commit 03d477520bfc6eb060cac6b75b4df1abebcfe453 Author: ModelHub XC Date: Tue Apr 21 07:28:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1189d8b --- /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-OpenHermes-2.5-Chat-v0.1-sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.f16.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6d0997b --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft +datasets: +- teknium/OpenHermes-2.5 +- abhinand/ultrachat_200k_sharegpt +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft + + +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-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft-GGUF/resolve/main/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.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-OpenHermes-2.5-Chat-v0.1-sft.IQ4_XS.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.IQ4_XS.gguf new file mode 100644 index 0000000..a7a34c3 --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:882c9150f1ae8c585c9fc39f570c8bfe018043916a36e2ad38411b3c9bd0e29b +size 609814688 diff --git a/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q2_K.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q2_K.gguf new file mode 100644 index 0000000..0f62e9c --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acac0bc7888ea45b6af2de1da686feb553ff89cde2cc44a1067047bfcbb07df4 +size 432137568 diff --git a/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_L.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_L.gguf new file mode 100644 index 0000000..9d5c787 --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:573edfd49289998cdf09135114d864512e7955a6013e5664d4f53cf15e017197 +size 591533824 diff --git a/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_M.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_M.gguf new file mode 100644 index 0000000..349f9b0 --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:758e690b62215f55d5d26d09058b7e8b1e40ced61731e1308d9b32905a7ff168 +size 548411136 diff --git a/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_S.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_S.gguf new file mode 100644 index 0000000..f6c4497 --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8824d327db449606f85a0bfb478a01c9abdd4d7898451ab1c9cd095e0c9925 +size 499349248 diff --git a/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q4_K_M.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q4_K_M.gguf new file mode 100644 index 0000000..a72ba62 --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8d0c3fe7508bc32e14e70c74a626ee575d29e6a56b0c61e7d927edc3ada50fa +size 667822368 diff --git a/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q4_K_S.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q4_K_S.gguf new file mode 100644 index 0000000..4a8cb59 --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610bb709f06bad553ef10418749a43a2292a3866448516c0fd525a9e759fbc3c +size 639879456 diff --git a/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q5_K_M.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q5_K_M.gguf new file mode 100644 index 0000000..fc92ed9 --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa259259667b8b0169237c62c5c61eaba05831c326c1e5c525f6559b90fe1ac2 +size 782052128 diff --git a/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q5_K_S.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q5_K_S.gguf new file mode 100644 index 0000000..20a9566 --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe5d5183599b22248468d6a1f3565316de6f8b3a66f39f2de3db21a0080b06a +size 766036768 diff --git a/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q6_K.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q6_K.gguf new file mode 100644 index 0000000..0a2df29 --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:091ae2c51669030ff92402026560cdf8c1a453e81d833f649d1906994da14911 +size 903421248 diff --git a/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q8_0.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q8_0.gguf new file mode 100644 index 0000000..3a8ed59 --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7ec920799066ef03fc32313a4c3a0f1935118a7d9fec6325f1a15a56a6e26b5 +size 1169818880 diff --git a/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.f16.gguf b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.f16.gguf new file mode 100644 index 0000000..b55a8d6 --- /dev/null +++ b/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:830006ed6bbc05cf6df4c0646b00565ec5c8ee1bea8acec39d23aa33dbce8da1 +size 2201035520