Question Answering
Transformers
PyTorch
Chinese
English
llama
text-generation
text-generation-inference
Instructions to use FlagAlpha/Llama2-Chinese-13b-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FlagAlpha/Llama2-Chinese-13b-Chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="FlagAlpha/Llama2-Chinese-13b-Chat")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("FlagAlpha/Llama2-Chinese-13b-Chat") model = AutoModelForMultimodalLM.from_pretrained("FlagAlpha/Llama2-Chinese-13b-Chat") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "/mnt/data/zhangzheng/data/other_model/models--meta-llama--Llama-2-13b-chat-hf", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "max_position_embeddings": 4096, | |
| "model_type": "llama", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 40, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.32.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |