commit e05260c50f483b383817fcbd8223f21fd02d3aa7 Author: ModelHub XC Date: Mon Jun 29 08:44:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6709a6a --- /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 +Taiwan-LLM-7B-v2.0.1-chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +Taiwan-LLM-7B-v2.0.1-chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Taiwan-LLM-7B-v2.0.1-chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Taiwan-LLM-7B-v2.0.1-chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Taiwan-LLM-7B-v2.0.1-chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Taiwan-LLM-7B-v2.0.1-chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Taiwan-LLM-7B-v2.0.1-chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Taiwan-LLM-7B-v2.0.1-chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Taiwan-LLM-7B-v2.0.1-chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Taiwan-LLM-7B-v2.0.1-chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Taiwan-LLM-7B-v2.0.1-chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Taiwan-LLM-7B-v2.0.1-chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2512eea --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: yentinglin/Taiwan-LLM-7B-v2.0.1-chat +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/yentinglin/Taiwan-LLM-7B-v2.0.1-chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-i1-GGUF +## 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/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Taiwan-LLM-7B-v2.0.1-chat-GGUF/resolve/main/Taiwan-LLM-7B-v2.0.1-chat.f16.gguf) | f16 | 13.6 | 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/Taiwan-LLM-7B-v2.0.1-chat.IQ4_XS.gguf b/Taiwan-LLM-7B-v2.0.1-chat.IQ4_XS.gguf new file mode 100644 index 0000000..381b307 --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6c5e663b6df426906564f442ae454b4330f59277a108451d4b4f2980325d88a +size 3647518208 diff --git a/Taiwan-LLM-7B-v2.0.1-chat.Q2_K.gguf b/Taiwan-LLM-7B-v2.0.1-chat.Q2_K.gguf new file mode 100644 index 0000000..4a60812 --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1a1d7cf2f4c3fd1a53ef3a746f241a4010147a5224a7c8a8e10a5cc2fafe766 +size 2532865536 diff --git a/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_L.gguf b/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_L.gguf new file mode 100644 index 0000000..5467935 --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee032dc3a2f026215e4d1457fd3cbde9b3701046bcc7cb88bade4ecaf1df261 +size 3597112832 diff --git a/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_M.gguf b/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_M.gguf new file mode 100644 index 0000000..5c1f3bc --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a148219b53fd2d11242b23a6efd0a1b00c3f94d514fc1b0fa4a450d394cb5995 +size 3298006528 diff --git a/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_S.gguf b/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_S.gguf new file mode 100644 index 0000000..6b2e6f8 --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:969ba3febdc15e18ff53483d5b872bca0c203eca0843c483f34fa61f63789f87 +size 2948306432 diff --git a/Taiwan-LLM-7B-v2.0.1-chat.Q4_K_M.gguf b/Taiwan-LLM-7B-v2.0.1-chat.Q4_K_M.gguf new file mode 100644 index 0000000..4cd4413 --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be4080f5324cab700eba2eb3b371a7166485c8836a955bf3554c834835f300c4 +size 4081006080 diff --git a/Taiwan-LLM-7B-v2.0.1-chat.Q4_K_S.gguf b/Taiwan-LLM-7B-v2.0.1-chat.Q4_K_S.gguf new file mode 100644 index 0000000..f77973c --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd416af5c5acb49077cc6d0f2224a8e5f794ff7ef615a3dad2945e7dc22367d6 +size 3856741888 diff --git a/Taiwan-LLM-7B-v2.0.1-chat.Q5_K_M.gguf b/Taiwan-LLM-7B-v2.0.1-chat.Q5_K_M.gguf new file mode 100644 index 0000000..96571d0 --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b52fa2353e173d2a75339bc0f3e9c080f76d52fa48556a627937be99ac57d77b +size 4783158784 diff --git a/Taiwan-LLM-7B-v2.0.1-chat.Q5_K_S.gguf b/Taiwan-LLM-7B-v2.0.1-chat.Q5_K_S.gguf new file mode 100644 index 0000000..d5d852c --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a1deaee4bbf307d7aac8f145eb919416ebbf47af911c6244ccef8280415756 +size 4651693568 diff --git a/Taiwan-LLM-7B-v2.0.1-chat.Q6_K.gguf b/Taiwan-LLM-7B-v2.0.1-chat.Q6_K.gguf new file mode 100644 index 0000000..5096c28 --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3abf4abe3f7c464dbd645e1c3c6c4eb09bba06c70a71ae152d192e50c1516fee +size 5529196032 diff --git a/Taiwan-LLM-7B-v2.0.1-chat.Q8_0.gguf b/Taiwan-LLM-7B-v2.0.1-chat.Q8_0.gguf new file mode 100644 index 0000000..5f6b84e --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20023378400c2172ea962fc559703aca9567df6e64665779ecb65437d2747dfd +size 7161091584 diff --git a/Taiwan-LLM-7B-v2.0.1-chat.f16.gguf b/Taiwan-LLM-7B-v2.0.1-chat.f16.gguf new file mode 100644 index 0000000..70a84d1 --- /dev/null +++ b/Taiwan-LLM-7B-v2.0.1-chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa987af8f5cce2d9c5b0c2a5cd551761537129f670c9b4aa0a0192a63c777cb +size 13478106624