commit f243f84e69f6e7dab36fa2639d23f9e0a4f38364 Author: ModelHub XC Date: Sat May 23 18:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/titulm-mpt-1b-v2.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d10e59a --- /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 +titulm-mpt-1b-v2.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +titulm-mpt-1b-v2.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +titulm-mpt-1b-v2.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +titulm-mpt-1b-v2.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +titulm-mpt-1b-v2.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +titulm-mpt-1b-v2.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +titulm-mpt-1b-v2.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +titulm-mpt-1b-v2.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +titulm-mpt-1b-v2.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +titulm-mpt-1b-v2.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +titulm-mpt-1b-v2.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +titulm-mpt-1b-v2.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ed4a125 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: hishab/titulm-mpt-1b-v2.0 +datasets: +- togethercomputer/RedPajama-Data-V2 +- uonlp/CulturaX +- wikipedia +language: +- en +- bn +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/hishab/titulm-mpt-1b-v2.0 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-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/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.IQ4_XS.gguf) | IQ4_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.Q5_K_S.gguf) | Q5_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.Q5_K_M.gguf) | Q5_K_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.Q6_K.gguf) | Q6_K | 1.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.Q8_0.gguf) | Q8_0 | 1.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/titulm-mpt-1b-v2.0-GGUF/resolve/main/titulm-mpt-1b-v2.0.f16.gguf) | f16 | 2.8 | 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/titulm-mpt-1b-v2.0.IQ4_XS.gguf b/titulm-mpt-1b-v2.0.IQ4_XS.gguf new file mode 100644 index 0000000..4c937ce --- /dev/null +++ b/titulm-mpt-1b-v2.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dbe307dc72f8c9220bd529714cf7be240732b0e0d9e912ec346504b0566570f +size 791817600 diff --git a/titulm-mpt-1b-v2.0.Q2_K.gguf b/titulm-mpt-1b-v2.0.Q2_K.gguf new file mode 100644 index 0000000..f670eb2 --- /dev/null +++ b/titulm-mpt-1b-v2.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e1e05593aed25adb78471302f5f9294c527e23b33d8858129b5c945a96d69c5 +size 589704576 diff --git a/titulm-mpt-1b-v2.0.Q3_K_L.gguf b/titulm-mpt-1b-v2.0.Q3_K_L.gguf new file mode 100644 index 0000000..c392594 --- /dev/null +++ b/titulm-mpt-1b-v2.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c878c50d711df499c4bb009ef7c340d17c1545dc186ab675f92f00cb93c960f +size 831139200 diff --git a/titulm-mpt-1b-v2.0.Q3_K_M.gguf b/titulm-mpt-1b-v2.0.Q3_K_M.gguf new file mode 100644 index 0000000..10cced2 --- /dev/null +++ b/titulm-mpt-1b-v2.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e09bda0d354dc1393144c9023e3388ce5250f587b2d8a5ab809c41d45357be +size 770321792 diff --git a/titulm-mpt-1b-v2.0.Q3_K_S.gguf b/titulm-mpt-1b-v2.0.Q3_K_S.gguf new file mode 100644 index 0000000..fbeae25 --- /dev/null +++ b/titulm-mpt-1b-v2.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c34474c7348a8af093c4878e296e9fda3a3a8a6398773c4461b9a7152beab25f +size 661269888 diff --git a/titulm-mpt-1b-v2.0.Q4_K_M.gguf b/titulm-mpt-1b-v2.0.Q4_K_M.gguf new file mode 100644 index 0000000..554edde --- /dev/null +++ b/titulm-mpt-1b-v2.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af80f33ab34d75dc5c4cf1a4619b5f92be3ed359430cd5c47f019e84040d5533 +size 911355264 diff --git a/titulm-mpt-1b-v2.0.Q4_K_S.gguf b/titulm-mpt-1b-v2.0.Q4_K_S.gguf new file mode 100644 index 0000000..cf00644 --- /dev/null +++ b/titulm-mpt-1b-v2.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:014abd82dcaf4e3fec2d9e74bf2a513abaf48212e480da05a1a2f3e45f327f5a +size 827993472 diff --git a/titulm-mpt-1b-v2.0.Q5_K_M.gguf b/titulm-mpt-1b-v2.0.Q5_K_M.gguf new file mode 100644 index 0000000..6f996d6 --- /dev/null +++ b/titulm-mpt-1b-v2.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f54560f071167c0296e4837a86f476802b638ab9b5f65305c46b626dd106a8 +size 1039543680 diff --git a/titulm-mpt-1b-v2.0.Q5_K_S.gguf b/titulm-mpt-1b-v2.0.Q5_K_S.gguf new file mode 100644 index 0000000..a79e958 --- /dev/null +++ b/titulm-mpt-1b-v2.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e1708f783ea3f3a897596c1e05c2c6da17b6e0021437e338e1eab28d4eec89f +size 972696960 diff --git a/titulm-mpt-1b-v2.0.Q6_K.gguf b/titulm-mpt-1b-v2.0.Q6_K.gguf new file mode 100644 index 0000000..1c43fa3 --- /dev/null +++ b/titulm-mpt-1b-v2.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10e34cf4d83fb6e99b9ec4c9053e8b2a9acc316df9ee9747c954976bee0b29dc +size 1133129088 diff --git a/titulm-mpt-1b-v2.0.Q8_0.gguf b/titulm-mpt-1b-v2.0.Q8_0.gguf new file mode 100644 index 0000000..6df3727 --- /dev/null +++ b/titulm-mpt-1b-v2.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e59b7c37cb15598e9dd7e60b70d439957b151a2a04cc5ca49ce78496924f9fbd +size 1461393792 diff --git a/titulm-mpt-1b-v2.0.f16.gguf b/titulm-mpt-1b-v2.0.f16.gguf new file mode 100644 index 0000000..d9a8d89 --- /dev/null +++ b/titulm-mpt-1b-v2.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66af2e1da494386c9dd86e62983b3d5dbbc6222c72e73210902a7516e00bb5c1 +size 2732095872