diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* 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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index 32897cd3e640101ba184f8c4ccd896981de3804a..694e610611a9e8c5720ba34b5563dbbe7abdd0bb 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,197 @@ --- license: mit +library_name: transformers +pipeline_tag: text-generation +tags: +- vLLM +- compressed-tensors +- INT4 +- INT8 +- W4A16 +- W8A16 +base_model: + - ZhipuAI/GLM-5.2 +base_model_relation: quantized + --- +# GLM-5.2-Int4-Int8Mix +Base model: [ZhipuAI/GLM-5.2](https://www.modelscope.cn/models/ZhipuAI/GLM-5.2) + +This repo quantizes the model using a data-free quantization tool. + +(no calibration dataset was involved) + +This release is prepared for **vLLM** with `compressed-tensors` weight-only A16 inference. It does not claim compatibility with SGLang or other runtimes. + +The default `reasoning_effort` is changed to `medium-high` to reduce thinking-token cost. You can override it per request with `"chat_template_kwargs": {"reasoning_effort": "max"}`, or edit `chat_template.jinja` to set a different default. + +### 【Quantization Policy】 + +| Scope | Format | +|-------|--------| +| `model.layers.0` | BF16 | +| `model.layers.1` - `model.layers.2` | W8A16, group size 128 | +| `model.layers.3` - `model.layers.77` ordinary linear weights | W8A16, group size 128 | +| `model.layers.3` - `model.layers.77` MoE expert weights | W4A16, group size 128 | +| `model.layers.78` MTP block | W8A16, channelwise | +| `mlp.gate.*` | FP32 | +| Attention indexer, norms, embeddings, and special heads | BF16 | + +Accuracy reference, using the [SGLang GLM-5.2 FP8 H200 / default / low-latency / single-node AIME25 recipe](https://lmsysorg.mintlify.app/cookbook/autoregressive/GLM/GLM-5.2#hw=h200&variant=default&quant=fp8&strategy=low-latency&nodes=single): + +| Model | Quantization | Reasoning effort | AIME25 pass@1 | +|-------|--------------|------------------|---------------| +| ZhipuAI/GLM-5.2-FP8 | FP8 | `max` | `87.7%` | +| tclf90/GLM-5.2-Int4-Int8Mix | Int4-Int8Mix, W4A16/W8A16 | `medium-high` | `86.46%` | + +This is a lightweight reproduction reference rather than a full formal benchmark. + +### 【Dependencies / Installation】 + +``` +vllm==0.23.0 +``` + +As of **2026-06-21**, this model has been verified on an 8 x H200 machine with a Python 3.12 virtual environment and vLLM 0.23.0. + +Create a fresh Python environment and install vLLM: +``` +python3.12 -m venv venv +source venv/bin/activate +pip install vllm==0.23.0 +``` + +[vLLM Official Guide](https://recipes.vllm.ai/zai-org/GLM-5.2) + +### 【vLLM Startup Command】 +Note: When launching with TP=8, include `--enable-expert-parallel`; otherwise the expert tensors may not be evenly sharded across GPU devices. + +``` +export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 + +vllm serve \ + __YOUR_PATH__/GLM-5.2-Int4-Int8Mix \ + --host 0.0.0.0 \ + --port 8000 \ + --served-model-name GLM-5.2 \ + --trust-remote-code \ + --dtype bfloat16 \ + --quantization compressed-tensors \ + --kv-cache-dtype fp8 \ + --tensor-parallel-size 8 \ + --enable-expert-parallel \ + --max-model-len auto \ + --gpu-memory-utilization 0.90 \ + --max-num-seqs 32 \ + --enable-auto-tool-choice \ + --tool-call-parser glm47 \ + --reasoning-parser glm45 \ + --speculative-config.method mtp \ + --speculative-config.num_speculative_tokens 1 \ + --disable-uvicorn-access-log +``` + +The first launch may spend several minutes on vLLM compilation and warmup. + +### 【Logs】 +``` +2026-06-21 +1. Initial vLLM-only INT4/INT8 compressed-tensors export. +2. MTP block uses W8A16 channelwise quantization. +3. Verified vLLM 0.23.0 TP=8 EP startup and /v1/chat/completions POST. +``` + +### 【Model Files】 +| File Size | Last Updated | +|-----------|--------------| +| `378GiB` | `2026-06-21` | + +### 【Model Download】 +```python +from modelscope import snapshot_download +snapshot_download('tclf90/GLM-5.2-Int4-Int8Mix', cache_dir="your_local_path") +``` + +### 【Overview】 +# GLM-5.2 + +
+ +
+

+ 👋 Join our WeChat or Discord community. +
+ 📖 Check out the GLM-5.2 blog and GLM-5 Technical report. +
+ 📍 Use GLM-5.2 API services on Z.ai API Platform. +
+ 🔜 Try GLM-5.2 here. +

+ +

+ [Paper] + [GitHub] +

+ +## Introduction + +We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a **solid 1M-token context**. GLM-5.2's new capabilities include: +- **Solid 1M Context:** A solid 1M-token context that stably sustains long-horizon work +- **Advanced Coding with Flexible Effort**: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency +- **Improved Architecture**: We propose [IndexShare](https://arxiv.org/abs/2603.12201), which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9× at a 1M context length. We also improve GLM-5.2’s MTP layer for speculative decoding, increasing the acceptance length by up to 20% +- **Pure Open**: An MIT open-source license — no regional limits, technical access without borders + +![bench_52](https://raw.githubusercontent.com/zai-org/GLM-5/refs/heads/main/resources/bench_52.png) + +## Benchmark + +|Benchmark|GLM-5.2|GLM-5.1|Qwen3.7-Max|MiniMax M3|DeepSeek-V4-Pro|Claude Opus 4.8|GPT-5.5|Gemini 3.1 Pro| +|:---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:| +|Reasoning||||||||||| +|HLE|40.5|31|41.4|37|37.7|49.8*|41.4*|45| +|HLE (w/ Tools)|54.7|52.3|53.5|-|48.2|57.9*|52.2*|51.4*| +|CritPt|16.7|4.6|13.4|3.7|12.9|20.9|27.1|17.7| +|AIME 2026|99.2|95.3|97|-|94.6|95.7|98.3|98.2| +|HMMT Nov. 2025|94.4|94|95|84.4|94.4|96.5|96.5|94.8| +|HMMT Feb. 2026|92.5|82.6|97.1|84.4|95.2|96.7|96.7|87.3| +|IMOAnswerBench|91.0|83.8|90|-|89.8|83.5|-|81| +|GPQA-Diamond|91.2|86.2|90|93|90.1|93.6|93.6|94.3| +|Coding||||||||||| +|SWE-bench Pro|62.1|58.4|60.6|59|55.4|69.2|58.6|54.2| +|NL2Repo|48.9|42.7|47.2|42.1|35.5|69.7|50.7|33.4| +|DeepSWE|46.2|18|18|20|8|58|70|10| +|ProgramBench|63.7|50.9|-|-|47.8|71.9|70.8|39.5| +|Terminal Bench 2.1 (Terminus-2)|81.0|63.5|75|65|64| 85|84|74| +|Terminal Bench 2.1 (Best Reported Harness)|82.7|69|-|-|-|78.9|83.4|70.7| +|FrontierSWE (Dominance)|74.4|30.5|-|-|29.0|75.1|72.6|39.6| +|PostTrainBench|34.3|20.1|-|-|-|37.2|28.4|21.6| +|SWE-Marathon|13.0|1.0|-|-|-|26.0|12.0|4.0| +|Agentic||||||||||| +|MCP-Atlas (Public Set)|76.8|71.8|76.4|74.2|73.6|77.8|75.3|69.2| +|Tool-Decathlon|48.2|40.7|-|-|52.8|59.9|55.6|48.8| + +## Serve GLM-5.2 Locally + +The following open-source frameworks support local deployment of GLM-5.2: + +- [SGLang](https://github.com/sgl-project/sglang) (v0.5.13.post1+) — see [cookbook](https://cookbook.sglang.io/autoregressive/GLM/GLM-5.2) +- [vLLM](https://github.com/vllm-project/vllm) (v0.23.0+) — see [recipes](https://github.com/vllm-project/recipes/blob/main/GLM/GLM5.md) +- [xLLM](https://github.com/jd-opensource/xllm) (v0.10.0+) — see [example](https://github.com/zai-org/GLM-5/blob/main/example/ascend.md) +- [Transformers](https://github.com/huggingface/transformers) (v0.5.12+) — see [transformers docs](https://github.com/huggingface/transformers/blob/main/docs/source/en/model_doc/glm_moe_dsa.md) +- [KTransformers](https://github.com/kvcache-ai/ktransformers) (v0.5.12+) — see [tutorial](https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/kt-kernel/GLM-5.2-Tutorial.md) + +## Citation + +If you find GLM-5.2 useful in your research, please cite our technical report: + +```bibtex +@misc{glm5team2026glm5vibecodingagentic, + title={GLM-5: