commit ee5bb56a982348c221231c581d794d35b176af89 Author: ModelHub XC Date: Thu Apr 30 05:12:31 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1cfa890 --- /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-3.2-SUN-HDIC-1B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-HDIC-1B-Instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.IQ4_XS.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..c842cb9 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2a3917409e914af7d7a15a82975baae4d71c205f2734e566d010f079957be9 +size 887929568 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.Q2_K.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..1e95f57 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3778e9cabcce958cdc08e4c50c9cba14f05968d7ff0d33e65b6fa20da6ac1bed +size 667065056 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_L.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..b2b1a76 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f73280eb879b4236ce88f5bc5bb122044a71c11ed975f155ba86534a5d361f5 +size 845392608 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_M.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b2cd831 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1c35f8720dfeba513a81b081f3290400c8355890ac83552573bc50b740087f4 +size 803711712 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_S.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..3f5d0de --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:057516afcfbf8c0183697384c18fb5dae9f59b5f18a60d403dea1ffa9c7d6c99 +size 754559712 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_0_4_4.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..5a1c803 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdfec2b577ace9d32486608d958b77cb5d9cc45d6b164e93051208c1532f925b +size 918682336 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_K_M.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..903fb25 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d43ed365e95dd33d5b6958c264984b6fc2e9b6057f02ce6e845ae163d494afa +size 955448032 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_K_S.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..0ff87f3 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bfb808ea56ca59669098679fddfb9038a34e4998166c403de6f4803ba52f019 +size 923400928 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.Q5_K_M.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..0a68466 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:507bd581b89ade396d5af8f24206e43807143c11895c05692cce7ea221009a39 +size 1092090592 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.Q5_K_S.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..1624f40 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7940e14cac0304938be4e2a4e0389580a810c49c90d56c84b4e65f8e0ed69a0 +size 1073150688 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.Q6_K.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..c5ca3c4 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3d2b5f61302d542e5907e2e4c5f56f83175704e6ec7460c17ee6e4f3ccf9185 +size 1237273312 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.Q8_0.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..8a1c949 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16ca63f0739b93faa93b2db722aa9fa3211eda142e41f5090a16ee3507b0c9e2 +size 1600170720 diff --git a/Llama-3.2-SUN-HDIC-1B-Instruct.f16.gguf b/Llama-3.2-SUN-HDIC-1B-Instruct.f16.gguf new file mode 100644 index 0000000..76a3da5 --- /dev/null +++ b/Llama-3.2-SUN-HDIC-1B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90b5a2606d7b53a0a0c94cb4a7057dd6dcb081fe8e3f523eb2f34ce215f7828e +size 3004934880 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a0fac2d --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: meditsolutions/Llama-3.2-SUN-HDIC-1B-Instruct +datasets: +- argilla/OpenHermesPreferences +- argilla/magpie-ultra-v0.1 +- argilla/Capybara-Preferences-Filtered +- mlabonne/open-perfectblend +- HuggingFaceTB/everyday-conversations-llama3.1-2k +- WizardLMTeam/WizardLM_evol_instruct_V2_196k +- ProlificAI/social-reasoning-rlhf +- allenai/tulu-3-sft-mixture +- allenai/llama-3.1-tulu-3-8b-preference-mixture +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/meditsolutions/Llama-3.2-SUN-HDIC-1B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-i1-GGUF +## 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-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-HDIC-1B-Instruct-GGUF/resolve/main/Llama-3.2-SUN-HDIC-1B-Instruct.f16.gguf) | f16 | 3.1 | 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. + +