Tlntin / ChatGLM2-6B-TensorRT

Related projects ⓘ

Alternatives and complementary repositories for ChatGLM2-6B-TensorRT

• Oneflow-Inc / one-glm
  A more efficient GLM implementation!
  ☆55Updated last year
• genggui001 / Megatron-DeepSpeed-Llama
  ☆82Updated last year
• sophgo / ChatGLM2-TPU
  run ChatGLM2-6B in BM1684X
  ☆48Updated 8 months ago
• luchangli03 / export_llama_to_onnx
  export llama to onnx
  ☆96Updated 5 months ago
• K024 / chatglm-q
  Another ChatGLM2 implementation for GPTQ quantization
  ☆54Updated last year
• zhaohb / fastapi_tritonserver
  ☆23Updated 2 weeks ago
• ProjectD-AI / llama_inference
  llama inference for tencentpretrain
  ☆96Updated last year
• QwenLM / vllm-gptq
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆123Updated 11 months ago
• seanzhang-zhichen / baichuan-Dynamic-NTK-ALiBi
  百川Dynamic NTK-ALiBi的代码实现：无需微调即可推理更长文本
  ☆46Updated last year
• xv44586 / Chinese-instruction-datasets
  中文 Instruction tuning datasets
  ☆118Updated 7 months ago
• yongzhuo / ChatGLM2-SFT
  ChatGLM2-6B微调, SFT/LoRA, instruction finetune
  ☆106Updated last year
• zejunwang1 / easytokenizer
  高性能文本 Tokenizer 库
  ☆27Updated 9 months ago
• shibing624 / lmft
  ChatGLM-6B fine-tuning.
  ☆135Updated last year
• wp931120 / baichuan_sft_lora
  baichuan LLM surpervised finetune by lora
  ☆60Updated last year
• ArtificialZeng / baichuan-speedup
  纯c++的全平台llm加速库，支持python调用，支持baichuan, glm, llama, moss基座，手机端流畅运行chatglm-6B级模型单卡可达10000+token / s，
  ☆45Updated last year
• zejunwang1 / LLMTuner
  大语言模型指令调优工具（支持 FlashAttention）
  ☆166Updated 10 months ago
• taishan1994 / sentencepiece_chinese_bpe
  使用sentencepiece中BPE训练中文词表，并在transformers中进行使用。
  ☆110Updated last year
• wangzhaode / llm-export
  llm-export can export llm model to onnx.
  ☆230Updated last week
• lilongxian / BaiYang-chatGLM2-6B
  （1）弹性区间标准化的旋转位置词嵌入编码器+peft LORA量化训练，提高万级tokens性能支持。（2）证据理论解释学习，提升模型的复杂逻辑推理能力（3）兼容alpaca数据格式。
  ☆45Updated last year
• TRT2022 / trtllm-llama
  ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化
  ☆44Updated last year
• SmartLi8 / stella
  text embedding
  ☆139Updated last year
• ssbuild / qwen_finetuning
  qwen-7b and qwen-14b finetuning
  ☆84Updated 7 months ago
• gameofdimension / vllm-cn
  演示 vllm 对中文大语言模型的神奇效果
  ☆31Updated last year
• yanqiangmiffy / how-to-train-tokenizer
  怎么训练一个LLM分词器
  ☆129Updated last year
• bug-developer021 / YOLOV5_optimization_on_triton
  Compare multiple optimization methods on triton to imporve model service performance
  ☆46Updated 10 months ago
• cauyxy / bilivideos
  ☆51Updated last year
• vxfla / kanchil
  Kanchil（鼷鹿）是世界上最小的偶蹄目动物，这个开源项目意在探索小模型（6B以下）是否也能具备和人类偏好对齐的能力。
  ☆114Updated last year
• mark1879 / Baichuan-13B-Finetuning
  Baichuan-13B 指令微调
  ☆89Updated last year
• luchangli03 / onnxsim_large_model
  simplify >2GB large onnx model
  ☆44Updated 8 months ago
• yongzhuo / LLM-SFT
  中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微…
  ☆168Updated 6 months ago