Text Generation
Transformers
PyTorch
English
Chinese
chatglm
feature-extraction
Long Context
custom_code
Instructions to use zai-org/LongAlign-6B-64k-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zai-org/LongAlign-6B-64k-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zai-org/LongAlign-6B-64k-base", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("zai-org/LongAlign-6B-64k-base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use zai-org/LongAlign-6B-64k-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zai-org/LongAlign-6B-64k-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zai-org/LongAlign-6B-64k-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zai-org/LongAlign-6B-64k-base
- SGLang
How to use zai-org/LongAlign-6B-64k-base with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "zai-org/LongAlign-6B-64k-base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zai-org/LongAlign-6B-64k-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "zai-org/LongAlign-6B-64k-base" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zai-org/LongAlign-6B-64k-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zai-org/LongAlign-6B-64k-base with Docker Model Runner:
docker model run hf.co/zai-org/LongAlign-6B-64k-base
Download pytorch_model.bin.index.json from zai-org/LongAlign-6B-64k-base: direct link, hf CLI and curl.
- Browser
- Download file 18.3 kB
-
https://huggingface.co/zai-org/LongAlign-6B-64k-base/resolve/main/pytorch_model.bin.index.json
- Command line
-
hf download hf://zai-org/LongAlign-6B-64k-base/pytorch_model.bin.index.json
-
curl -L -o pytorch_model.bin.index.json https://huggingface.co/zai-org/LongAlign-6B-64k-base/resolve/main/pytorch_model.bin.index.json
18.3 kB
| {"weight_map": {"transformer.encoder.layers.0.input_layernorm.weight": "pytorch_model-0-of-29.bin", "transformer.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-0-of-29.bin", "transformer.encoder.layers.0.self_attention.query_key_value.weight": "pytorch_model-0-of-29.bin", "transformer.encoder.layers.0.self_attention.query_key_value.bias": "pytorch_model-0-of-29.bin", "transformer.encoder.layers.0.self_attention.dense.weight": "pytorch_model-0-of-29.bin", "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-0-of-29.bin", "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-0-of-29.bin", "transformer.encoder.layers.1.input_layernorm.weight": "pytorch_model-1-of-29.bin", "transformer.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-1-of-29.bin", "transformer.encoder.layers.1.self_attention.query_key_value.weight": "pytorch_model-1-of-29.bin", "transformer.encoder.layers.1.self_attention.query_key_value.bias": "pytorch_model-1-of-29.bin", "transformer.encoder.layers.1.self_attention.dense.weight": "pytorch_model-1-of-29.bin", "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-1-of-29.bin", "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-1-of-29.bin", "transformer.encoder.layers.2.input_layernorm.weight": "pytorch_model-2-of-29.bin", "transformer.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-2-of-29.bin", "transformer.encoder.layers.2.self_attention.query_key_value.weight": "pytorch_model-2-of-29.bin", "transformer.encoder.layers.2.self_attention.query_key_value.bias": "pytorch_model-2-of-29.bin", "transformer.encoder.layers.2.self_attention.dense.weight": "pytorch_model-2-of-29.bin", "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-2-of-29.bin", "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-2-of-29.bin", "transformer.encoder.layers.3.input_layernorm.weight": "pytorch_model-3-of-29.bin", "transformer.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-3-of-29.bin", "transformer.encoder.layers.3.self_attention.query_key_value.weight": "pytorch_model-3-of-29.bin", "transformer.encoder.layers.3.self_attention.query_key_value.bias": "pytorch_model-3-of-29.bin", "transformer.encoder.layers.3.self_attention.dense.weight": "pytorch_model-3-of-29.bin", "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-3-of-29.bin", "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-3-of-29.bin", "transformer.encoder.layers.4.input_layernorm.weight": "pytorch_model-4-of-29.bin", "transformer.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-4-of-29.bin", "transformer.encoder.layers.4.self_attention.query_key_value.weight": "pytorch_model-4-of-29.bin", "transformer.encoder.layers.4.self_attention.query_key_value.bias": "pytorch_model-4-of-29.bin", "transformer.encoder.layers.4.self_attention.dense.weight": "pytorch_model-4-of-29.bin", "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-4-of-29.bin", "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-4-of-29.bin", "transformer.encoder.layers.5.input_layernorm.weight": "pytorch_model-5-of-29.bin", "transformer.