commit 4b102b96384c5e71a0301dc6aaf47257bcf723f9 Author: ModelHub XC Date: Tue Jun 2 16:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hemanth-llm-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1bf5cb6 --- /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 +Hemanth-llm.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemanth-llm.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hemanth-llm.f16.gguf filter=lfs diff=lfs merge=lfs -text +Hemanth-llm.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hemanth-llm.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hemanth-llm.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemanth-llm.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemanth-llm.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hemanth-llm.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemanth-llm.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemanth-llm.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemanth-llm.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hemanth-llm.IQ4_XS.gguf b/Hemanth-llm.IQ4_XS.gguf new file mode 100644 index 0000000..d9819fa --- /dev/null +++ b/Hemanth-llm.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af5bf0d7d083f2d95073e0e91051f7b0c6a34c5a639adb2c661f264e68b85865 +size 3944389696 diff --git a/Hemanth-llm.Q2_K.gguf b/Hemanth-llm.Q2_K.gguf new file mode 100644 index 0000000..83d60aa --- /dev/null +++ b/Hemanth-llm.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8be6899ee6f54ac806bc82fbf6d97165d883024048d047e72910fd12fed640be +size 2719243328 diff --git a/Hemanth-llm.Q3_K_L.gguf b/Hemanth-llm.Q3_K_L.gguf new file mode 100644 index 0000000..d183a22 --- /dev/null +++ b/Hemanth-llm.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd33e2d7a40786a3e42baf074d1b4d2490243040d3edbe70f373285397c36fc5 +size 3822025792 diff --git a/Hemanth-llm.Q3_K_M.gguf b/Hemanth-llm.Q3_K_M.gguf new file mode 100644 index 0000000..13c06cd --- /dev/null +++ b/Hemanth-llm.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dbd034c0db6dcf370a52069ba5bdd8f2114305e0503be1550ce86de2e003e28 +size 3518987328 diff --git a/Hemanth-llm.Q3_K_S.gguf b/Hemanth-llm.Q3_K_S.gguf new file mode 100644 index 0000000..9185338 --- /dev/null +++ b/Hemanth-llm.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6bb75b8a96e9ddb72b8e44430da1990fe0e01f17ac515e80e10774f3c1c331 +size 3164568640 diff --git a/Hemanth-llm.Q4_K_M.gguf b/Hemanth-llm.Q4_K_M.gguf new file mode 100644 index 0000000..5171478 --- /dev/null +++ b/Hemanth-llm.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49843761e09f4212e2abe63570d1f295303d303dec31e6c6fed745fe57981274 +size 4368440384 diff --git a/Hemanth-llm.Q4_K_S.gguf b/Hemanth-llm.Q4_K_S.gguf new file mode 100644 index 0000000..4481a81 --- /dev/null +++ b/Hemanth-llm.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28983ce721bec71cd2d8aa492082ec9af85866381d0143ae6b9301014ec56a7c +size 4140375104 diff --git a/Hemanth-llm.Q5_K_M.gguf b/Hemanth-llm.Q5_K_M.gguf new file mode 100644 index 0000000..c2060db --- /dev/null +++ b/Hemanth-llm.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc6da07095d15b77eeea0f291735f3a1389485024af4908b8a91c4a0cbc1b41 +size 5131410496 diff --git a/Hemanth-llm.Q5_K_S.gguf b/Hemanth-llm.Q5_K_S.gguf new file mode 100644 index 0000000..e3e30b4 --- /dev/null +++ b/Hemanth-llm.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7a4ada18f435fc51d018456f48ea9c08897a5579aa41fc91c3530e22df62741 +size 4997717056 diff --git a/Hemanth-llm.Q6_K.gguf b/Hemanth-llm.Q6_K.gguf new file mode 100644 index 0000000..1860d84 --- /dev/null +++ b/Hemanth-llm.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ed7fd9ef3ea991a5ee58c1ac3b3b17518048461b86508e2d12679d7c65d6d8 +size 5942066240 diff --git a/Hemanth-llm.Q8_0.gguf b/Hemanth-llm.Q8_0.gguf new file mode 100644 index 0000000..ff9c39c --- /dev/null +++ b/Hemanth-llm.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4545c06ed6cbae95bcddbd6bbea407782d3a920ac15a6266645b5191589a95aa +size 7695858752 diff --git a/Hemanth-llm.f16.gguf b/Hemanth-llm.f16.gguf new file mode 100644 index 0000000..1191eb8 --- /dev/null +++ b/Hemanth-llm.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0d4473494a78b221c28bc83773b03bf992c1ab658cb4d5018425d4174dbe9b +size 14484732992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0061ee7 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Kumar955/Hemanth-llm +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- udkai/Turdus +- flemmingmiguel/MBX-7B +--- +## About + + + + + + +static quants of https://huggingface.co/Kumar955/Hemanth-llm + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hemanth-llm-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/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hemanth-llm-GGUF/resolve/main/Hemanth-llm.f16.gguf) | f16 | 14.6 | 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. + +