commit 6f80a499c50ee72d700c7c7278bfb7bb7fe7f9ce Author: ModelHub XC Date: Fri Jun 26 11:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenHathi-7B-Hi-VLLM-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cf4917c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +OpenHathi-7B-Hi-VLLM.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.f16.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHathi-7B-Hi-VLLM.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenHathi-7B-Hi-VLLM.IQ4_XS.gguf b/OpenHathi-7B-Hi-VLLM.IQ4_XS.gguf new file mode 100644 index 0000000..5279d92 --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6761d25fc62146e6ff3c7a2affb8197b21430cd5d1f27eee4c038c982c01a51f +size 3736997504 diff --git a/OpenHathi-7B-Hi-VLLM.Q2_K.gguf b/OpenHathi-7B-Hi-VLLM.Q2_K.gguf new file mode 100644 index 0000000..91c8460 --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d3e7435dc5756e6215053bb402a7bb126fe7baf55d1b8a41679544df3e493fa +size 2608979584 diff --git a/OpenHathi-7B-Hi-VLLM.Q3_K_L.gguf b/OpenHathi-7B-Hi-VLLM.Q3_K_L.gguf new file mode 100644 index 0000000..e27798d --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da187fdc2f30a9371329e69ad62c04082ba320a6e1575a1e97f42e51ee6ceccb +size 3679909504 diff --git a/OpenHathi-7B-Hi-VLLM.Q3_K_M.gguf b/OpenHathi-7B-Hi-VLLM.Q3_K_M.gguf new file mode 100644 index 0000000..11eb100 --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d7fe3bf3c37f314bc23ae7a337e809757aab39e9f425d7d9bebed847291f59 +size 3380803200 diff --git a/OpenHathi-7B-Hi-VLLM.Q3_K_S.gguf b/OpenHathi-7B-Hi-VLLM.Q3_K_S.gguf new file mode 100644 index 0000000..1224d8b --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf27b44f53b66c6e582372f21c5a600230e96295e418aff15339912488899b07 +size 3031103104 diff --git a/OpenHathi-7B-Hi-VLLM.Q4_0_4_4.gguf b/OpenHathi-7B-Hi-VLLM.Q4_0_4_4.gguf new file mode 100644 index 0000000..5a979e5 --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dccca7ad388441907e42ab8d3f82a0bf29d6d10b3371554502571d592e7ef010 +size 3917344384 diff --git a/OpenHathi-7B-Hi-VLLM.Q4_K_M.gguf b/OpenHathi-7B-Hi-VLLM.Q4_K_M.gguf new file mode 100644 index 0000000..1d59d9d --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7776b38ad3398d6a5e56b829538f748d4073294cc76d47605a0cf3d804b2cae +size 4172541568 diff --git a/OpenHathi-7B-Hi-VLLM.Q4_K_S.gguf b/OpenHathi-7B-Hi-VLLM.Q4_K_S.gguf new file mode 100644 index 0000000..e5b6428 --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8a326156faa86b20ad493f5a37e8b3f414ef691da52e7365302dbe4d4f38eb3 +size 3948277376 diff --git a/OpenHathi-7B-Hi-VLLM.Q5_K_M.gguf b/OpenHathi-7B-Hi-VLLM.Q5_K_M.gguf new file mode 100644 index 0000000..a7f6de9 --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c342abfb8c959d7cf86d670cabd5643e37d67e9bc32bdcd7982e75e399a5709 +size 4882919040 diff --git a/OpenHathi-7B-Hi-VLLM.Q5_K_S.gguf b/OpenHathi-7B-Hi-VLLM.Q5_K_S.gguf new file mode 100644 index 0000000..d7faa0f --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f02308e44400bddd18e62bb8d33b22724e3b4ef5e4ea419fe04a6108ee0638 +size 4751453824 diff --git a/OpenHathi-7B-Hi-VLLM.Q6_K.gguf b/OpenHathi-7B-Hi-VLLM.Q6_K.gguf new file mode 100644 index 0000000..d1b6c81 --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61e0a91ee26cc9d2fc1e32858c382660483ffe0df4d8dfb08689d8ca6cbe90f2 +size 5637695104 diff --git a/OpenHathi-7B-Hi-VLLM.Q8_0.gguf b/OpenHathi-7B-Hi-VLLM.Q8_0.gguf new file mode 100644 index 0000000..4bb8e7d --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcfc17e56a974e2ae3f829f0fa4da52fe8e380c412201d5f3dcc2e0b7094498c +size 7301461632 diff --git a/OpenHathi-7B-Hi-VLLM.f16.gguf b/OpenHathi-7B-Hi-VLLM.f16.gguf new file mode 100644 index 0000000..d6fc750 --- /dev/null +++ b/OpenHathi-7B-Hi-VLLM.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b48243ec6c4b74d21b37656b850254b8b8aebda71311bd9fd6a0cef0a06fb6 +size 13741848192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7523bef --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: aryasuneesh/OpenHathi-7B-Hi-VLLM +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/aryasuneesh/OpenHathi-7B-Hi-VLLM + + +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/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.Q3_K_S.gguf) | Q3_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.Q3_K_L.gguf) | Q3_K_L | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.IQ4_XS.gguf) | IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.Q5_K_S.gguf) | Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.Q6_K.gguf) | Q6_K | 5.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHathi-7B-Hi-VLLM-GGUF/resolve/main/OpenHathi-7B-Hi-VLLM.f16.gguf) | f16 | 13.8 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +