commit a65cc3025f78801bac7ee516e9ef6be84c2b6891 Author: ModelHub XC Date: Tue Apr 28 10:58:37 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f9638ff --- /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-Instruct-Hindi.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Hindi.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Hindi.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Hindi.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Hindi.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Hindi.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Hindi.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Hindi.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Hindi.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Hindi.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Hindi.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Hindi.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-Hindi.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-Hindi.IQ4_XS.gguf new file mode 100644 index 0000000..012acbd --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f070ceb1568a8807bc32dcca0682234d57cdf0abab20d0b1dc99dfef1758ac7e +size 887927552 diff --git a/Llama-3.2-1B-Instruct-Hindi.Q2_K.gguf b/Llama-3.2-1B-Instruct-Hindi.Q2_K.gguf new file mode 100644 index 0000000..9812891 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d303109754739d6472ed8e87afed7eb99d047a338a8ad748511a08251994af3 +size 667063040 diff --git a/Llama-3.2-1B-Instruct-Hindi.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-Hindi.Q3_K_L.gguf new file mode 100644 index 0000000..2827dfe --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14dd26947a588f37647bacb3032600e73270f127272db3aec6cd55bd03c745fb +size 845390592 diff --git a/Llama-3.2-1B-Instruct-Hindi.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-Hindi.Q3_K_M.gguf new file mode 100644 index 0000000..148b41e --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebcf2cb0219ef6801b607f796ece9f87582a9ba3f9657582721a8d259939cb2c +size 803709696 diff --git a/Llama-3.2-1B-Instruct-Hindi.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-Hindi.Q3_K_S.gguf new file mode 100644 index 0000000..2ad4d82 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3ca6622e45ffa2bec322bef11e2ed5b6c34f5fd3ced4a733a6fd08443cfa3e7 +size 754557696 diff --git a/Llama-3.2-1B-Instruct-Hindi.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-Hindi.Q4_K_M.gguf new file mode 100644 index 0000000..34b0309 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a61ea1799c2da987098c104884cb187ff494decd9867594bc40ca2f71f18ea9 +size 955446016 diff --git a/Llama-3.2-1B-Instruct-Hindi.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-Hindi.Q4_K_S.gguf new file mode 100644 index 0000000..241e71b --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b854b1b01b92cbdac01c8ef87f0273d38976725d4e0a70d227eb6d40eb26a919 +size 923398912 diff --git a/Llama-3.2-1B-Instruct-Hindi.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-Hindi.Q5_K_M.gguf new file mode 100644 index 0000000..cb999ba --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef78438b30d86fd46c81e51dd1c50ab078383c30ff53fc73c5d8873ced8e284a +size 1092088576 diff --git a/Llama-3.2-1B-Instruct-Hindi.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-Hindi.Q5_K_S.gguf new file mode 100644 index 0000000..cec44f3 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e986476639ff9ff6a65106f20286bde9e70ccc6302d8ee1d101a63fa6b4cda7e +size 1073148672 diff --git a/Llama-3.2-1B-Instruct-Hindi.Q6_K.gguf b/Llama-3.2-1B-Instruct-Hindi.Q6_K.gguf new file mode 100644 index 0000000..6e89b7b --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81300770707028ad599981e59fb619e566090c8819969cc321a10c64c7c65cc6 +size 1237271296 diff --git a/Llama-3.2-1B-Instruct-Hindi.Q8_0.gguf b/Llama-3.2-1B-Instruct-Hindi.Q8_0.gguf new file mode 100644 index 0000000..9b7b0c1 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb9c8bbfcf31e9709e640ec0af4e8b44c2bcc1385db517163bc6550166f8aa6 +size 1600168704 diff --git a/Llama-3.2-1B-Instruct-Hindi.f16.gguf b/Llama-3.2-1B-Instruct-Hindi.f16.gguf new file mode 100644 index 0000000..4518b5c --- /dev/null +++ b/Llama-3.2-1B-Instruct-Hindi.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5817f59ead5ae2729e6a80fcb7e3809e6f5b99efa31ad146f6687c37b74c60e9 +size 3004932864 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ce1e21f --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Ryder99/Llama-3.2-1B-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-3.2-1B-Instruct-Hindi + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-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-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Hindi-GGUF/resolve/main/Llama-3.2-1B-Instruct-Hindi.f16.gguf) | f16 | 3.1 | 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. + +