commit 7dac85dd47a72ce837ea68aa230e9dc42b0b97dd Author: ModelHub XC Date: Sun Aug 9 18:37:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-indotuned-v0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5e2f8c6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-indotuned-v0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-indotuned-v0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b2a0bb2 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: NekoFi/llama-3-indotuned-v0 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + +static quants of https://huggingface.co/NekoFi/llama-3-indotuned-v0 + + +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-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-indotuned-v0-GGUF/resolve/main/llama-3-indotuned-v0.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/llama-3-indotuned-v0.IQ3_M.gguf b/llama-3-indotuned-v0.IQ3_M.gguf new file mode 100644 index 0000000..f74e3d1 --- /dev/null +++ b/llama-3-indotuned-v0.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6753ce652a554439f808d9e151dd6cb43a53cd326e591cd601162b2dd993e03 +size 3785335680 diff --git a/llama-3-indotuned-v0.IQ3_S.gguf b/llama-3-indotuned-v0.IQ3_S.gguf new file mode 100644 index 0000000..7834d06 --- /dev/null +++ b/llama-3-indotuned-v0.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0083e6c0e7165ea8771d20f5b65cf602370430c81821468b2aec8f25e4b50bb3 +size 3682837376 diff --git a/llama-3-indotuned-v0.IQ3_XS.gguf b/llama-3-indotuned-v0.IQ3_XS.gguf new file mode 100644 index 0000000..b8c4754 --- /dev/null +++ b/llama-3-indotuned-v0.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c03f9565e1a1cf057cc89a1ee0d116e2cf528b6dd51722fff97d28993f8136c2 +size 3519259520 diff --git a/llama-3-indotuned-v0.IQ4_XS.gguf b/llama-3-indotuned-v0.IQ4_XS.gguf new file mode 100644 index 0000000..eb89c57 --- /dev/null +++ b/llama-3-indotuned-v0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92ac0b34c955f8c1099408d421da459c711248b6c1ee15212eb49b8e8cdad102 +size 4484875136 diff --git a/llama-3-indotuned-v0.Q2_K.gguf b/llama-3-indotuned-v0.Q2_K.gguf new file mode 100644 index 0000000..08b9f54 --- /dev/null +++ b/llama-3-indotuned-v0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f31ed238e656adb4e01d45bf7bd2d59e209899f1efdb891ca679c744f24138d8 +size 3179643776 diff --git a/llama-3-indotuned-v0.Q3_K_L.gguf b/llama-3-indotuned-v0.Q3_K_L.gguf new file mode 100644 index 0000000..90f6a79 --- /dev/null +++ b/llama-3-indotuned-v0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd68627832fa4302037daea1369497968a20ed386964b4656d309857f00c1aef +size 4322468736 diff --git a/llama-3-indotuned-v0.Q3_K_M.gguf b/llama-3-indotuned-v0.Q3_K_M.gguf new file mode 100644 index 0000000..54578bf --- /dev/null +++ b/llama-3-indotuned-v0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5fc077e928115757f7092cc07ea1c14d69db0e3146bbff28fc6248375f23a5c +size 4019430272 diff --git a/llama-3-indotuned-v0.Q3_K_S.gguf b/llama-3-indotuned-v0.Q3_K_S.gguf new file mode 100644 index 0000000..0af72fc --- /dev/null +++ b/llama-3-indotuned-v0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2483a2866e8542f449b643ac50325595663a6298d3992c3ce3dd91cd26911ad7 +size 3665011584 diff --git a/llama-3-indotuned-v0.Q4_K_M.gguf b/llama-3-indotuned-v0.Q4_K_M.gguf new file mode 100644 index 0000000..15fc9aa --- /dev/null +++ b/llama-3-indotuned-v0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdcdef28a4f52686075fd0ee114f614dd12058af31fc273ecc39f07f38a66514 +size 4921246592 diff --git a/llama-3-indotuned-v0.Q4_K_S.gguf b/llama-3-indotuned-v0.Q4_K_S.gguf new file mode 100644 index 0000000..c271063 --- /dev/null +++ b/llama-3-indotuned-v0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c1c1cbee05f057255e6cd7de6bd61d7126813ebff0eda571cbc33d9cd01f8a3 +size 4693181312 diff --git a/llama-3-indotuned-v0.Q5_K_M.gguf b/llama-3-indotuned-v0.Q5_K_M.gguf new file mode 100644 index 0000000..82003d2 --- /dev/null +++ b/llama-3-indotuned-v0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:648f2cf1568ec8b694815f1f6c8301b5ce2c50fef426eb4c1f621a853280c005 +size 5733499776 diff --git a/llama-3-indotuned-v0.Q5_K_S.gguf b/llama-3-indotuned-v0.Q5_K_S.gguf new file mode 100644 index 0000000..e55d5f2 --- /dev/null +++ b/llama-3-indotuned-v0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f19f6ae22a6fed70416391ef8acbc69f041a86a8f3279c4b7e7a6b581dbfd9e8 +size 5599806336 diff --git a/llama-3-indotuned-v0.Q6_K.gguf b/llama-3-indotuned-v0.Q6_K.gguf new file mode 100644 index 0000000..075209e --- /dev/null +++ b/llama-3-indotuned-v0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d40f578948105bf0e8074a78110347c95463d31b4bb3c02324b9980b862d971 +size 6596518784 diff --git a/llama-3-indotuned-v0.Q8_0.gguf b/llama-3-indotuned-v0.Q8_0.gguf new file mode 100644 index 0000000..c24c3f8 --- /dev/null +++ b/llama-3-indotuned-v0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6606a283846afae201210dcd2d5a1c4ae7dcfa7fac0f9d82a7d7339a5cc75784 +size 8541283200 diff --git a/llama-3-indotuned-v0.f16.gguf b/llama-3-indotuned-v0.f16.gguf new file mode 100644 index 0000000..c2dd6f3 --- /dev/null +++ b/llama-3-indotuned-v0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9f64fff451a719c671304b05ec471f8c785261d19cbf8e55347a6f4bb3ed145 +size 16069403520