commit 6fc5b0c0c2855f2c5e8b185834b38ffc6466a2bc Author: ModelHub XC Date: Sat Jul 11 08:50:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8b409fe --- /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 +LLAMA-3.2-1B-IDENTITY.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3.2-1B-IDENTITY.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3.2-1B-IDENTITY.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3.2-1B-IDENTITY.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3.2-1B-IDENTITY.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3.2-1B-IDENTITY.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3.2-1B-IDENTITY.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3.2-1B-IDENTITY.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3.2-1B-IDENTITY.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3.2-1B-IDENTITY.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3.2-1B-IDENTITY.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3.2-1B-IDENTITY.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLAMA-3.2-1B-IDENTITY.IQ4_XS.gguf b/LLAMA-3.2-1B-IDENTITY.IQ4_XS.gguf new file mode 100644 index 0000000..3b91547 --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00e1543e726a46e846cae7902639e22735423a9b586f949bfed68f6a0617eb67 +size 748384416 diff --git a/LLAMA-3.2-1B-IDENTITY.Q2_K.gguf b/LLAMA-3.2-1B-IDENTITY.Q2_K.gguf new file mode 100644 index 0000000..aa07969 --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcc253ddd500a7c3d7dd6dcb0e336e2698ffac4bbfae0a7999ae6ac19fa7d900 +size 580874400 diff --git a/LLAMA-3.2-1B-IDENTITY.Q3_K_L.gguf b/LLAMA-3.2-1B-IDENTITY.Q3_K_L.gguf new file mode 100644 index 0000000..1205ae0 --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a43c3ab1eca20596cd74d145ba3005b83430bc42978615bfbe91e3effb6ce77 +size 732524704 diff --git a/LLAMA-3.2-1B-IDENTITY.Q3_K_M.gguf b/LLAMA-3.2-1B-IDENTITY.Q3_K_M.gguf new file mode 100644 index 0000000..f6948bd --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e1e2089f697f355766665b671236f266c9b45ef80826eba9804e88383642cd7 +size 690843808 diff --git a/LLAMA-3.2-1B-IDENTITY.Q3_K_S.gguf b/LLAMA-3.2-1B-IDENTITY.Q3_K_S.gguf new file mode 100644 index 0000000..ec519b8 --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada690c24edeb8ec1eea565d1523b5440e1701863eefed5214e36c53e372fec7 +size 641691808 diff --git a/LLAMA-3.2-1B-IDENTITY.Q4_K_M.gguf b/LLAMA-3.2-1B-IDENTITY.Q4_K_M.gguf new file mode 100644 index 0000000..de4511a --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b69cc036d8f81955eaf0d53eac73ce3acae3f87b6f0ec4bd47de85934c22f27f +size 807694496 diff --git a/LLAMA-3.2-1B-IDENTITY.Q4_K_S.gguf b/LLAMA-3.2-1B-IDENTITY.Q4_K_S.gguf new file mode 100644 index 0000000..3f20122 --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8df8ac1ea30f70c7acb600498480ab343f21fa56c092ce3f61575c87fb373365 +size 775647392 diff --git a/LLAMA-3.2-1B-IDENTITY.Q5_K_M.gguf b/LLAMA-3.2-1B-IDENTITY.Q5_K_M.gguf new file mode 100644 index 0000000..5313cde --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e8eddd6f5058f23f6f1753e0eb5f6c2539c4d4f3e926a3e5beae117d7564b92 +size 911503520 diff --git a/LLAMA-3.2-1B-IDENTITY.Q5_K_S.gguf b/LLAMA-3.2-1B-IDENTITY.Q5_K_S.gguf new file mode 100644 index 0000000..5704eee --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:637b88329e1fd09ab04ebc8f2d7f470aa22d7fdf20b39c12e3608bfe88c04a29 +size 892563616 diff --git a/LLAMA-3.2-1B-IDENTITY.Q6_K.gguf b/LLAMA-3.2-1B-IDENTITY.Q6_K.gguf new file mode 100644 index 0000000..d7cb02f --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87052ab36f605a7d3129049549a18f0c91dfd1f19677e4a0313e0746edca8df2 +size 1021800608 diff --git a/LLAMA-3.2-1B-IDENTITY.Q8_0.gguf b/LLAMA-3.2-1B-IDENTITY.Q8_0.gguf new file mode 100644 index 0000000..801c18d --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8731feaf8ea154d541f40d8619412f5eb3acb5505eb869c8317c614a3fa820 +size 1321083040 diff --git a/LLAMA-3.2-1B-IDENTITY.f16.gguf b/LLAMA-3.2-1B-IDENTITY.f16.gguf new file mode 100644 index 0000000..07671a5 --- /dev/null +++ b/LLAMA-3.2-1B-IDENTITY.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c577267080a99777d7b19a148f9a425d4d9d48950c1e29b6688e5523b9abe430 +size 2479595680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..925d94b --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: SriSanthM/LLAMA-3.2-1B-IDENTITY +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/SriSanthM/LLAMA-3.2-1B-IDENTITY + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LLAMA-3.2-1B-IDENTITY-GGUF).*** + +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-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3.2-1B-IDENTITY-GGUF/resolve/main/LLAMA-3.2-1B-IDENTITY.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. + +