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-5-of-29.bin", "transformer.encoder.layers.5.self_attention.query_key_value.weight": "pytorch_model-5-of-29.bin", "transformer.encoder.layers.5.self_attention.query_key_value.bias": "pytorch_model-5-of-29.bin", "transformer.encoder.layers.5.self_attention.dense.weight": "pytorch_model-5-of-29.bin", "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-5-of-29.bin", "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-5-of-29.bin", "transformer.encoder.layers.6.input_layernorm.weight": "pytorch_model-6-of-29.bin", "transformer.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-6-of-29.bin", "transformer.encoder.layers.6.self_attention.query_key_value.weight": "pytorch_model-6-of-29.bin", "transformer.encoder.layers.6.self_attention.query_key_value.bias": "pytorch_model-6-of-29.bin", "transformer.encoder.layers.6.self_attention.dense.weight": "pytorch_model-6-of-29.bin", "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-6-of-29.bin", "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-6-of-29.bin", "transformer.encoder.layers.7.input_layernorm.weight": "pytorch_model-7-of-29.bin", "transformer.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-7-of-29.bin", "transformer.encoder.layers.7.self_attention.query_key_value.weight": "pytorch_model-7-of-29.bin", "transformer.encoder.layers.7.self_attention.query_key_value.bias": "pytorch_model-7-of-29.bin", "transformer.encoder.layers.7.self_attention.dense.weight": "pytorch_model-7-of-29.bin", "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-7-of-29.bin", "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-7-of-29.bin", "transformer.encoder.layers.8.input_layernorm.weight": "pytorch_model-8-of-29.bin", "transformer.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-8-of-29.bin", "transformer.encoder.layers.8.self_attention.query_key_value.weight": "pytorch_model-8-of-29.bin", "transformer.encoder.layers.8.self_attention.query_key_value.bias": "pytorch_model-8-of-29.bin", "transformer.encoder.layers.8.self_attention.dense.weight": "pytorch_model-8-of-29.bin", "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-8-of-29.bin", "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-8-of-29.bin", "transformer.encoder.layers.9.input_layernorm.weight": "pytorch_model-9-of-29.bin", "transformer.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-9-of-29.bin", "transformer.encoder.layers.9.self_attention.query_key_value.weight": "pytorch_model-9-of-29.bin", "transformer.encoder.layers.9.self_attention.query_key_value.bias": "pytorch_model-9-of-29.bin", "transformer.encoder.layers.9.self_attention.dense.weight": "pytorch_model-9-of-29.bin", "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-9-of-29.bin", "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-9-of-29.bin", "transformer.encoder.layers.10.input_layernorm.weight": "pytorch_model-10-of-29.bin", "transformer.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-10-of-29.bin", "transformer.encoder.layers.10.self_attention.query_key_value.weight": "pytorch_model-10-of-29.bin", "transformer.encoder.layers.10.self_attention.query_key_value.bias": "pytorch_model-10-of-29.bin", "transformer.encoder.layers.10.self_attention.dense.weight": "pytorch_model-10-of-29.bin", "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-10-of-29.bin", "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-10-of-29.bin", "transformer.encoder.layers.11.input_layernorm.weight": "pytorch_model-11-of-29.bin", "transformer.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-11-of-29.bin", "transformer.encoder.layers.11.self_attention.query_key_value.weight": "pytorch_model-11-of-29.bin", "transformer.encoder.layers.11.self_attention.query_key_value.bias": "pytorch_model-11-of-29.bin", "transformer.encoder.layers.11.self_attention.dense.weight": "pytorch_model-11-of-29.bin", "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-11-of-29.bin", "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-11-of-29.bin", "transformer.encoder.layers.12.input_layernorm.weight": "pytorch_model-12-of-29.bin", "transformer.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-12-of-29.bin", "transformer.encoder.layers.12.self_attention.query_key_value.weight": "pytorch_model-12-of-29.bin", "transformer.encoder.layers.12.self_attention.query_key_value.bias": "pytorch_model-12-of-29.bin", "transformer.encoder.layers.12.self_attention.dense.weight": "pytorch_model-12-of-29.bin", "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-12-of-29.bin", "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-12-of-29.bin", "transformer.encoder.layers.13.input_layernorm.weight": "pytorch_model-13-of-29.bin", "transformer.