from Vibe Coding to Agentic Engineering}, + author={GLM-5-Team and : and Aohan Zeng and Xin Lv and Zhenyu Hou and Zhengxiao Du and Qinkai Zheng and Bin Chen and Da Yin and Chendi Ge and Chenghua Huang and Chengxing Xie and Chenzheng Zhu and Congfeng Yin and Cunxiang Wang and Gengzheng Pan and Hao Zeng and Haoke Zhang and Haoran Wang and Huilong Chen and Jiajie Zhang and Jian Jiao and Jiaqi Guo and Jingsen Wang and Jingzhao Du and Jinzhu Wu and Kedong Wang and Lei Li and Lin Fan and Lucen Zhong and Mingdao Liu and Mingming Zhao and Pengfan Du and Qian Dong and Rui Lu and Shuang-Li and Shulin Cao and Song Liu and Ting Jiang and Xiaodong Chen and Xiaohan Zhang and Xuancheng Huang and Xuezhen Dong and Yabo Xu and Yao Wei and Yifan An and Yilin Niu and Yitong Zhu and Yuanhao Wen and Yukuo Cen and Yushi Bai and Zhongpei Qiao and Zihan Wang and Zikang Wang and Zilin Zhu and Ziqiang Liu and Zixuan Li and Bojie Wang and Bosi Wen and Can Huang and Changpeng Cai and Chao Yu and Chen Li and Chengwei Hu and Chenhui Zhang and Dan Zhang and Daoyan Lin and Dayong Yang and Di Wang and Ding Ai and Erle Zhu and Fangzhou Yi and Feiyu Chen and Guohong Wen and Hailong Sun and Haisha Zhao and Haiyi Hu and Hanchen Zhang and Hanrui Liu and Hanyu Zhang and Hao Peng and Hao Tai and Haobo Zhang and He Liu and Hongwei Wang and Hongxi Yan and Hongyu Ge and Huan Liu and Huanpeng Chu and Jia'ni Zhao and Jiachen Wang and Jiajing Zhao and Jiamin Ren and Jiapeng Wang and Jiaxin Zhang and Jiayi Gui and Jiayue Zhao and Jijie Li and Jing An and Jing Li and Jingwei Yuan and Jinhua Du and Jinxin Liu and Junkai Zhi and Junwen Duan and Kaiyue Zhou and Kangjian Wei and Ke Wang and Keyun Luo and Laiqiang Zhang and Leigang Sha and Liang Xu and Lindong Wu and Lintao Ding and Lu Chen and Minghao Li and Nianyi Lin and Pan Ta and Qiang Zou and Rongjun Song and Ruiqi Yang and Shangqing Tu and Shangtong Yang and Shaoxiang Wu and Shengyan Zhang and Shijie Li and Shuang Li and Shuyi Fan and Wei Qin and Wei Tian and Weining Zhang and Wenbo Yu and Wenjie Liang and Xiang Kuang and Xiangmeng Cheng and Xiangyang Li and Xiaoquan Yan and Xiaowei Hu and Xiaoying Ling and Xing Fan and Xingye Xia and Xinyuan Zhang and Xinze Zhang and Xirui Pan and Xu Zou and Xunkai Zhang and Yadi Liu and Yandong Wu and Yanfu Li and Yidong Wang and Yifan Zhu and Yijun Tan and Yilin Zhou and Yiming Pan and Ying Zhang and Yinpei Su and Yipeng Geng and Yong Yan and Yonglin Tan and Yuean Bi and Yuhan Shen and Yuhao Yang and Yujiang Li and Yunan Liu and Yunqing Wang and Yuntao Li and Yurong Wu and Yutao Zhang and Yuxi Duan and Yuxuan Zhang and Zezhen Liu and Zhengtao Jiang and Zhenhe Yan and Zheyu Zhang and Zhixiang Wei and Zhuo Chen and Zhuoer Feng and Zijun Yao and Ziwei Chai and Ziyuan Wang and Zuzhou Zhang and Bin Xu and Minlie Huang and Hongning Wang and Juanzi Li and Yuxiao Dong and Jie Tang}, + year={2026}, + eprint={2602.15763}, + archivePrefix={arXiv}, + primaryClass={cs.LG}, + url={https://arxiv.org/abs/2602.15763}, +} +``` diff --git a/model-00008-of-00124.safetensors b/model-00008-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ad444d33c3398df34f325198396dd49213eb99c5 --- /dev/null +++ b/model-00008-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59bb5527c424cefd864baefe78c0d83ce3f116e3e7061e667fbf4916022bf041 +size 3218271904 diff --git a/model-00015-of-00124.safetensors b/model-00015-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b14f745a7cda4889cd736e6aa2c427375ab96da --- /dev/null +++ b/model-00015-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582a4a5d497c64bba3898854d6dd07592aa28f91c6bea6e3f8b4904f5791ac8a +size 3216414984 diff --git a/model-00041-of-00124.safetensors