commit ca9c63b14897c7b842cdf91ac6d0f1651fe0d5e3 Author: ModelHub XC Date: Thu Jun 11 07:55:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLMTwin-Llama-3.2-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5b96a95 --- /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 +LLMTwin-Llama-3.2-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.2-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.2-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.2-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.2-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.2-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.2-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.2-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.2-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.2-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.2-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.2-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLMTwin-Llama-3.2-1B.IQ4_XS.gguf b/LLMTwin-Llama-3.2-1B.IQ4_XS.gguf new file mode 100644 index 0000000..e2d37b1 --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94e68d7930d8424e9bc354abdb9f0f31a04d1a8949311e7a9b6e19f322af1430 +size 748381344 diff --git a/LLMTwin-Llama-3.2-1B.Q2_K.gguf b/LLMTwin-Llama-3.2-1B.Q2_K.gguf new file mode 100644 index 0000000..6c0588c --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29d08dbcafb0e2f4152ae36e2dcac819cfaed3726b97e496f516b858edb9f7c +size 580871328 diff --git a/LLMTwin-Llama-3.2-1B.Q3_K_L.gguf b/LLMTwin-Llama-3.2-1B.Q3_K_L.gguf new file mode 100644 index 0000000..de0ac2e --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81c4d2423efb4475aec13294db6765a748826d6051a0fbe78c1c00c225b942dc +size 732521632 diff --git a/LLMTwin-Llama-3.2-1B.Q3_K_M.gguf b/LLMTwin-Llama-3.2-1B.Q3_K_M.gguf new file mode 100644 index 0000000..931c879 --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7db973c3c63bc7374d14b0170f568e79afdcff2dd05ba031a1171a34588f12c +size 690840736 diff --git a/LLMTwin-Llama-3.2-1B.Q3_K_S.gguf b/LLMTwin-Llama-3.2-1B.Q3_K_S.gguf new file mode 100644 index 0000000..79ad41d --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b590751e9950aab28b77a430cb518c52566d4231c5b792484995700ea2ffb657 +size 641688736 diff --git a/LLMTwin-Llama-3.2-1B.Q4_K_M.gguf b/LLMTwin-Llama-3.2-1B.Q4_K_M.gguf new file mode 100644 index 0000000..f986956 --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47a2edf49a3510b96e870cecd4f33bb70211d90535c4be3f514b26c00d8836fe +size 807691424 diff --git a/LLMTwin-Llama-3.2-1B.Q4_K_S.gguf b/LLMTwin-Llama-3.2-1B.Q4_K_S.gguf new file mode 100644 index 0000000..5987d91 --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bcaa1c0be8ad765664cc3182882e66305ab28dd7c080d06bcf283d0c6108246 +size 775644320 diff --git a/LLMTwin-Llama-3.2-1B.Q5_K_M.gguf b/LLMTwin-Llama-3.2-1B.Q5_K_M.gguf new file mode 100644 index 0000000..da5189f --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:446b58f36cf0a7ba9497bdaaccfa17ad2cec60b7b41beab8b4e86bea1144d979 +size 911500448 diff --git a/LLMTwin-Llama-3.2-1B.Q5_K_S.gguf b/LLMTwin-Llama-3.2-1B.Q5_K_S.gguf new file mode 100644 index 0000000..4bbc0fd --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f7b545724e26bae1af36af1fafd1823dfac579c35b27e1e9a1daee98d6cea37 +size 892560544 diff --git a/LLMTwin-Llama-3.2-1B.Q6_K.gguf b/LLMTwin-Llama-3.2-1B.Q6_K.gguf new file mode 100644 index 0000000..06d1514 --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb11a794635a5254c275deaf973dc7cb6b32df77db584e5a66b6d5f7d1acb4e1 +size 1021797536 diff --git a/LLMTwin-Llama-3.2-1B.Q8_0.gguf b/LLMTwin-Llama-3.2-1B.Q8_0.gguf new file mode 100644 index 0000000..fac1603 --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08e7e96f217651da732b2ee4c2c07d93ab628bd7c281ec947b559f62c0da73ad +size 1321079968 diff --git a/LLMTwin-Llama-3.2-1B.f16.gguf b/LLMTwin-Llama-3.2-1B.f16.gguf new file mode 100644 index 0000000..b622cd5 --- /dev/null +++ b/LLMTwin-Llama-3.2-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eea01a92b09056b35fdfac3d36f0daf71797f34239eb29d56af2785c443f44e +size 2479592608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9ea9e7e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: slchangtw/LLMTwin-Llama-3.2-1B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/slchangtw/LLMTwin-Llama-3.2-1B + + +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/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.2-1B-GGUF/resolve/main/LLMTwin-Llama-3.2-1B.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. + +