commit 23f732bb0fe31a58b95cd48565a0c01c4eceb776 Author: ModelHub XC Date: Thu Apr 30 20:04:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7db2f51 --- /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-3.2-3B-Instruct-Jopara-V1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Jopara-V1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Jopara-V1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Jopara-V1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Jopara-V1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Jopara-V1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Jopara-V1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Jopara-V1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Jopara-V1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.IQ4_XS.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.IQ4_XS.gguf new file mode 100644 index 0000000..21886c6 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3fa430a842fe26f45fb2cd869d1e1e8317dff7c453d407948d90081bdb0e231 +size 1840907424 diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.Q2_K.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.Q2_K.gguf new file mode 100644 index 0000000..913946c --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48e9e0e4b3a6b4d29d4dfc2b16c6ee178bb403b03c4d5f922c9b1aa5d7d38b56 +size 1363936416 diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_L.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_L.gguf new file mode 100644 index 0000000..c4aebf4 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a476c6e75a97fcf97ee8000fc3a322cfa490621ace50d9b2401cb8a87a91f251 +size 1815348384 diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_M.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_M.gguf new file mode 100644 index 0000000..7ececca --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:656fb9dd5c7c1da28dc8964cf3f8650649204780efb43d4fd2e1221d2600b5d9 +size 1687159968 diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_S.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_S.gguf new file mode 100644 index 0000000..96c0f29 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e104ef198c46a872d2abf5cb21c2b740a42857b5e692b65f5f097df51c71c3 +size 1542849696 diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.Q4_K_M.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.Q4_K_M.gguf new file mode 100644 index 0000000..46dd414 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8fd7ddc57aacff7f8631253bfa4b2b9dd5b8def78496193751cb35fa782cd5 +size 2019378336 diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.Q4_K_S.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.Q4_K_S.gguf new file mode 100644 index 0000000..6c69d2a --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d29af86439d68bc57822e3dc1d4d99e86d7c677816861be1fe885c9915296884 +size 1928201376 diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.Q5_K_M.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.Q5_K_M.gguf new file mode 100644 index 0000000..2d7596f --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ffb57005f9f13959a909de139fc0bc451aafecc7aecc5a3014e8835713f6074 +size 2322154656 diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.Q5_K_S.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.Q5_K_S.gguf new file mode 100644 index 0000000..cd5c29f --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:338399befb2c97d3be8867a23e2f755c4742b514992744baa3ab33c7ea1e2e45 +size 2269512864 diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.Q6_K.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.Q6_K.gguf new file mode 100644 index 0000000..c9a9f77 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87bf9d11d3f34cda9b2e34f4ea5e0bef6e9c7330d872d0e50d01091cf240fa8e +size 2643854496 diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.Q8_0.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.Q8_0.gguf new file mode 100644 index 0000000..b83f2c6 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd35de35c1487ad145428d7cdd2155470f26c85b69389ec87ea5d132ef97032f +size 3421899936 diff --git a/Llama-3.2-3B-Instruct-Jopara-V1.f16.gguf b/Llama-3.2-3B-Instruct-Jopara-V1.f16.gguf new file mode 100644 index 0000000..fbc5027 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Jopara-V1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c59af8b83c830bfb1f459245f2124be08b148e8d57e0e41d2e0b6296079d347 +size 6433688736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd58ca0 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Emilio407/Llama-3.2-3B-Instruct-Jopara-V1 +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/Emilio407/Llama-3.2-3B-Instruct-Jopara-V1 + + +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-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Jopara-V1-GGUF/resolve/main/Llama-3.2-3B-Instruct-Jopara-V1.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. + +