commit 5af8a389301fabc50a1bdb1a8254451233f7067e Author: ModelHub XC Date: Thu Jun 25 16:11:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..889a54f --- /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_Intruct_Tool_Calling.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.IQ4_XS.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.IQ4_XS.gguf new file mode 100644 index 0000000..187bcc6 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b95afa18231f84a69d6c478db13234da347ceb0386fd7d0a4107064e75fe60b8 +size 748382112 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.Q2_K.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.Q2_K.gguf new file mode 100644 index 0000000..9196e88 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e8aba575c976fc1a649dc5d9046e3b8a147fa6666ade4eb0f7eb6d07a1457ec +size 580872096 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_L.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_L.gguf new file mode 100644 index 0000000..112a937 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:262a2b0f0927d5e9ac389fe068e2ba2d3bb82ec68f6417d2ffb351b36bdc7e52 +size 732522400 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_M.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_M.gguf new file mode 100644 index 0000000..9f83a66 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:834b7232e077a419141821c6908db9e59fdbc90866dcfb6eded1de0d21dd0ffc +size 690841504 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_S.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_S.gguf new file mode 100644 index 0000000..fc55a66 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d52164d7e45e6988511f9d3f1875da47803104ed4d9e9fb98ca97e4c3f1a6f3 +size 641689504 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.Q4_K_M.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.Q4_K_M.gguf new file mode 100644 index 0000000..a66745d --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4dda99d0ab1fafffbb9a40e2cb52c64404fde40f5f91224836752fb903cfcf0 +size 807692192 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.Q4_K_S.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.Q4_K_S.gguf new file mode 100644 index 0000000..7958c87 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ccd0ce80ffd0a92931aed49579b58f4f8bf2f16dd9ba5950c5f0542713bce42 +size 775645088 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.Q5_K_M.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.Q5_K_M.gguf new file mode 100644 index 0000000..2153df8 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d77f5a8f415573ff4717b6ab758a3ddaf084c35c75c76de98c09396a73957d +size 911501216 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.Q5_K_S.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.Q5_K_S.gguf new file mode 100644 index 0000000..5ed0e48 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1cb6b954a5a53650c37ef75d68088a576f0712bd1f1184e34eb24edc69fe8bb +size 892561312 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.Q6_K.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.Q6_K.gguf new file mode 100644 index 0000000..45582e0 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1802cc73df24d0c51eda7b92dec0cb62920b4259dc17d79337cb7ccd0215089 +size 1021798304 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.Q8_0.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.Q8_0.gguf new file mode 100644 index 0000000..debcf9a --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df932ae4253794216bb4e6b194dd180584dc16717a767487e63cb12f410ba57d +size 1321080736 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling.f16.gguf b/Llama_3.2_1B_Intruct_Tool_Calling.f16.gguf new file mode 100644 index 0000000..e90156f --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f529e2c40ca36c9a188360c6d3adafd69f80deda958a2d03b5f86a3e187956c4 +size 2479593376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4bfc19f --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: nguyenthanhthuan/Llama_3.2_1B_Intruct_Tool_Calling +datasets: +- nguyenthanhthuan/function-calling-sharegpt +language: +- en +- vi +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- Ollama +- Tool-Calling +--- +## About + + + + + + +static quants of https://huggingface.co/nguyenthanhthuan/Llama_3.2_1B_Intruct_Tool_Calling + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama_3.2_1B_Intruct_Tool_Calling-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_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling.f16.gguf) | f16 | 2.6 | 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. + +