commit b77fe295cc5f2a0d8c49f9dabbcc7a474840b1d6 Author: ModelHub XC Date: Sat Sep 12 12:36:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..58b927d --- /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 +GAINRL-LLaMA-3.2-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GAINRL-LLaMA-3.2-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GAINRL-LLaMA-3.2-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GAINRL-LLaMA-3.2-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GAINRL-LLaMA-3.2-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GAINRL-LLaMA-3.2-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GAINRL-LLaMA-3.2-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GAINRL-LLaMA-3.2-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GAINRL-LLaMA-3.2-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.IQ4_XS.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..9a165fe --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5e5af1c6a059aa54962549ae7bf40033eb38af9e5102c3ee2f315e62ebe178 +size 1840906880 diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.Q2_K.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..55578d7 --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585b9d941ddad23ddbe7198dfd9bd4d33530238b6934d91eb46c6bc842beadd6 +size 1363935872 diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_L.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..9731f4a --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:553eafe75ad5f4cf4ebd7357064c89228cf30cba29cdcf911d61c88951f52ce6 +size 1815347840 diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_M.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..0764d2a --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b656e926c44a25d18cd21ba2680b3ab65503f5523e1f75441110e146add71734 +size 1687159424 diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_S.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..4bc5780 --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1fc228775e522fe182afd540321ac30b11978620de249d897d303f9724089cd +size 1542849152 diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.Q4_K_M.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..28983c3 --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3df07963fb95906dcb3067827062aa8f9512b8f4bacbd7b2b38c6d84b8c4fe61 +size 2019377792 diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.Q4_K_S.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..c2bee65 --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:664fca37ef0c2e0e36e8aa12eea1c226d155ced54bede62c356584f9dc0b6f5d +size 1928200832 diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.Q5_K_M.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..55a5a58 --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb553237e7217b8c2314df43dae377ba9c7225e357aaf4261645dabd2f90c302 +size 2322154112 diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.Q5_K_S.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..269c4ed --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e941c69473a5d89d99c178f9ea83dfa845ea812c44449df18a944fb7b8a43626 +size 2269512320 diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.Q6_K.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..608179d --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eae931b16b9c997f419c434408c23f32474b6f99b3f16899b3e0d84b0aa6246 +size 2643853952 diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.Q8_0.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..feb2b30 --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde82e4af046d2babb38533b07bb6d65ce41f5763f5931815d1d39946ab5d6fd +size 3421899392 diff --git a/GAINRL-LLaMA-3.2-3B-Instruct.f16.gguf b/GAINRL-LLaMA-3.2-3B-Instruct.f16.gguf new file mode 100644 index 0000000..5dd9066 --- /dev/null +++ b/GAINRL-LLaMA-3.2-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e24f58d6856b92c10ed7016e27b25380b44d338fab9d3f03671b2b0fd14f9fe5 +size 6433688192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a19baa7 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Qinsi1/GAINRL-LLaMA-3.2-3B-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Qinsi1/GAINRL-LLaMA-3.2-3B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GAINRL-LLaMA-3.2-3B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-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/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GAINRL-LLaMA-3.2-3B-Instruct-GGUF/resolve/main/GAINRL-LLaMA-3.2-3B-Instruct.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. + +