commit 87ef8ea95e39d789ccbf36d8c3e77189874f34c0 Author: ModelHub XC Date: Thu Jul 23 19:13:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Palembang-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1ebea82 --- /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-Palembang.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Palembang.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Palembang.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Palembang.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Palembang.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Palembang.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Palembang.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Palembang.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Palembang.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Palembang.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Palembang.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Palembang.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Palembang.IQ4_XS.gguf b/Llama-3-Palembang.IQ4_XS.gguf new file mode 100644 index 0000000..606ba15 --- /dev/null +++ b/Llama-3-Palembang.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc617195add3940a13a77bd0b994eee452ac3299183628edda8ae6ab48f0d948 +size 4484362880 diff --git a/Llama-3-Palembang.Q2_K.gguf b/Llama-3-Palembang.Q2_K.gguf new file mode 100644 index 0000000..50d1489 --- /dev/null +++ b/Llama-3-Palembang.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d3cb97484dc904e7f976d70e3ca46dd11c29aeb7a9d0021856d4a9d59a3bb0f +size 3179131520 diff --git a/Llama-3-Palembang.Q3_K_L.gguf b/Llama-3-Palembang.Q3_K_L.gguf new file mode 100644 index 0000000..88bcef6 --- /dev/null +++ b/Llama-3-Palembang.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f89215444fb83cde41761424fa87307a7ed7f95890a1617dd5261b1cdf928f +size 4321956480 diff --git a/Llama-3-Palembang.Q3_K_M.gguf b/Llama-3-Palembang.Q3_K_M.gguf new file mode 100644 index 0000000..83c83d9 --- /dev/null +++ b/Llama-3-Palembang.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d395bd20f03cce4fd493b415274c8a48dae53df8c1dac8be73eac61f8cd880 +size 4018918016 diff --git a/Llama-3-Palembang.Q3_K_S.gguf b/Llama-3-Palembang.Q3_K_S.gguf new file mode 100644 index 0000000..8145db8 --- /dev/null +++ b/Llama-3-Palembang.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d2f7eee8b496e323642a2852952b1b1e62234ea67bbe80a5dc03c457c8b9f2 +size 3664499328 diff --git a/Llama-3-Palembang.Q4_K_M.gguf b/Llama-3-Palembang.Q4_K_M.gguf new file mode 100644 index 0000000..21013af --- /dev/null +++ b/Llama-3-Palembang.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:455956602b5ea3e8af70f8a530887a68a2a74e2712c6a35cf48b69c0a647ab5c +size 4920734336 diff --git a/Llama-3-Palembang.Q4_K_S.gguf b/Llama-3-Palembang.Q4_K_S.gguf new file mode 100644 index 0000000..b27576d --- /dev/null +++ b/Llama-3-Palembang.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e09e50064c9be197404ec94b81a8f22806f48eb440b64fee4b862de4ba1b3c26 +size 4692669056 diff --git a/Llama-3-Palembang.Q5_K_M.gguf b/Llama-3-Palembang.Q5_K_M.gguf new file mode 100644 index 0000000..dd4809b --- /dev/null +++ b/Llama-3-Palembang.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6301197d260616da02efca75705c92b231b56d54e5184160638013f4bcd87f1b +size 5732987520 diff --git a/Llama-3-Palembang.Q5_K_S.gguf b/Llama-3-Palembang.Q5_K_S.gguf new file mode 100644 index 0000000..3297191 --- /dev/null +++ b/Llama-3-Palembang.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2e545bc6496c0830ee87bdf3af95e90a14997ad7eb309c9bdf4069b98c030d7 +size 5599294080 diff --git a/Llama-3-Palembang.Q6_K.gguf b/Llama-3-Palembang.Q6_K.gguf new file mode 100644 index 0000000..ad5f7d2 --- /dev/null +++ b/Llama-3-Palembang.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88a7bee728788a39a4ad11db91e5225e696674f3b985234526ac135a0577d8e2 +size 6596006528 diff --git a/Llama-3-Palembang.Q8_0.gguf b/Llama-3-Palembang.Q8_0.gguf new file mode 100644 index 0000000..14a7240 --- /dev/null +++ b/Llama-3-Palembang.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:363d67d53ed555a799b27999a5c3a4203d768f6e1ba04be6e89b9b95b35b7f18 +size 8540770944 diff --git a/Llama-3-Palembang.f16.gguf b/Llama-3-Palembang.f16.gguf new file mode 100644 index 0000000..4065f3f --- /dev/null +++ b/Llama-3-Palembang.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d1706f2aebee8e6043496cadf17f02327c707b9a9fd13123f7c50e61b6757a0 +size 16068891264 diff --git a/README.md b/README.md new file mode 100644 index 0000000..855f5cc --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: nibih/Llama-3-Palembang +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/nibih/Llama-3-Palembang + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-Palembang-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/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Palembang-GGUF/resolve/main/Llama-3-Palembang.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. + +