commit a4873f5fc4f932de5a2908aa744a565acb9b2637 Author: ModelHub XC Date: Mon May 4 16:24:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..31633a2 --- /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-Math-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-Math-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-Math-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-Math-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-Math-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-Math-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-Math-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-Math-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B-Chat-Math-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..26be3da --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: theuerc/TinyLlama-1.1B-Chat-Math-v1.0 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/theuerc/TinyLlama-1.1B-Chat-Math-v1.0 + + +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-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Chat-Math-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-Math-v1.0.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.IQ4_XS.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..315b18a --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41a9d20fe00485aa0d7d10523f2407b16248aff2ac4eb283f3304088f4d1e014 +size 609808256 diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.Q2_K.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.Q2_K.gguf new file mode 100644 index 0000000..be58b0f --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23b57f0094d096930a3bc2d1c3ac6387f972637db4f02b22af63e3c34b78466 +size 432131968 diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_L.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..7d5ff7a --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3183e88a6aba7b6e8887d84a2ef54ead0c08e9561c1f45edf5b404ec651b9622 +size 591527808 diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_M.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..b5fb3ac --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b6670500023668130494f9806f68b6396ce1859a989b299d2c73f9e9f7e3d9b +size 548405120 diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_S.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..7e52e6e --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53c4ad251f8ff2033300c899fd146021566aeef8bc061c3ab709499ad4fa6a6e +size 499343232 diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.Q4_K_M.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..70935e6 --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7f8acd8e23f0cd783ad72487d836414e9c9ca32d4a7975301206482bf09d3e8 +size 667815808 diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.Q4_K_S.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..61e2d9e --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b01476ab14b855ae277729d310115808dfb8cdd099b5142e176d6bc6d96b51ad +size 639872896 diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.Q5_K_M.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..91b1993 --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:403f14823cfb010c2890af644c1e333ad1451b635feb7496664e2cd30e3b2840 +size 782045056 diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.Q5_K_S.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..74dc856 --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:207b89bc210045412d7956cfd3e870f825e6d50ac00844dfc9b6147ffb242a18 +size 766029696 diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.Q6_K.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.Q6_K.gguf new file mode 100644 index 0000000..2ef2982 --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09301084d441d5b5b88178e43bbfa5ca23d85c222d59aedf216fb2bbdb0275af +size 903413632 diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.Q8_0.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.Q8_0.gguf new file mode 100644 index 0000000..cc01672 --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7818b6fa3fe409ef63f406e1967ed06ea3f5742b0d45660652d7ce96571b4ce +size 1169809280 diff --git a/TinyLlama-1.1B-Chat-Math-v1.0.f16.gguf b/TinyLlama-1.1B-Chat-Math-v1.0.f16.gguf new file mode 100644 index 0000000..3898e78 --- /dev/null +++ b/TinyLlama-1.1B-Chat-Math-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0d15a93f985cf697804ca9ab693e4e3f23ffada129ec8ca1f356f597ba80375 +size 2201018240