commit 5b7e6989c23ec964963f1c2590ceb3c8e11d9ef4 Author: ModelHub XC Date: Thu Oct 1 01:53:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6aed34d --- /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-cat-persona-p1-minimal.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-cat-persona-p1-minimal.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-cat-persona-p1-minimal.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-cat-persona-p1-minimal.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-cat-persona-p1-minimal.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-cat-persona-p1-minimal.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-cat-persona-p1-minimal.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-cat-persona-p1-minimal.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-cat-persona-p1-minimal.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-cat-persona-p1-minimal.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-cat-persona-p1-minimal.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-cat-persona-p1-minimal.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..84fc025 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: amangeld/llama-3.2-1b-cat-persona-p1-minimal +language: +- en +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/amangeld/llama-3.2-1b-cat-persona-p1-minimal + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.2-1b-cat-persona-p1-minimal-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-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-1b-cat-persona-p1-minimal-GGUF/resolve/main/llama-3.2-1b-cat-persona-p1-minimal.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. + + diff --git a/llama-3.2-1b-cat-persona-p1-minimal.IQ4_XS.gguf b/llama-3.2-1b-cat-persona-p1-minimal.IQ4_XS.gguf new file mode 100644 index 0000000..6119dcc --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff91ac4a84311594ab4095ebfe41113f7fda8dbe67a178f05cfaff9ac95335bd +size 748384928 diff --git a/llama-3.2-1b-cat-persona-p1-minimal.Q2_K.gguf b/llama-3.2-1b-cat-persona-p1-minimal.Q2_K.gguf new file mode 100644 index 0000000..fe3a257 --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a935999b02cf9fc9c3b21438407445587cba40a3eb91da78d77bc356c255a6e +size 580874912 diff --git a/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_L.gguf b/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_L.gguf new file mode 100644 index 0000000..c63797c --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:745366039ba7070bdd5ca1fbf16808df319af15de9fbd61f6407a56d94ec0a53 +size 732525216 diff --git a/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_M.gguf b/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_M.gguf new file mode 100644 index 0000000..d148476 --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051139a5e1d61fbdfc6274f52ccfb4798981109d965df40299edcbb5ad376c53 +size 690844320 diff --git a/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_S.gguf b/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_S.gguf new file mode 100644 index 0000000..23a7bd4 --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f393edd9c44f195c74800ecea9445265efb4f23518fd618f11ca65a497ff7dc6 +size 641692320 diff --git a/llama-3.2-1b-cat-persona-p1-minimal.Q4_K_M.gguf b/llama-3.2-1b-cat-persona-p1-minimal.Q4_K_M.gguf new file mode 100644 index 0000000..e31e475 --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aafd619126c6093f23aec0ffcb8829782ecf98e0597780b5de7d69b716b54251 +size 807695008 diff --git a/llama-3.2-1b-cat-persona-p1-minimal.Q4_K_S.gguf b/llama-3.2-1b-cat-persona-p1-minimal.Q4_K_S.gguf new file mode 100644 index 0000000..5d1b398 --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ade44e0db43c2e3d13739563744e25db29b5496470b3bc7c43d9be20dd0e8e5 +size 775647904 diff --git a/llama-3.2-1b-cat-persona-p1-minimal.Q5_K_M.gguf b/llama-3.2-1b-cat-persona-p1-minimal.Q5_K_M.gguf new file mode 100644 index 0000000..661a200 --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94485780869345f41e01197f5bddb5efc08db713bed8dd8554e0d390fcbbf8d4 +size 911504032 diff --git a/llama-3.2-1b-cat-persona-p1-minimal.Q5_K_S.gguf b/llama-3.2-1b-cat-persona-p1-minimal.Q5_K_S.gguf new file mode 100644 index 0000000..ed5ccb8 --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4de0aec1a141573b3ac8b28f9193a141a635ce6d53078881d1ee2bdb06b3f9fa +size 892564128 diff --git a/llama-3.2-1b-cat-persona-p1-minimal.Q6_K.gguf b/llama-3.2-1b-cat-persona-p1-minimal.Q6_K.gguf new file mode 100644 index 0000000..6313944 --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3f418c2a3214da3ea765578b4ebe69a2fa94a4dda2396152c57f03545ccc0a6 +size 1021801120 diff --git a/llama-3.2-1b-cat-persona-p1-minimal.Q8_0.gguf b/llama-3.2-1b-cat-persona-p1-minimal.Q8_0.gguf new file mode 100644 index 0000000..1cea764 --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9dc02f3691b58ed196796ac33d42d532bc0a2f6bb04d92d99d1e6334789702a +size 1321083552 diff --git a/llama-3.2-1b-cat-persona-p1-minimal.f16.gguf b/llama-3.2-1b-cat-persona-p1-minimal.f16.gguf new file mode 100644 index 0000000..5f06fb5 --- /dev/null +++ b/llama-3.2-1b-cat-persona-p1-minimal.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:579efddc759cf8380312aba705e1bb44b2b9ece817bb6ff5dc857e3006281ad6 +size 2479596192