commit fd953ca2592c8435d8951b138b2d7576876382c6 Author: ModelHub XC Date: Thu Jun 18 12:33:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2-3b-babagpt-1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..559958e --- /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-babagpt-1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-babagpt-1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-babagpt-1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-babagpt-1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-babagpt-1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-babagpt-1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-babagpt-1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-babagpt-1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-babagpt-1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-babagpt-1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-babagpt-1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-babagpt-1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ad3b604 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: lkapoor/llama-3.2-3b-babagpt-1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/lkapoor/llama-3.2-3b-babagpt-1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.2-3b-babagpt-1-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-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-babagpt-1-GGUF/resolve/main/llama-3.2-3b-babagpt-1.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. + + diff --git a/llama-3.2-3b-babagpt-1.IQ4_XS.gguf b/llama-3.2-3b-babagpt-1.IQ4_XS.gguf new file mode 100644 index 0000000..62d7720 --- /dev/null +++ b/llama-3.2-3b-babagpt-1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce36dd34121edfd7659f7ccc70e3696a67c8f2a2095833769b05002f9beae77 +size 1840903200 diff --git a/llama-3.2-3b-babagpt-1.Q2_K.gguf b/llama-3.2-3b-babagpt-1.Q2_K.gguf new file mode 100644 index 0000000..95093bc --- /dev/null +++ b/llama-3.2-3b-babagpt-1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228268b4512012ed528977c3e0fd80addfb4fcfc953411e6f204253a85cf4ded +size 1363932192 diff --git a/llama-3.2-3b-babagpt-1.Q3_K_L.gguf b/llama-3.2-3b-babagpt-1.Q3_K_L.gguf new file mode 100644 index 0000000..ea9708e --- /dev/null +++ b/llama-3.2-3b-babagpt-1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa51dc3f14b17a93b011806009a74aac29adc94d7342449ffb739f22ba221bb +size 1815344160 diff --git a/llama-3.2-3b-babagpt-1.Q3_K_M.gguf b/llama-3.2-3b-babagpt-1.Q3_K_M.gguf new file mode 100644 index 0000000..1397f1e --- /dev/null +++ b/llama-3.2-3b-babagpt-1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b7af752535ec9ddd681637757bbddf7d16fe2e335f7fe1dcea3b56b79d530c6 +size 1687155744 diff --git a/llama-3.2-3b-babagpt-1.Q3_K_S.gguf b/llama-3.2-3b-babagpt-1.Q3_K_S.gguf new file mode 100644 index 0000000..f8db564 --- /dev/null +++ b/llama-3.2-3b-babagpt-1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b76682dfbbc0f71a1fd63e3475009ad7fabfcbc508639cc40b95da8ff702834 +size 1542845472 diff --git a/llama-3.2-3b-babagpt-1.Q4_K_M.gguf b/llama-3.2-3b-babagpt-1.Q4_K_M.gguf new file mode 100644 index 0000000..433513f --- /dev/null +++ b/llama-3.2-3b-babagpt-1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:730657359e36f3882d25781d7fa02b6aa08efb3e503a6ad8a86da0700c880a30 +size 2019374112 diff --git a/llama-3.2-3b-babagpt-1.Q4_K_S.gguf b/llama-3.2-3b-babagpt-1.Q4_K_S.gguf new file mode 100644 index 0000000..84d3e5e --- /dev/null +++ b/llama-3.2-3b-babagpt-1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f2ebcb55b0fff035a3774642f02c76f2fb7e4dc349a028130ea58e0a7421ee3 +size 1928197152 diff --git a/llama-3.2-3b-babagpt-1.Q5_K_M.gguf b/llama-3.2-3b-babagpt-1.Q5_K_M.gguf new file mode 100644 index 0000000..cd0579d --- /dev/null +++ b/llama-3.2-3b-babagpt-1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da22c418347cdcd14be6ec4ea3a069aea5b89c86e26f1e22e8b8db5360b950a3 +size 2322150432 diff --git a/llama-3.2-3b-babagpt-1.Q5_K_S.gguf b/llama-3.2-3b-babagpt-1.Q5_K_S.gguf new file mode 100644 index 0000000..1c2cdac --- /dev/null +++ b/llama-3.2-3b-babagpt-1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e9cee3869946784694b16e6d18a4a460525bd2ad6a1c2ff9af993c0fc853574 +size 2269508640 diff --git a/llama-3.2-3b-babagpt-1.Q6_K.gguf b/llama-3.2-3b-babagpt-1.Q6_K.gguf new file mode 100644 index 0000000..c2937a7 --- /dev/null +++ b/llama-3.2-3b-babagpt-1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71308b31a5f6edba5c9f125962606295dbd30985c0106eab175d2e348939a473 +size 2643850272 diff --git a/llama-3.2-3b-babagpt-1.Q8_0.gguf b/llama-3.2-3b-babagpt-1.Q8_0.gguf new file mode 100644 index 0000000..7d2634d --- /dev/null +++ b/llama-3.2-3b-babagpt-1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c16fbbe2af58d233edb5b26eee63c5f00c62c28d7a9f24881b5d47db63af29e8 +size 3421895712 diff --git a/llama-3.2-3b-babagpt-1.f16.gguf b/llama-3.2-3b-babagpt-1.f16.gguf new file mode 100644 index 0000000..095ac1d --- /dev/null +++ b/llama-3.2-3b-babagpt-1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd9ffb5c6505d94cbe23794de2b68a935d43f5bec8631d8bfdcbd45246a0c561 +size 6433684512