commit 083f53cda72478151db17268a51970245a1de162 Author: ModelHub XC Date: Mon Jun 15 02:29:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Rahul-FineTunedLLM-v03-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a2b2f51 --- /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 +Rahul-FineTunedLLM-v03.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Rahul-FineTunedLLM-v03.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Rahul-FineTunedLLM-v03.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Rahul-FineTunedLLM-v03.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Rahul-FineTunedLLM-v03.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Rahul-FineTunedLLM-v03.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Rahul-FineTunedLLM-v03.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Rahul-FineTunedLLM-v03.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Rahul-FineTunedLLM-v03.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Rahul-FineTunedLLM-v03.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Rahul-FineTunedLLM-v03.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Rahul-FineTunedLLM-v03.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2f45c56 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: rahul7star/Rahul-FineTunedLLM-v03 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/rahul7star/Rahul-FineTunedLLM-v03 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Rahul-FineTunedLLM-v03-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/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Rahul-FineTunedLLM-v03-GGUF/resolve/main/Rahul-FineTunedLLM-v03.f16.gguf) | f16 | 0.4 | 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/Rahul-FineTunedLLM-v03.IQ4_XS.gguf b/Rahul-FineTunedLLM-v03.IQ4_XS.gguf new file mode 100644 index 0000000..e84c742 --- /dev/null +++ b/Rahul-FineTunedLLM-v03.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f405b85867a1a12349dc20a973f65e3f3842a2adee5fd988be6db3d27ad5bb8e +size 103063872 diff --git a/Rahul-FineTunedLLM-v03.Q2_K.gguf b/Rahul-FineTunedLLM-v03.Q2_K.gguf new file mode 100644 index 0000000..bd5fe85 --- /dev/null +++ b/Rahul-FineTunedLLM-v03.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c97819494302bb0988279a40eda9590e1b670e0912e554d9cb30affe077db674 +size 81197024 diff --git a/Rahul-FineTunedLLM-v03.Q3_K_L.gguf b/Rahul-FineTunedLLM-v03.Q3_K_L.gguf new file mode 100644 index 0000000..079c77d --- /dev/null +++ b/Rahul-FineTunedLLM-v03.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece4ba6ac3bdd4e9ce35722031655c72154f3d09a44ca47e1d82e0a1029b3c2b +size 102092960 diff --git a/Rahul-FineTunedLLM-v03.Q3_K_M.gguf b/Rahul-FineTunedLLM-v03.Q3_K_M.gguf new file mode 100644 index 0000000..8ef8e86 --- /dev/null +++ b/Rahul-FineTunedLLM-v03.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4353e1f49ccb9eb0e7e6b07eddaa7e1e48f8677c3119d7acd971e89645c0b6e +size 97669280 diff --git a/Rahul-FineTunedLLM-v03.Q3_K_S.gguf b/Rahul-FineTunedLLM-v03.Q3_K_S.gguf new file mode 100644 index 0000000..9c14fac --- /dev/null +++ b/Rahul-FineTunedLLM-v03.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d18ccdc3b8b990a98166717cda1e8c2c178c4ce3dc95acce0aba91208a96cfb +size 90149024 diff --git a/Rahul-FineTunedLLM-v03.Q4_K_M.gguf b/Rahul-FineTunedLLM-v03.Q4_K_M.gguf new file mode 100644 index 0000000..4d7e87e --- /dev/null +++ b/Rahul-FineTunedLLM-v03.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf7e241f81bcfc1ecd9ff15611894318d4e9dffbb0057177cd5222c2bd45e6e5 +size 112859360 diff --git a/Rahul-FineTunedLLM-v03.Q4_K_S.gguf b/Rahul-FineTunedLLM-v03.Q4_K_S.gguf new file mode 100644 index 0000000..96c2f54 --- /dev/null +++ b/Rahul-FineTunedLLM-v03.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fa8cf26eb240f475ca7811f162cded8adf4ffe60616bc019ed9c59e22e0712a +size 106850528 diff --git a/Rahul-FineTunedLLM-v03.Q5_K_M.gguf b/Rahul-FineTunedLLM-v03.Q5_K_M.gguf new file mode 100644 index 0000000..0dffa11 --- /dev/null +++ b/Rahul-FineTunedLLM-v03.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:018349732a595cff743ffa4b6b3329d7c8719097b1544418b745724a9a42eafb +size 126697280 diff --git a/Rahul-FineTunedLLM-v03.Q5_K_S.gguf b/Rahul-FineTunedLLM-v03.Q5_K_S.gguf new file mode 100644 index 0000000..0d78ca2 --- /dev/null +++ b/Rahul-FineTunedLLM-v03.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb10740491a754d1611f4e0b95fc56a7019582c7bed2461894b2aca7064d730b +size 121997120 diff --git a/Rahul-FineTunedLLM-v03.Q6_K.gguf b/Rahul-FineTunedLLM-v03.Q6_K.gguf new file mode 100644 index 0000000..0c56553 --- /dev/null +++ b/Rahul-FineTunedLLM-v03.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab486f5c205b4f91826d60301f92d1939cb69b56be519a2dc349188c94448dd +size 138403712 diff --git a/Rahul-FineTunedLLM-v03.Q8_0.gguf b/Rahul-FineTunedLLM-v03.Q8_0.gguf new file mode 100644 index 0000000..bb3e6ac --- /dev/null +++ b/Rahul-FineTunedLLM-v03.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a0eb963edfc582e07ed20a350ac32e06af422b2a78abcbc2770349f4f64a8ee +size 177669440 diff --git a/Rahul-FineTunedLLM-v03.f16.gguf b/Rahul-FineTunedLLM-v03.f16.gguf new file mode 100644 index 0000000..3e65554 --- /dev/null +++ b/Rahul-FineTunedLLM-v03.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fba94b28d7e85d02fd1712cd9feded1f85cf8ac5202c8c5d475dabf463e16aa2 +size 329665728