commit 5c3378aa26239c1266907edb3bab92d5dc7474b0 Author: ModelHub XC Date: Mon Jun 15 06:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ad79ce --- /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-Hindi.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Hindi.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Hindi.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Hindi.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Hindi.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Hindi.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Hindi.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Hindi.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Hindi.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Hindi.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Hindi.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Hindi.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-Hindi.IQ4_XS.gguf b/Llama-3.2-3B-Instruct-Hindi.IQ4_XS.gguf new file mode 100644 index 0000000..82affe4 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5f68087c336b782ecb0e9e930e8a5c2f409eebbc41ca3327be3d240f66e999 +size 2050221248 diff --git a/Llama-3.2-3B-Instruct-Hindi.Q2_K.gguf b/Llama-3.2-3B-Instruct-Hindi.Q2_K.gguf new file mode 100644 index 0000000..ee9b863 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1eb0e8c04f3eb0c76c5a76546e03ca9ee083a72828e6231786639fb6b6b7405 +size 1493218496 diff --git a/Llama-3.2-3B-Instruct-Hindi.Q3_K_L.gguf b/Llama-3.2-3B-Instruct-Hindi.Q3_K_L.gguf new file mode 100644 index 0000000..6e8f2c7 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1d8808045f26979a08795a29d6a066e4145cbaee8fff12790840b6a8336fb08 +size 1984646336 diff --git a/Llama-3.2-3B-Instruct-Hindi.Q3_K_M.gguf b/Llama-3.2-3B-Instruct-Hindi.Q3_K_M.gguf new file mode 100644 index 0000000..a74935d --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39aee19233c049d70bb84c212a2551434e483c2d3db04cee00249284cded8e36 +size 1856457920 diff --git a/Llama-3.2-3B-Instruct-Hindi.Q3_K_S.gguf b/Llama-3.2-3B-Instruct-Hindi.Q3_K_S.gguf new file mode 100644 index 0000000..6901469 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0549cd2f8aedbd02bb0942f81ea0377ed3a05f9f0c7f340a2023e9d0915f8523 +size 1712147648 diff --git a/Llama-3.2-3B-Instruct-Hindi.Q4_K_M.gguf b/Llama-3.2-3B-Instruct-Hindi.Q4_K_M.gguf new file mode 100644 index 0000000..6e2638a --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdff2c6d2ae81c581beb01ad71bd4f85aa77dd3da218c84bd4ce3b905a0268c4 +size 2241004736 diff --git a/Llama-3.2-3B-Instruct-Hindi.Q4_K_S.gguf b/Llama-3.2-3B-Instruct-Hindi.Q4_K_S.gguf new file mode 100644 index 0000000..61e140f --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4737d351ea39720097a3351aa187b6ca3d575d42e59bbea3c83fb4f98ac7a0aa +size 2149827776 diff --git a/Llama-3.2-3B-Instruct-Hindi.Q5_K_M.gguf b/Llama-3.2-3B-Instruct-Hindi.Q5_K_M.gguf new file mode 100644 index 0000000..461ac75 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd8416cf7fe800ff306a04f04bf8f875d56fec62fd2cdb254c6e68fff8d23e21 +size 2593031360 diff --git a/Llama-3.2-3B-Instruct-Hindi.Q5_K_S.gguf b/Llama-3.2-3B-Instruct-Hindi.Q5_K_S.gguf new file mode 100644 index 0000000..621f8a7 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebe9d679623d50c10f3f19205a6e9145b99ebf2d11158edc6f5fb331af976214 +size 2540389568 diff --git a/Llama-3.2-3B-Instruct-Hindi.Q6_K.gguf b/Llama-3.2-3B-Instruct-Hindi.Q6_K.gguf new file mode 100644 index 0000000..ab18244 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bd9f16af0e032856c0191a187d9d47dfa6ab2c741d870ada457752bb7d747ab +size 2967059648 diff --git a/Llama-3.2-3B-Instruct-Hindi.Q8_0.gguf b/Llama-3.2-3B-Instruct-Hindi.Q8_0.gguf new file mode 100644 index 0000000..0b340c7 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e42f1242e9c959275030b20ef3df3baff00ad2e58daa3fda18263c498a70be6 +size 3840527552 diff --git a/Llama-3.2-3B-Instruct-Hindi.f16.gguf b/Llama-3.2-3B-Instruct-Hindi.f16.gguf new file mode 100644 index 0000000..25b0835 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Hindi.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:276b82122956b843b6b13a628de7f0b7115335252e4e9d49f5a3644350e86493 +size 7221693632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..00188a4 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Ryder99/Llama-3.2-3B-Instruct-Hindi +language: +- en +- hi +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Ryder99/Llama-3.2-3B-Instruct-Hindi + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Instruct-Hindi-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-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-3B-Instruct-Hindi.f16.gguf) | f16 | 7.3 | 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. + +