commit 13c1f9e3029be4e53c472a85d85d00ba44f9ed77 Author: ModelHub XC Date: Sun Oct 11 13:15:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyChat-200m-2x16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2288300 --- /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 +TinyChat-200m-2x16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyChat-200m-2x16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyChat-200m-2x16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyChat-200m-2x16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyChat-200m-2x16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyChat-200m-2x16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyChat-200m-2x16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyChat-200m-2x16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyChat-200m-2x16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyChat-200m-2x16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyChat-200m-2x16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyChat-200m-2x16.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e12cdf8 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: FlameF0X/TinyChat-200m-2x16 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/FlameF0X/TinyChat-200m-2x16 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyChat-200m-2x16-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/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.Q5_K_S.gguf) | Q5_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.Q5_K_M.gguf) | Q5_K_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.Q6_K.gguf) | Q6_K | 0.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyChat-200m-2x16-GGUF/resolve/main/TinyChat-200m-2x16.f16.gguf) | f16 | 0.5 | 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/TinyChat-200m-2x16.IQ4_XS.gguf b/TinyChat-200m-2x16.IQ4_XS.gguf new file mode 100644 index 0000000..15ca9bf --- /dev/null +++ b/TinyChat-200m-2x16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dcd237fbe4ceac5d1b24dd11a917f97624e25655f0b414cdf6f97a441c9465d +size 118533184 diff --git a/TinyChat-200m-2x16.Q2_K.gguf b/TinyChat-200m-2x16.Q2_K.gguf new file mode 100644 index 0000000..8a7f266 --- /dev/null +++ b/TinyChat-200m-2x16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be972b050353e948dd973bb4b6fe2b2fde6b05eb1519093f7eac4057218702fe +size 112045120 diff --git a/TinyChat-200m-2x16.Q3_K_L.gguf b/TinyChat-200m-2x16.Q3_K_L.gguf new file mode 100644 index 0000000..71298b0 --- /dev/null +++ b/TinyChat-200m-2x16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04a0c3b69b9547cd18304b69535173614ad3b1efccdc4fe668b139897319852 +size 127140928 diff --git a/TinyChat-200m-2x16.Q3_K_M.gguf b/TinyChat-200m-2x16.Q3_K_M.gguf new file mode 100644 index 0000000..d0f5a5a --- /dev/null +++ b/TinyChat-200m-2x16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd99bcd89fc9b29870304ad1a51bdeeb5c37387b252495cd5894b6e45cc96b1e +size 119906368 diff --git a/TinyChat-200m-2x16.Q3_K_S.gguf b/TinyChat-200m-2x16.Q3_K_S.gguf new file mode 100644 index 0000000..77edf97 --- /dev/null +++ b/TinyChat-200m-2x16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32bebf787b69f46cc030f1c2e98b213d027994cb1731204a48a4a7dcb8a087b1 +size 112045120 diff --git a/TinyChat-200m-2x16.Q4_K_M.gguf b/TinyChat-200m-2x16.Q4_K_M.gguf new file mode 100644 index 0000000..cf6a0f0 --- /dev/null +++ b/TinyChat-200m-2x16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fda74ccca564a8c39622ff24f790702b8a0e5518ffb75752196442fea741674 +size 143385664 diff --git a/TinyChat-200m-2x16.Q4_K_S.gguf b/TinyChat-200m-2x16.Q4_K_S.gguf new file mode 100644 index 0000000..5a7d2de --- /dev/null +++ b/TinyChat-200m-2x16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356d6e4164568729b727c31f78536444b3e9f770e70f20285770e7f763f5c5ea +size 136528960 diff --git a/TinyChat-200m-2x16.Q5_K_M.gguf b/TinyChat-200m-2x16.Q5_K_M.gguf new file mode 100644 index 0000000..9287f65 --- /dev/null +++ b/TinyChat-200m-2x16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3547db0c80ef7dc86b91f614c90d2cbf83c8811e17ef8a3a7ba1641eba97910 +size 155074624 diff --git a/TinyChat-200m-2x16.Q5_K_S.gguf b/TinyChat-200m-2x16.Q5_K_S.gguf new file mode 100644 index 0000000..e15f362 --- /dev/null +++ b/TinyChat-200m-2x16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f361e34b8ceb2aba741fc0bd0eb5feb460054aac355c0a3a3636339432d63d59 +size 151176256 diff --git a/TinyChat-200m-2x16.Q6_K.gguf b/TinyChat-200m-2x16.Q6_K.gguf new file mode 100644 index 0000000..5d2fa91 --- /dev/null +++ b/TinyChat-200m-2x16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f594c59d1f7694f3fbdd7115e1c6584abe9d1081ccf668b58c0d468eca767e +size 199584832 diff --git a/TinyChat-200m-2x16.Q8_0.gguf b/TinyChat-200m-2x16.Q8_0.gguf new file mode 100644 index 0000000..4f9a933 --- /dev/null +++ b/TinyChat-200m-2x16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71ce2d89eb22b50736401e3ecac2400275b362097470eb9c5beddd07b93bab0e +size 213298240 diff --git a/TinyChat-200m-2x16.f16.gguf b/TinyChat-200m-2x16.f16.gguf new file mode 100644 index 0000000..0800b64 --- /dev/null +++ b/TinyChat-200m-2x16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:522b6c4a686e50e11b9561183b4a083866734fb68e4e2db20db48b3d0ef5c4f1 +size 400567360