commit b1d95c575e00d16276bbbf34f4dbde1518d768c9 Author: ModelHub XC Date: Thu Aug 20 09:45:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Explore_Llama-3.2-1B-Inst-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..02c8e17 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +Explore_Llama-3.2-1B-Inst.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.f16.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Explore_Llama-3.2-1B-Inst.IQ3_M.gguf b/Explore_Llama-3.2-1B-Inst.IQ3_M.gguf new file mode 100644 index 0000000..87fa995 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06ce02b52018873fb11f860d63512885565127170b356782baef105c45fdd8f +size 657289280 diff --git a/Explore_Llama-3.2-1B-Inst.IQ3_S.gguf b/Explore_Llama-3.2-1B-Inst.IQ3_S.gguf new file mode 100644 index 0000000..74f5e10 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f271b14caf0a7ff1370250d92243117f5bdae075f1045f79d325f78dcb7873a1 +size 643919936 diff --git a/Explore_Llama-3.2-1B-Inst.IQ3_XS.gguf b/Explore_Llama-3.2-1B-Inst.IQ3_XS.gguf new file mode 100644 index 0000000..d2047b3 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cedd1764790dfe877049603e8677bd33d4b8e6536c88408d31ac3a70e5c377f5 +size 621113408 diff --git a/Explore_Llama-3.2-1B-Inst.IQ4_XS.gguf b/Explore_Llama-3.2-1B-Inst.IQ4_XS.gguf new file mode 100644 index 0000000..3da0b7a --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9fffe9892ae54a1f544e739987cb6309d26f1b473d0eee5f3a036a3dbf30e1 +size 748384320 diff --git a/Explore_Llama-3.2-1B-Inst.Q2_K.gguf b/Explore_Llama-3.2-1B-Inst.Q2_K.gguf new file mode 100644 index 0000000..e700be3 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3600429016f35e4ef8a8290e4dfb454c018eab995717af0eedeb9647d98c1f6d +size 580874304 diff --git a/Explore_Llama-3.2-1B-Inst.Q3_K_L.gguf b/Explore_Llama-3.2-1B-Inst.Q3_K_L.gguf new file mode 100644 index 0000000..e16df95 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af24de949bdecf3af2b9f20746a0cb23ec3729c46ce466212f4f76127d1b3bef +size 732524608 diff --git a/Explore_Llama-3.2-1B-Inst.Q3_K_M.gguf b/Explore_Llama-3.2-1B-Inst.Q3_K_M.gguf new file mode 100644 index 0000000..876f6db --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0ceec94dd5fd1ca4bf583da37c97f3577bf7303bf976873aed6e6fe866a1dc +size 690843712 diff --git a/Explore_Llama-3.2-1B-Inst.Q3_K_S.gguf b/Explore_Llama-3.2-1B-Inst.Q3_K_S.gguf new file mode 100644 index 0000000..27ee742 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18a154c541d8021d70d4eacd8c499ddb859f5fae90913af3b78e5f5c0b5771cd +size 641691712 diff --git a/Explore_Llama-3.2-1B-Inst.Q4_K_M.gguf b/Explore_Llama-3.2-1B-Inst.Q4_K_M.gguf new file mode 100644 index 0000000..9002275 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c93cdf4b900128dfeaa3846c0c53c04c46755a29e249196afcb68bd4ff3978ec +size 807694400 diff --git a/Explore_Llama-3.2-1B-Inst.Q4_K_S.gguf b/Explore_Llama-3.2-1B-Inst.Q4_K_S.gguf new file mode 100644 index 0000000..2c06e53 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942f22d7e067cd4ce9018b84368dfcbef7c64525a0ee28cd993987c8b45f970c +size 775647296 diff --git a/Explore_Llama-3.2-1B-Inst.Q5_K_M.gguf b/Explore_Llama-3.2-1B-Inst.Q5_K_M.gguf new file mode 100644 index 0000000..0dec4b5 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed5cb99c51d83d9e7d6a0305a9f0268af8f989e90b09879dc896d58236717bc4 +size 911503424 diff --git a/Explore_Llama-3.2-1B-Inst.Q5_K_S.gguf b/Explore_Llama-3.2-1B-Inst.Q5_K_S.gguf new file mode 100644 index 0000000..e43ba68 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faecff10d97d15b711dc57b57ad9c191d1dde79506b5ebe305b340f75c4b2125 +size 892563520 diff --git a/Explore_Llama-3.2-1B-Inst.Q6_K.gguf b/Explore_Llama-3.2-1B-Inst.Q6_K.gguf new file mode 100644 index 0000000..c608902 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92f2599bd023cc2b6e72013d5c892a93579d05dcaf3d09b89ffda814bef3a3e5 +size 1021800512 diff --git a/Explore_Llama-3.2-1B-Inst.Q8_0.gguf b/Explore_Llama-3.2-1B-Inst.Q8_0.gguf new file mode 100644 index 0000000..b7eb98e --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111f49efc8df8b038de6a53a389a40d6303420a18ca90a923d13c478493cbbc8 +size 1321082944 diff --git a/Explore_Llama-3.2-1B-Inst.f16.gguf b/Explore_Llama-3.2-1B-Inst.f16.gguf new file mode 100644 index 0000000..8b0a8f1 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0944f2e48419c1de741b756c7e5278e5294ca7f4e85e4c9844edf803e033cac9 +size 2479595584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e6cba77 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: DeepAuto-AI/Explore_Llama-3.2-1B-Inst +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/DeepAuto-AI/Explore_Llama-3.2-1B-Inst + + +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/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.IQ3_XS.gguf) | IQ3_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.IQ3_S.gguf) | IQ3_S | 0.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.IQ3_M.gguf) | IQ3_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst.f16.gguf) | f16 | 2.6 | 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. + +