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-13-of-29.bin", "transformer.encoder.layers.13.self_attention.query_key_value.weight": "pytorch_model-13-of-29.bin", "transformer.encoder.layers.13.self_attention.query_key_value.bias": "pytorch_model-13-of-29.bin", "transformer.encoder.layers.13.self_attention.dense.weight": "pytorch_model-13-of-29.bin", "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-13-of-29.bin", "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-13-of-29.bin", "transformer.encoder.layers.14.input_layernorm.weight": "pytorch_model-14-of-29.bin", "transformer.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-14-of-29.bin", "transformer.encoder.layers.14.self_attention.query_key_value.weight": "pytorch_model-14-of-29.bin", "transformer.encoder.layers.14.self_attention.query_key_value.bias": "pytorch_model-14-of-29.bin", "transformer.encoder.layers.14.self_attention.dense.weight": "pytorch_model-14-of-29.bin", "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-14-of-29.bin", "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-14-of-29.bin", "transformer.encoder.layers.15.input_layernorm.weight": "pytorch_model-15-of-29.bin", "transformer.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-15-of-29.bin", "transformer.encoder.layers.15.self_attention.query_key_value.weight": "pytorch_model-15-of-29.bin", "transformer.encoder.layers.15.self_attention.query_key_value.bias": "pytorch_model-15-of-29.bin", "transformer.encoder.layers.15.self_attention.dense.weight": "pytorch_model-15-of-29.bin", "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-15-of-29.bin", "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-15-of-29.bin", "transformer.encoder.layers.16.input_layernorm.weight": "pytorch_model-16-of-29.bin", "transformer.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-16-of-29.bin", "transformer.encoder.layers.16.self_attention.query_key_value.weight": "pytorch_model-16-of-29.bin", "transformer.encoder.layers.16.self_attention.query_key_value.bias": "pytorch_model-16-of-29.bin", "transformer.encoder.layers.16.self_attention.dense.weight": "pytorch_model-16-of-29.bin", "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-16-of-29.bin", "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-16-of-29.bin", "transformer.encoder.layers.17.input_layernorm.weight": "pytorch_model-17-of-29.bin", "transformer.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-17-of-29.bin", "transformer.encoder.layers.17.self_attention.query_key_value.weight": "pytorch_model-17-of-29.bin", "transformer.encoder.layers.17.self_attention.query_key_value.bias": "pytorch_model-17-of-29.bin", "transformer.encoder.layers.17.self_attention.dense.weight": "pytorch_model-17-of-29.bin", "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-17-of-29.bin", "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-17-of-29.bin", "transformer.encoder.layers.18.input_layernorm.weight": "pytorch_model-18-of-29.bin", "transformer.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-18-of-29.bin", "transformer.encoder.layers.18.self_attention.query_key_value.weight": "pytorch_model-18-of-29.bin", "transformer.encoder.layers.18.self_attention.query_key_value.bias": "pytorch_model-18-of-29.bin", "transformer.encoder.layers.18.self_attention.dense.weight": "pytorch_model-18-of-29.bin", "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-18-of-29.bin", "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-18-of-29.bin", "transformer.encoder.layers.19.input_layernorm.weight": "pytorch_model-19-of-29.bin", "transformer.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-19-of-29.bin", "transformer.encoder.layers.19.self_attention.query_key_value.weight": "pytorch_model-19-of-29.bin", "transformer.encoder.layers.19.self_attention.query_key_value.bias": "pytorch_model-19-of-29.bin", "transformer.encoder.layers.19.self_attention.dense.weight": "pytorch_model-19-of-29.bin", "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-19-of-29.bin", "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-19-of-29.bin", "transformer.encoder.layers.20.input_layernorm.weight": "pytorch_model-20-of-29.bin", "transformer.