2f88c18005ed1f73f116d4c4f9b27e007d3487f7a27bf +size 16068892448