commit f766ec71748d975cc9d16280d6caac66636ae1ee Author: ModelHub XC Date: Wed Apr 29 08:51:31 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2f0c0e0 --- /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 +LLAMA_Harsha_8_B_ORDP_10k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA_Harsha_8_B_ORDP_10k.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLAMA_Harsha_8_B_ORDP_10k.IQ4_XS.gguf b/LLAMA_Harsha_8_B_ORDP_10k.IQ4_XS.gguf new file mode 100644 index 0000000..f4013ea --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4f4ce7e53e523294a13d85bcefa897155d3389f0e02e4b9bd68507a1a35c582 +size 4484374208 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.Q2_K.gguf b/LLAMA_Harsha_8_B_ORDP_10k.Q2_K.gguf new file mode 100644 index 0000000..51b938d --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdd4c6268ed658a8573c3a60380a0c0f0b1815c4d5f6b0a334cdeefe81ab23c0 +size 3179141184 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_L.gguf b/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_L.gguf new file mode 100644 index 0000000..ca4def0 --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1c44a1e05e94ab3488f7867a9ceb2de395fe6e5b5d5603473cc14797723578d +size 4321966976 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_M.gguf b/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_M.gguf new file mode 100644 index 0000000..b9f39c1 --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db02d56d40108748540a36fb2cb0878a755b38bbd0a9ce9a88a8f7b604520f58 +size 4018928512 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_S.gguf b/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_S.gguf new file mode 100644 index 0000000..ba434e7 --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18e15132ff44db1585c3ff24718845adbd94aa4d12800cb631b3dd4ac4f06aef +size 3664509824 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.Q4_0_4_4.gguf b/LLAMA_Harsha_8_B_ORDP_10k.Q4_0_4_4.gguf new file mode 100644 index 0000000..b503576 --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f07e12a2208ec6c4496eb812f788358be3859ff55bb1f86c393fbd2d8b15a589 +size 4661223360 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.Q4_K_M.gguf b/LLAMA_Harsha_8_B_ORDP_10k.Q4_K_M.gguf new file mode 100644 index 0000000..41af11d --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322499a4aa69ea5dde8ae895583e8d598ea18be661734b8c349ed15a4649ceba +size 4920745920 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.Q4_K_S.gguf b/LLAMA_Harsha_8_B_ORDP_10k.Q4_K_S.gguf new file mode 100644 index 0000000..23e646e --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88be47538b86bf558edc80f12a297c1f6a98bde9fdca67afbcb57d926f1313fe +size 4692680640 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.Q5_K_M.gguf b/LLAMA_Harsha_8_B_ORDP_10k.Q5_K_M.gguf new file mode 100644 index 0000000..5a0d599 --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74cdb0d9c908a6bf292c8185a5ef5de92b5d0ad1a9ed6261846ccbe9763972b4 +size 5733000128 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.Q5_K_S.gguf b/LLAMA_Harsha_8_B_ORDP_10k.Q5_K_S.gguf new file mode 100644 index 0000000..e46d8c6 --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19470bca92f03ed4141aaad78fba2902dcd722209e488b43b252f76838a4856 +size 5599306688 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.Q6_K.gguf b/LLAMA_Harsha_8_B_ORDP_10k.Q6_K.gguf new file mode 100644 index 0000000..98f1f90 --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5a95389b409165fcd3009af9a5a9fd8a4cbd3e23d27eefa7d034776cdbd67f +size 6596020224 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.Q8_0.gguf b/LLAMA_Harsha_8_B_ORDP_10k.Q8_0.gguf new file mode 100644 index 0000000..4fe9006 --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff5cfd5459978a2c0451c175745dbea36140737e10f5ad214eae720d18ea17d +size 8540788608 diff --git a/LLAMA_Harsha_8_B_ORDP_10k.f16.gguf b/LLAMA_Harsha_8_B_ORDP_10k.f16.gguf new file mode 100644 index 0000000..e9c077f --- /dev/null +++ b/LLAMA_Harsha_8_B_ORDP_10k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd512612eab9a3f93bbb9ca441ca8274754caf6a6463dbfa64532ad5d32caa7d +size 16068924288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..81999fd --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: asharsha30/LLAMA_Harsha_8_B_ORDP_10k +datasets: +- mlabonne/orpo-dpo-mix-40k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- orpo +- llama3-8B +- Supervised_Training +--- +## About + + + + + + +static quants of https://huggingface.co/asharsha30/LLAMA_Harsha_8_B_ORDP_10k + + +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_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA_Harsha_8_B_ORDP_10k-GGUF/resolve/main/LLAMA_Harsha_8_B_ORDP_10k.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. 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. + +