commit 9b17f31b43bb7ded1a69a48acc089d19fd132e43 Author: ModelHub XC Date: Mon Sep 21 03:14:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-Chisato-Merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1361124 --- /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-Chisato-Merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-Chisato-Merged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-Chisato-Merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-Chisato-Merged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-Chisato-Merged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-Chisato-Merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-Chisato-Merged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-Chisato-Merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-Chisato-Merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-Chisato-Merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-Chisato-Merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-Chisato-Merged.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..33a9e03 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: ChisatoAI/TinyLlama-Chisato-Merged +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ChisatoAI/TinyLlama-Chisato-Merged + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyLlama-Chisato-Merged-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-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-Chisato-Merged-GGUF/resolve/main/TinyLlama-Chisato-Merged.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-Chisato-Merged.IQ4_XS.gguf b/TinyLlama-Chisato-Merged.IQ4_XS.gguf new file mode 100644 index 0000000..85a43e0 --- /dev/null +++ b/TinyLlama-Chisato-Merged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21426ee5cb155c51dc8e503f59e2f763838c4aa509a13bed71ffba3151b4e407 +size 609808192 diff --git a/TinyLlama-Chisato-Merged.Q2_K.gguf b/TinyLlama-Chisato-Merged.Q2_K.gguf new file mode 100644 index 0000000..c0c9edc --- /dev/null +++ b/TinyLlama-Chisato-Merged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60636bc0c9ab4c50eed37bc5c8e0693a8114287d206d6ddc40b27da25bc5dbeb +size 432131904 diff --git a/TinyLlama-Chisato-Merged.Q3_K_L.gguf b/TinyLlama-Chisato-Merged.Q3_K_L.gguf new file mode 100644 index 0000000..d00d33e --- /dev/null +++ b/TinyLlama-Chisato-Merged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e734fee674bcfabb4651bd75a61cff6bcdb775f4408ed7b0aba233a99a561bb +size 591527744 diff --git a/TinyLlama-Chisato-Merged.Q3_K_M.gguf b/TinyLlama-Chisato-Merged.Q3_K_M.gguf new file mode 100644 index 0000000..f09454a --- /dev/null +++ b/TinyLlama-Chisato-Merged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6384a516902429b188727e3f95b4e1d01ef7e435cfdac3a4ed0fd2683c35f33 +size 548405056 diff --git a/TinyLlama-Chisato-Merged.Q3_K_S.gguf b/TinyLlama-Chisato-Merged.Q3_K_S.gguf new file mode 100644 index 0000000..4385897 --- /dev/null +++ b/TinyLlama-Chisato-Merged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1498a7ee90273024b9c5836b10f5c16d20a3ef0cdb127baef0541fda681f7aec +size 499343168 diff --git a/TinyLlama-Chisato-Merged.Q4_K_M.gguf b/TinyLlama-Chisato-Merged.Q4_K_M.gguf new file mode 100644 index 0000000..d370487 --- /dev/null +++ b/TinyLlama-Chisato-Merged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:244925fc862cdbeec0def2b24f42b7fa4fd473bab6cef510e49cffa368aa34c0 +size 667815744 diff --git a/TinyLlama-Chisato-Merged.Q4_K_S.gguf b/TinyLlama-Chisato-Merged.Q4_K_S.gguf new file mode 100644 index 0000000..258ce50 --- /dev/null +++ b/TinyLlama-Chisato-Merged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b91ddbf1e6d50c155b0c533a22cb4e09768a097d9935f93f9ae76976c716708 +size 639872832 diff --git a/TinyLlama-Chisato-Merged.Q5_K_M.gguf b/TinyLlama-Chisato-Merged.Q5_K_M.gguf new file mode 100644 index 0000000..4c8d128 --- /dev/null +++ b/TinyLlama-Chisato-Merged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cccb9b4f2d7b8d7bf6082eb201435e7c04e07c11bef06f442bb7564444d7579 +size 782044992 diff --git a/TinyLlama-Chisato-Merged.Q5_K_S.gguf b/TinyLlama-Chisato-Merged.Q5_K_S.gguf new file mode 100644 index 0000000..bee34b9 --- /dev/null +++ b/TinyLlama-Chisato-Merged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96289cbc206e830afaf9de65fbc80900036bd9cd40d7570b105f227aec96519f +size 766029632 diff --git a/TinyLlama-Chisato-Merged.Q6_K.gguf b/TinyLlama-Chisato-Merged.Q6_K.gguf new file mode 100644 index 0000000..2370d2f --- /dev/null +++ b/TinyLlama-Chisato-Merged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b1db291c1a2a940a3e97ce79f5ccdfa9b197b9f26350de4b018cc5cf7cc27f9 +size 903413568 diff --git a/TinyLlama-Chisato-Merged.Q8_0.gguf b/TinyLlama-Chisato-Merged.Q8_0.gguf new file mode 100644 index 0000000..56635e7 --- /dev/null +++ b/TinyLlama-Chisato-Merged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74ee8cd542eebcd71d924276df8b3f0b25262e2f8553f6e410cb532d79ec43e9 +size 1169809216 diff --git a/TinyLlama-Chisato-Merged.f16.gguf b/TinyLlama-Chisato-Merged.f16.gguf new file mode 100644 index 0000000..bc1654e --- /dev/null +++ b/TinyLlama-Chisato-Merged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e0a5656bc539fcd3aa9c0bbafece00c872455631f811ee5eac99ae24527ea9f +size 2201018176