commit 7fdd24dd615ff937a71192652c8fb6181c6e02d7 Author: ModelHub XC Date: Sat May 9 05:09:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6d44602 --- /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 +TinyLlama-1.1B-Chat-finetune.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-finetune.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-finetune.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-finetune.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-finetune.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-finetune.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-finetune.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-finetune.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-finetune.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-finetune.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-finetune.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-finetune.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7ff4b68 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: misaeboca/TinyLlama-1.1B-Chat-finetune +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/misaeboca/TinyLlama-1.1B-Chat-finetune + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyLlama-1.1B-Chat-finetune-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/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-finetune-GGUF/resolve/main/TinyLlama-1.1B-Chat-finetune.f16.gguf) | f16 | 2.3 | 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/TinyLlama-1.1B-Chat-finetune.IQ4_XS.gguf b/TinyLlama-1.1B-Chat-finetune.IQ4_XS.gguf new file mode 100644 index 0000000..7e9eb02 --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eacfa1aa91b7935a35cd288fc45c476eb104516e8cf1830ed6335f028aab41f9 +size 609808288 diff --git a/TinyLlama-1.1B-Chat-finetune.Q2_K.gguf b/TinyLlama-1.1B-Chat-finetune.Q2_K.gguf new file mode 100644 index 0000000..f40ed28 --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e91ba5928b304b9e6f81a112a25835f9c593919477bc64d55e3a0390ff0e88 +size 432132000 diff --git a/TinyLlama-1.1B-Chat-finetune.Q3_K_L.gguf b/TinyLlama-1.1B-Chat-finetune.Q3_K_L.gguf new file mode 100644 index 0000000..111f24e --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b9f0cf27c99f380e84bed0e0e81f25185d14355b8077630e41f902002ad26b +size 591527840 diff --git a/TinyLlama-1.1B-Chat-finetune.Q3_K_M.gguf b/TinyLlama-1.1B-Chat-finetune.Q3_K_M.gguf new file mode 100644 index 0000000..f1df21a --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de40103e7bc4d820a733ee34a78fc229369477e44734c827cd1a0b9e87b2eb5 +size 548405152 diff --git a/TinyLlama-1.1B-Chat-finetune.Q3_K_S.gguf b/TinyLlama-1.1B-Chat-finetune.Q3_K_S.gguf new file mode 100644 index 0000000..6ac157e --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82778a04ab2059edb9155308b8ee7981accb71c2c36299234bdf90925f33500e +size 499343264 diff --git a/TinyLlama-1.1B-Chat-finetune.Q4_K_M.gguf b/TinyLlama-1.1B-Chat-finetune.Q4_K_M.gguf new file mode 100644 index 0000000..1182495 --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a588479837f76cd7e881199477cda8e53138274a0bef9ce71601b8ff02ffd4 +size 667815840 diff --git a/TinyLlama-1.1B-Chat-finetune.Q4_K_S.gguf b/TinyLlama-1.1B-Chat-finetune.Q4_K_S.gguf new file mode 100644 index 0000000..0d3f0f3 --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad496b23c8d8b3c97910d2c00f6a4a8ea21feeab2f5c533c8aa591724f4dc338 +size 639872928 diff --git a/TinyLlama-1.1B-Chat-finetune.Q5_K_M.gguf b/TinyLlama-1.1B-Chat-finetune.Q5_K_M.gguf new file mode 100644 index 0000000..fc9374d --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6918633a09e368a5166ee31911a4c0e48bb12f661279bcd7907684d7888d0c57 +size 782045088 diff --git a/TinyLlama-1.1B-Chat-finetune.Q5_K_S.gguf b/TinyLlama-1.1B-Chat-finetune.Q5_K_S.gguf new file mode 100644 index 0000000..fdfcac1 --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef389baa36a084d815f864806696e1775bf6466955cf218110d112ebda938dda +size 766029728 diff --git a/TinyLlama-1.1B-Chat-finetune.Q6_K.gguf b/TinyLlama-1.1B-Chat-finetune.Q6_K.gguf new file mode 100644 index 0000000..3ab21d6 --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b5d0cbdcaf18a188c23dbdb6709899d62441b73bce121be51d0b078caf9766 +size 903413664 diff --git a/TinyLlama-1.1B-Chat-finetune.Q8_0.gguf b/TinyLlama-1.1B-Chat-finetune.Q8_0.gguf new file mode 100644 index 0000000..aaecec0 --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:861ebf66fce2bdff53121c3653dfb037a54fe4850acee46039e03fbb94ad2771 +size 1169809312 diff --git a/TinyLlama-1.1B-Chat-finetune.f16.gguf b/TinyLlama-1.1B-Chat-finetune.f16.gguf new file mode 100644 index 0000000..804c345 --- /dev/null +++ b/TinyLlama-1.1B-Chat-finetune.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4198a96bc401961ae3d4be927886745ae2dc8a4f3f002d6a3c4bd7aa3152153f +size 2201018272