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-20-of-29.bin", "transformer.encoder.layers.20.self_attention.query_key_value.weight": "pytorch_model-20-of-29.bin", "transformer.encoder.layers.20.self_attention.query_key_value.bias": "pytorch_model-20-of-29.bin", "transformer.encoder.layers.20.self_attention.dense.weight": "pytorch_model-20-of-29.bin", "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-20-of-29.bin", "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-20-of-29.bin", "transformer.encoder.layers.21.input_layernorm.weight": "pytorch_model-21-of-29.bin", "transformer.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-21-of-29.bin", "transformer.encoder.layers.21.self_attention.query_key_value.weight": "pytorch_model-21-of-29.bin", "transformer.encoder.layers.21.self_attention.query_key_value.bias": "pytorch_model-21-of-29.bin", "transformer.encoder.layers.21.self_attention.dense.weight": "pytorch_model-21-of-29.bin", "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-21-of-29.bin", "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-21-of-29.bin", "transformer.encoder.layers.22.input_layernorm.weight": "pytorch_model-22-of-29.bin", "transformer.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-22-of-29.bin", "transformer.encoder.layers.22.self_attention.query_key_value.weight": "pytorch_model-22-of-29.bin", "transformer.encoder.layers.22.self_attention.query_key_value.bias": "pytorch_model-22-of-29.bin", "transformer.encoder.layers.22.self_attention.dense.weight": "pytorch_model-22-of-29.bin", "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-22-of-29.bin", "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-22-of-29.bin", "transformer.encoder.layers.23.input_layernorm.weight": "pytorch_model-23-of-29.bin", "transformer.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-23-of-29.bin", "transformer.encoder.layers.23.self_attention.query_key_value.weight": "pytorch_model-23-of-29.bin", "transformer.encoder.layers.23.self_attention.query_key_value.bias": "pytorch_model-23-of-29.bin", "transformer.encoder.layers.23.self_attention.dense.weight": "pytorch_model-23-of-29.bin", "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-23-of-29.bin", "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-23-of-29.bin", "transformer.encoder.layers.24.input_layernorm.weight": "pytorch_model-24-of-29.bin", "transformer.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-24-of-29.bin", "transformer.encoder.layers.24.self_attention.query_key_value.weight": "pytorch_model-24-of-29.bin", "transformer.encoder.layers.24.self_attention.query_key_value.bias": "pytorch_model-24-of-29.bin", "transformer.encoder.layers.24.self_attention.dense.weight": "pytorch_model-24-of-29.bin", "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-24-of-29.bin", "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-24-of-29.bin", "transformer.encoder.layers.25.input_layernorm.weight": "pytorch_model-25-of-29.bin", "transformer.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-25-of-29.bin", "transformer.encoder.layers.25.self_attention.query_key_value.weight": "pytorch_model-25-of-29.bin", "transformer.encoder.layers.25.self_attention.query_key_value.bias": "pytorch_model-25-of-29.bin", "transformer.encoder.layers.25.self_attention.dense.weight": "pytorch_model-25-of-29.bin", "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-25-of-29.bin", "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-25-of-29.bin", "transformer.encoder.layers.26.input_layernorm.weight": "pytorch_model-26-of-29.bin", "transformer.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-26-of-29.bin", "transformer.encoder.layers.26.self_attention.query_key_value.weight": "pytorch_model-26-of-29.bin", "transformer.encoder.layers.26.self_attention.query_key_value.bias": "pytorch_model-26-of-29.bin", "transformer.encoder.layers.26.self_attention.dense.weight": "pytorch_model-26-of-29.bin", "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-26-of-29.bin", "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-26-of-29.bin", "transformer.encoder.layers.27.input_layernorm.weight": "pytorch_model-27-of-29.bin", "transformer.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-27-of-29.bin", "transformer.encoder.layers.27.self_attention.query_key_value.weight": "pytorch_model-27-of-29.bin", "transformer.encoder.layers.27.self_attention.query_key_value.bias": "pytorch_model-27-of-29.bin", "transformer.encoder.layers.27.self_attention.dense.weight": "pytorch_model-27-of-29.bin", "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-27-of-29.bin", "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-27-of-29.bin", "transformer.embedding.word_embeddings.weight": "pytorch_model-28-of-29.bin", "transformer.output_layer.weight": "pytorch_model-28-of-29.bin", "transformer.encoder.final_layernorm.weight": "pytorch_model-28-of-29.bin"}, "metadata": {"total_size": 12487168000}} |