commit 1ee117ed03b6adbf31e34993f330e7fb6107e542 Author: ModelHub XC Date: Fri Jul 10 05:04:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6e0337b --- /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-FC-v1.1-think.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.1-think.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.1-think.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.1-think.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.1-think.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.1-think.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.1-think.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.1-think.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.1-think.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.1-think.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.1-think.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.1-think.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-FC-v1.1-think.IQ4_XS.gguf b/Llama-3.2-1B-FC-v1.1-think.IQ4_XS.gguf new file mode 100644 index 0000000..9e95966 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f77908214ab5c36ad27dc614121e60840c7e193aaf550c951b8c3f105fc12df7 +size 748384512 diff --git a/Llama-3.2-1B-FC-v1.1-think.Q2_K.gguf b/Llama-3.2-1B-FC-v1.1-think.Q2_K.gguf new file mode 100644 index 0000000..ca27c6b --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6494be21be7c3ff043a53702a326c41975ff9e831fec24681ec7cc920dbe4eac +size 580874496 diff --git a/Llama-3.2-1B-FC-v1.1-think.Q3_K_L.gguf b/Llama-3.2-1B-FC-v1.1-think.Q3_K_L.gguf new file mode 100644 index 0000000..1905374 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fef4fe0ce22762935cb1515353c5afd8fae44b85522a9ee90634e958084a38f +size 732524800 diff --git a/Llama-3.2-1B-FC-v1.1-think.Q3_K_M.gguf b/Llama-3.2-1B-FC-v1.1-think.Q3_K_M.gguf new file mode 100644 index 0000000..e4dbf4f --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08e30423c62395fb99976d65d9731e3ccf3dc9cd9a82c1c7d5a4fb1f821a9ffc +size 690843904 diff --git a/Llama-3.2-1B-FC-v1.1-think.Q3_K_S.gguf b/Llama-3.2-1B-FC-v1.1-think.Q3_K_S.gguf new file mode 100644 index 0000000..4176300 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5096208e3bfbc6da5f7b2ee438f6b82f81241d025723defedcc1bd092cd1facd +size 641691904 diff --git a/Llama-3.2-1B-FC-v1.1-think.Q4_K_M.gguf b/Llama-3.2-1B-FC-v1.1-think.Q4_K_M.gguf new file mode 100644 index 0000000..a9a05d7 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:647e5af6deabf44df0ded87886a41760ac62a87fe051e311689a19d8ac1b4302 +size 807694592 diff --git a/Llama-3.2-1B-FC-v1.1-think.Q4_K_S.gguf b/Llama-3.2-1B-FC-v1.1-think.Q4_K_S.gguf new file mode 100644 index 0000000..710f899 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8415c493921a85ececa15215ad13ab2b31cca35892eb8cc815d15ec426469e3 +size 775647488 diff --git a/Llama-3.2-1B-FC-v1.1-think.Q5_K_M.gguf b/Llama-3.2-1B-FC-v1.1-think.Q5_K_M.gguf new file mode 100644 index 0000000..95b7245 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cf60bba9ae06b6fccc2eafc03aa5e111950edb56b94a2203026029cc864aee5 +size 911503616 diff --git a/Llama-3.2-1B-FC-v1.1-think.Q5_K_S.gguf b/Llama-3.2-1B-FC-v1.1-think.Q5_K_S.gguf new file mode 100644 index 0000000..97cc254 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b40e9bf9b80db62e32ba84b95ed56ab75bff0cb3cc721121814ae83d9fff1c7 +size 892563712 diff --git a/Llama-3.2-1B-FC-v1.1-think.Q6_K.gguf b/Llama-3.2-1B-FC-v1.1-think.Q6_K.gguf new file mode 100644 index 0000000..6003cc2 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a90b50e71382ccb8064fe1a613bd6ebec17c3b2ea0e9da017986f180230688b +size 1021800704 diff --git a/Llama-3.2-1B-FC-v1.1-think.Q8_0.gguf b/Llama-3.2-1B-FC-v1.1-think.Q8_0.gguf new file mode 100644 index 0000000..705ed49 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8989e1b2846e5ca60c5fc819407bf2018837e72b2643d1241c1e70eb843098f +size 1321083136 diff --git a/Llama-3.2-1B-FC-v1.1-think.f16.gguf b/Llama-3.2-1B-FC-v1.1-think.f16.gguf new file mode 100644 index 0000000..3da7e42 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.1-think.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74b9c6dc5c422733781d127aa2db47921986aec90afe9812775c25e00ed87367 +size 2479595776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eaad924 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: AymanTarig/Llama-3.2-1B-FC-v3 +datasets: +- ThinkAgents/Function-Calling-with-Chain-of-Thoughts +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/AymanTarig/Llama-3.2-1B-FC-v3 + + +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-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.1-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.1-think.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. + +