commit f245207c402fc7cffb1e7cb4d49ffa12d6ac755d Author: ModelHub XC Date: Wed Jun 24 11:53:17 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_V2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..721a295 --- /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_V2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling_V2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling_V2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling_V2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling_V2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling_V2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling_V2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling_V2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1B_Intruct_Tool_Calling_V2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.IQ4_XS.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.IQ4_XS.gguf new file mode 100644 index 0000000..e6ac1f6 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020438a12d9aa2583aa98f3f3d8d14fc49305371e7fdffc5f9b050cf362201cb +size 748382240 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q2_K.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q2_K.gguf new file mode 100644 index 0000000..3d17737 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66751e3f983d887298c77a5aad5c66655e4b643169b152c71f8d9cfcfaf107d0 +size 580872224 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_L.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_L.gguf new file mode 100644 index 0000000..f067f20 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:911fdf0c511ea936df107aa0f3d574bd008ebbd0f4edbb5a40c27abcd37b2a26 +size 732522528 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_M.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_M.gguf new file mode 100644 index 0000000..fc40c27 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e3c26b6c6826073bad261ef8a2e0995e718b88e90e9393cc632111f92b7c51a +size 690841632 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_S.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_S.gguf new file mode 100644 index 0000000..8d7677a --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b70ea56e704d5f3cd49f525e22ef89495d0f96a5dfca167fec8e876fdd013f78 +size 641689632 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q4_K_M.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q4_K_M.gguf new file mode 100644 index 0000000..894955a --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a13da69b498c560965ad15b5eede6dffacd5eb985759070a5b35575ed6a801c +size 807692320 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q4_K_S.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q4_K_S.gguf new file mode 100644 index 0000000..61c894f --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70e146136fa48accffcf55660eee654045bfe3db1a8d7bfe53731deb37d6b4bb +size 775645216 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q5_K_M.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q5_K_M.gguf new file mode 100644 index 0000000..ad46358 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4481a06f9ad922a463d4c873c7c1cf2d6733371b7830ce8e6e679c044296bb39 +size 911501344 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q5_K_S.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q5_K_S.gguf new file mode 100644 index 0000000..b1616cb --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:531e147e665acc5a35aec6501d2a6b375d883bced82de7deecbf3e5012d6d823 +size 892561440 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q6_K.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q6_K.gguf new file mode 100644 index 0000000..563ec26 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bba4cfe417f401df2b60a707c1804cc1d9363d0c4886dc962b70cc4dd98e176 +size 1021798432 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q8_0.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q8_0.gguf new file mode 100644 index 0000000..72d10ff --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ebae690aa966159544cee5bb3c37cb397be6742ac4f99dfa1b5af0924aed11b +size 1321080864 diff --git a/Llama_3.2_1B_Intruct_Tool_Calling_V2.f16.gguf b/Llama_3.2_1B_Intruct_Tool_Calling_V2.f16.gguf new file mode 100644 index 0000000..4059df9 --- /dev/null +++ b/Llama_3.2_1B_Intruct_Tool_Calling_V2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3292e41a94e885ad8731fe6c8030a3ff932dbf147d77514fae09d150be7a082 +size 2479593504 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8d88ba4 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: nguyenthanhthuan/Llama_3.2_1B_Intruct_Tool_Calling_V2 +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_V2 + + + +***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_V2-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_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1B_Intruct_Tool_Calling_V2-GGUF/resolve/main/Llama_3.2_1B_Intruct_Tool_Calling_V2.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. + +