commit b9a285d8b77c00939bbab96ec30c1cda7b514978 Author: ModelHub XC Date: Thu Sep 3 02:30:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8344ba1 --- /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 +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_M.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_M.gguf new file mode 100644 index 0000000..126f956 --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c017ddbbce75091a639d56bf11e0ea33f89fd72e6fc2ea5a42d5154ec62bb9a7 +size 3784828448 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_S.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_S.gguf new file mode 100644 index 0000000..781673f --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42c225196461d72fe2262f5e72376af5fba3065e34c9be2e0c0feff0b476b883 +size 3682330144 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_XS.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_XS.gguf new file mode 100644 index 0000000..08a11df --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f37cc7eafb68e9025d36720702febd5127f4b006798e563e6d238d66e027381 +size 3518752288 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ4_XS.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..b812cfa --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04091874af707a452bf3e170c0c7b4ec52325b699da347a4c5206ea562abba8d +size 4484367904 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q2_K.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..ccc3b33 --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0efa23c70f881fd3091985013d72ac14e712d4c0c65e6fbde9bcf89f2c45b1 +size 3179136544 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_L.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..3b8660b --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c2be62b9aed74b645c293be953820d052f45d7f2ecdee720b20febd4c6a960e +size 4321961504 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_M.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..8c11419 --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed2dd45f963b588417253c2241d5d1c164bea63f6a0115f53dcbe8821be44b4c +size 4018923040 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_S.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..c7f3441 --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:807324ee7c8d3f18bac0cc2aae3de2512283e8dc6b67dd6cf40d1c5442b33af9 +size 3664504352 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q4_K_M.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..6a5a673 --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e629b365dd99ac60e45fbbd8740a9bd813e393bd5668d14c73046c74cb314795 +size 4920739360 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q4_K_S.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..58d397f --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:284560f929d49151e377b1eb1007d33c712ccd812e510d726b7a427ecd4a83da +size 4692674080 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q5_K_M.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..4c49a7e --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f404c660a3ef5b806e8e8d84fa47d6a0939adfb6be18f671052fe4478090fb24 +size 5732992544 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q5_K_S.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..2ca2138 --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d68577735f8390551178fe16aa683f47213c02f314975d83e1f82547c7eb6ec +size 5599299104 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q6_K.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..2bfd32e --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca83a707e68a3b02e511900a4da9d4853afc2e5702e7ee50e41783b947342255 +size 6596011552 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q8_0.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..33a0cf1 --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21be2bbabdac17c9029294ee38ae829074adfcfa64d27e20b0909e800ceab81e +size 8540775968 diff --git a/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.f16.gguf b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.f16.gguf new file mode 100644 index 0000000..b166305 --- /dev/null +++ b/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3db13ab468783b57dd0868c8633721b65a6e12d2615060880f60e4fbbea6497 +size 16068896288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..059aab4 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: chheplo/Dhenu2-India-2.1-Llama-3.1-8B-Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/chheplo/Dhenu2-India-2.1-Llama-3.1-8B-Instruct + + +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/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Dhenu2-India-2.1-Llama-3.1-8B-Instruct-GGUF/resolve/main/Dhenu2-India-2.1-Llama-3.1-8B-Instruct.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. + +