commit 5946be7c8cff1438b231b9b0696bb8749c63123a Author: ModelHub XC Date: Wed Sep 30 05:33:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..42a35a0 --- /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 +AI_1611_llama3.2_3B_Instruct_AI_Interview.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AI_1611_llama3.2_3B_Instruct_AI_Interview.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI_1611_llama3.2_3B_Instruct_AI_Interview.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI_1611_llama3.2_3B_Instruct_AI_Interview.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI_1611_llama3.2_3B_Instruct_AI_Interview.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI_1611_llama3.2_3B_Instruct_AI_Interview.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI_1611_llama3.2_3B_Instruct_AI_Interview.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AI_1611_llama3.2_3B_Instruct_AI_Interview.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AI_1611_llama3.2_3B_Instruct_AI_Interview.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.IQ4_XS.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.IQ4_XS.gguf new file mode 100644 index 0000000..f37e904 --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ad4961f6b0d716ddfab2f06add7fce81c4cb5f83717d8d050677705998697f +size 1840912448 diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q2_K.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q2_K.gguf new file mode 100644 index 0000000..ff0b18f --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52885948456b28e9c47d8d8f21a931245a0cac952e7b918e725680a9c5a2cad6 +size 1363941440 diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_L.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_L.gguf new file mode 100644 index 0000000..1374779 --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef5b88380bf47093db73352d32f03469bcd05879698e71bc655039de472f192e +size 1815353408 diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_M.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_M.gguf new file mode 100644 index 0000000..79d40eb --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a43506f4d183a769643d0992d3bcfebc2b7ccc2dced96dd1df7cab34f60787ad +size 1687164992 diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_S.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_S.gguf new file mode 100644 index 0000000..f7bac89 --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18f9192e9a1e7b8476d600bc881b7bf9c6c6cd902ea272d595f79c33de1d624a +size 1542854720 diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q4_K_M.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q4_K_M.gguf new file mode 100644 index 0000000..6912726 --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c209f6b1fe5a8bb4a34a2c4e3e4d10542778d7f124a9681f72a3a92d7c5a3220 +size 2019383360 diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q4_K_S.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q4_K_S.gguf new file mode 100644 index 0000000..8ce6652 --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:238775c3df4772363bc3c789d5b5b0176d7cd6ffcab10cbf860fb409e49b78df +size 1928206400 diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q5_K_M.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q5_K_M.gguf new file mode 100644 index 0000000..50c4883 --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e35565eff84bfb7a1b90c875eddd0460850b8dbade556b1933cfdfff80fd3063 +size 2322159680 diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q5_K_S.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q5_K_S.gguf new file mode 100644 index 0000000..759bf95 --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff26d41311139776ec8440ad1b57392a3af123b03924c37312aae92687e9e1ad +size 2269517888 diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q6_K.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q6_K.gguf new file mode 100644 index 0000000..7fda638 --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ae62736cdbe94ed2acae442343532814dcdbeab5c58d7de27d600eb0323a3d4 +size 2643859520 diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q8_0.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q8_0.gguf new file mode 100644 index 0000000..5763016 --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0918038fa478ad0c243b1465736ca4a1f48a09a62a260b99db6a45e6d4cbb1 +size 3421904960 diff --git a/AI_1611_llama3.2_3B_Instruct_AI_Interview.f16.gguf b/AI_1611_llama3.2_3B_Instruct_AI_Interview.f16.gguf new file mode 100644 index 0000000..71edaca --- /dev/null +++ b/AI_1611_llama3.2_3B_Instruct_AI_Interview.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6476eddb64214ee279844405de3ef0d82cbf6b1c42421ee3134ed9b670daab0f +size 6433693760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a52f715 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: harry767701/AI_1611_llama3.2_3B_Instruct_AI_Interview +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/harry767701/AI_1611_llama3.2_3B_Instruct_AI_Interview + + +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/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AI_1611_llama3.2_3B_Instruct_AI_Interview-GGUF/resolve/main/AI_1611_llama3.2_3B_Instruct_AI_Interview.f16.gguf) | f16 | 6.5 | 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. + +