b/model-00041-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a403c3db44345b25333564fcc9089e22c486e616 --- /dev/null +++ b/model-00041-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51da63314e847080630f4b5494cd6140c90a26ff3c262d9598f7560298170c22 +size 3216414976 diff --git a/model-00047-of-00124.safetensors b/model-00047-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..942ca42430e36b399c533f70afcc5bb44af2c481 --- /dev/null +++ b/model-00047-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6def620a23ba52e0d3644b6a9cba08cfe77e65910d5455fb7d95a06006e1083 +size 3218271792 diff --git a/model-00048-of-00124.safetensors b/model-00048-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..60e87815907150464dd7628526f74644701ef215 --- /dev/null +++ b/model-00048-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08e11bb175e0f0b5aa31e5e9e0bd32400d5a0d6482757bcf5082f965dd680439 +size 3216415280 diff --git a/model-00049-of-00124.safetensors b/model-00049-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..269a7f260f79833e7509bdd80a66184eca48ad31 --- /dev/null +++ b/model-00049-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c6ea0f4816174d5888c4791fb2ff97bbb59264504617fdfe543065cb8cabfb6 +size 3216414968 diff --git a/model-00050-of-00124.safetensors b/model-00050-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a53cfc627da4085a818bc4803979bc80578ab01 --- /dev/null +++ b/model-00050-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0b35cf7d4c4e5341f0509cafbf22bfdb6587de445b0e389e5e102c8a74b10b2 +size 3218272080 diff --git a/model-00053-of-00124.safetensors b/model-00053-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..452bbd9478dc404c90724fc07e5e31ffe60e21b3 --- /dev/null +++ b/model-00053-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0198d0726f07488795b8bf503b8bd5d5cce29ca9eddb02268798730434de1a13 +size 3216414344 diff --git a/model-00054-of-00124.safetensors b/model-00054-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5fc3d57891926c6770dfdaf5c8048e88a177cd7a --- /dev/null +++ b/model-00054-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caede820fb3415784e89e87cac34bf403eefdd337fb6e18ab595b333ab2dcdf8 +size 3216413824 diff --git a/model-00057-of-00124.safetensors b/model-00057-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..885a8dbedbcd2451c574dddae9c20c0abb83b5d6 --- /dev/null +++ b/model-00057-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee32bbad45350e55d069b63f89922c3f72a230a89605afa3b3fa91ee6ac1d03c +size 3211390168 diff --git a/model-00059-of-00124.safetensors b/model-00059-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c9519ecaa7fb75f8854d9ba0ae48e158f99ac70c --- /dev/null +++ b/model-00059-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f5ab62cbe6fd0b162d239efd03b2aa68adaafcba3ed858abc16d8f9c1918ead +size 3215694048 diff --git a/model-00061-of-00124.safetensors b/model-00061-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc5277347d43cacc23e995233f8181dda0d24534 --- /dev/null +++ b/model-00061-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f862637298174bab1f5eeaff51b9c1faead2567df3e18b75d337a6b72850d5 +size 3216415400 diff --git a/model-00062-of-00124.safetensors b/model-00062-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..97d2b3614152057239c26ad4fccff0bf0980f38a --- /dev/null +++ b/model-00062-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e48e84e208a09b54158c9c187698f613cabf2cda948422d980256c56b8f150 +size 3216414984 diff --git a/model-00065-of-00124.safetensors b/model-00065-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a9c4f28f3112dae38c097e25ea3819586d4b557 --- /dev/null +++ b/model-00065-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:393bf868fdb882ebf7164ab4581571a85ffa32bf9cf6938ddc98f59ae26198a4 +size 3218271472 diff --git a/model-00066-of-00124.safetensors b/model-00066-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d801516eb9cb95f4edfcf52e09744deb54a324e4 --- /dev/null +++ b/model-00066-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab97877c990861861929b63cca1b1dfef1bb1db19d48f6ec7406351f7ba11ed1 +size 3215694688 diff --git a/model-00069-of-00124.safetensors b/model-00069-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b74ea2161c7469d59e3502392dd8b317c40e4a1 --- /dev/null +++ b/model-00069-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd0d197744e186e991fedeabf31cb655d928fcd8acc33f70970f1ca5569c4eba +size 3216415248 diff --git a/model-00072-of-00124.safetensors b/model-00072-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d32cf180cf5cf05a5fae34b1924e219fa7c6bb6c --- /dev/null +++ b/model-00072-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6d24fa19673cea09c84d2114cea3134743fab081be1e3d90b35896efea6420 +size 3216414144 diff --git a/model-00075-of-00124.safetensors b/model-00075-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..481fdafb27f63c1cfae56e53cfa36852fc14bb9f --- /dev/null +++ b/model-00075-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59b90c807788815b4306eb7c1a57182e8f49eae0f9ab88f94a8b7436bafdc367 +size 3216414976 diff --git a/model-00076-of-00124.safetensors b/model-00076-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bd850df1c0560362dd8404a6398510103a04a53c --- /dev/null +++ b/model-00076-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba1be96b23bc2fd4e273966ffe60a6d9b00b60e89c101a05eb71e64dc9b53a67 +size 3218271944 diff --git a/model-00077-of-00124.safetensors b/model-00077-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3667a6ac7cb3194362414cf198cd9b6b21a5d20a --- /dev/null +++ b/model-00077-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5a1ab6b5acca27008f16c33e1d8c11eb8a165a875b5d615e9be45c3ebb49eee +size 3216415136 diff --git a/model-00078-of-00124.safetensors b/model-00078-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f91319d7765325241d24aef0c328e44908a562e5 --- /dev/null +++ b/model-00078-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:649e769c9dbaee881e2c370936acf6593d9c48f8304408613349dce72e2e8130 +size 3218271360 diff --git a/model-00080-of-00124.safetensors b/model-00080-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..570eceafabc5bb420e867a61c4284d4714ac24a2 --- /dev/null +++ b/model-00080-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f50ff3a3b555b60f1423f2dafd9d83c202322bfa63316aa5c38ad24dece4969 +size 3215694048 diff --git a/model-00081-of-00124.safetensors b/model-00081-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..df1ecdd50d4b5d70956aa113ed4811ceab80c906 --- /dev/null +++ b/model-00081-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb36aa0000870174af9e4bb629dba13f469223d820e8bb54eaf28892fe953646 +size 3218271712 diff --git a/model-00083-of-00124.safetensors b/model-00083-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d8a11f8e8e36987c8e31c99bd0c4ea549c56ae4b --- /dev/null +++ b/model-00083-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c414fa49a9bdea305dfbe74476de9fd9eb617014695f0542b2cfe29a36aa7c66 +size 3216414992 diff --git a/model-00084-of-00124.safetensors b/model-00084-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da0205b75fe822e10d0da783161b4aa4d8d3b13a --- /dev/null +++ b/model-00084-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aa2ce5d82d76637a8d8c86f5f1d80c6b64d44d71c2a77f91a34aeee5cc30f27 +size 3218272056 diff --git a/model-00087-of-00124.safetensors b/model-00087-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..80e1f7c7181f869f7ffa2c6e38566b6be62326f5 --- /dev/null +++ b/model-00087-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd0ef2dacb1d92a2ef94032178d38e6d34f0c32564d62a98e3ce884ad87ba9e3 +size 3215694672 diff --git a/model-00088-of-00124.safetensors b/model-00088-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a03f7d8952c4baefb3b4aaa9007d5997d5b2313c --- /dev/null +++ b/model-00088-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12669c2bee19764a6a3fe0b6398c20a0f7c561e70883e290b8c574d7c18f7826 +size 3216414648 diff --git a/model-00089-of-00124.safetensors b/model-00089-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..26f3107ca012be15534e62ca3bab9a125062edb2 --- /dev/null +++ b/model-00089-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e21c714d7deb8f7d62473e6ee3fb57c06bc8b518d2be790b3882d40466bd6a +size 3218270352 diff --git a/model-00090-of-00124.safetensors b/model-00090-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..79ee742075dc716cca3d14eb8a1a45bf763e6d95 --- /dev/null +++ b/model-00090-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c067aa3c4156886867ebfa08e5037ecf7753c56906a3b6182699b11d3a89bb01 +size 3215693784 diff --git a/model-00092-of-00124.safetensors b/model-00092-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06c52a529ca54133aaf82123b2d0ffd4c6b986ba --- /dev/null +++ b/model-00092-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b13b66388c07c881ea45bdcfcf54f8dc9067f4a4f93eef31353c2c8a914ab66b +size 3219921296 diff --git a/model-00098-of-00124.safetensors b/model-00098-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dacf50a2e3cabb77dbfc65482c206a751e279c40 --- /dev/null +++ b/model-00098-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a68ace6a9480bc703dfa91c1c10a3f0337e0d84048afad7e1dfb0409865f73a7 +size 3216415104 diff --git a/model-00101-of-00124.safetensors b/model-00101-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..44383bcc7a3c244c21fef5339e7b333720643463 --- /dev/null +++ b/model-00101-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f45ffbaefbcf3de405ca6deda7a51b44a635de1fd2c3e5e0aa2207ef9b73a29 +size 3215694048 diff --git a/model-00102-of-00124.safetensors b/model-00102-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ab89ac7d1b99809209b68acb9157ae41f65ab16 --- /dev/null +++ b/model-00102-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:307507aee232626d8e4e4dd1e5a3058090365ce38c33ad47034884f397501749 +size 3218271736 diff --git a/model-00103-of-00124.safetensors b/model-00103-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2eacc24cc59a52fc3f99531f95a601cac7b78b99 --- /dev/null +++ b/model-00103-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:758d174d1f6cd1f4973405638a8c45b8f957d693e48e99c4788b761bedd05d9d +size 3216415376 diff --git a/model-00104-of-00124.safetensors b/model-00104-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d7d7ebd8fef1f045126c1122c683231d61bcfb1 --- /dev/null +++ b/model-00104-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f2015455095912796d32862b2091e27c9cd04b823521c59e0367823c9079474 +size 3216414968 diff --git a/model-00106-of-00124.safetensors b/model-00106-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ab2d396ffb11c9c10c88f66e4c6988acb891711 --- /dev/null +++ b/model-00106-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fcc26a0c1a07013d011950e37b13d20e60c419be8c19e356c1c61ed97f40c0e +size 3216414320 diff --git a/model-00110-of-00124.safetensors b/model-00110-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..11a56af450b1c096503b8f8dc054eb2809bcb84d --- /dev/null +++ b/model-00110-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2d9708cc417b086bb1bb550fd44a7bbd59a040c6d36f23bf3ed84fb9ea096f +size 3218271864 diff --git a/model-00111-of-00124.safetensors b/model-00111-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..04b4ebdf57191fc77aeebb422ce0f9ac9e51ce75 --- /dev/null +++ b/model-00111-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af3177af86803af86ee4671d31bbd68c26ad6f21ffc032405ff16b9f9772a4e4 +size 3216415200 diff --git a/model-00112-of-00124.safetensors b/model-00112-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b644e982d6962cb90287ddbe9dd45a1387bba08 --- /dev/null +++ b/model-00112-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbef7e75abbff848761faeade60fac6444cdb47ace1eb3e2e9f493082ad039c7 +size 3138675856 diff --git a/model-00114-of-00124.safetensors b/model-00114-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35927e99b2cb92615a8abcdfbaf6e020e7b3c209 --- /dev/null +++ b/model-00114-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e0feccf6a5ea7fa78313df51863c7b84a83142b71365e96f55f5794957373c0 +size 3216414984 diff --git a/model-00115-of-00124.safetensors b/model-00115-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5047adcd07bf079878849eb2e184b09f07e2631a --- /dev/null +++ b/model-00115-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc4c3dd7776b81eea499a83d998c8717a554a7638fa12ca3420cbdb27892489 +size 3218271672 diff --git a/model-00117-of-00124.safetensors b/model-00117-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..915fb5eb65819540949de0f565d050cde182133d --- /dev/null +++ b/model-00117-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a4ad14ec6c76a4a9f5a518b4f4d2aea17600c8fdec35de5cc190c07aab3be39 +size 3216414976 diff --git a/model-00119-of-00124.safetensors b/model-00119-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c05362d40caf335729b6fb89837cf472038a3e99 --- /dev/null +++ b/model-00119-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec1dbbae6fe14b8018f5e3f4e509408ca8655fcce9bfe4bded80460526a3756b +size 3216415048 diff --git a/model-00121-of-00124.safetensors b/model-00121-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a73111a4c9f8457d7d145e452c42e4cfce9983d --- /dev/null +++ b/model-00121-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef5387cdbc1e8ae1b4b4c86d520f50f01df761bedef4361a0f8f6753b2f85f2b +size 3216414360 diff --git a/model-00122-of-00124.safetensors b/model-00122-of-00124.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f60d4bd6854996eb7517344ad008b3557d731b9c --- /dev/null +++ b/model-00122-of-00124.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b22d8ed3e0676c9172a7699224d9d77a260f86b24872fe7fa10f7e6597cf4553 +size 3216413568 diff --git a/mtp-00001-of-00004.safetensors b/mtp-00001-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb1bfc4fccfff6cb19b7e6ee563d006cc13c6a2d --- /dev/null +++ b/mtp-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e547131c16fc8da5eab20897087e1116819e18b10544892d8a5e51a548b40ddb +size 3210432792 diff --git a/mtp-00002-of-00004.safetensors b/mtp-00002-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d5b6d7b93b9b676f26ca2d09618dc597382404bd --- /dev/null +++ b/mtp-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef349e53c0a2c1fcf037e42222723d61d50b85950441bf801a0ba241c4e16852 +size 3210482112 diff --git a/mtp-00004-of-00004.safetensors b/mtp-00004-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a4c9fed8a08a7d7d02092c9028e6f0b5ca0f89e1 --- /dev/null +++ b/mtp-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb916505ffe18245236e2360fb9d6681363e13ae82f131c2065095423120796 +size 416818584 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..aba40197a4cdb5607f4ab7a05fb0a4ee8054fd6d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d +size 20217442