Instructions to use ssbuild/internlm-chat-7b-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ssbuild/internlm-chat-7b-int4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ssbuild/internlm-chat-7b-int4", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ssbuild/internlm-chat-7b-int4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "/data/nlp/pre_models/torch/internlm/internlm-chat-7b", | |
| "architectures": [ | |
| "InternLMForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_internlm.InternLMConfig", | |
| "AutoModel": "modeling_internlm.InternLMForCausalLM", | |
| "AutoModelForCausalLM": "modeling_internlm.InternLMForCausalLM" | |
| }, | |
| "bias": true, | |
| "bos_token_id": 1, | |
| "decoder_start_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "initializer_weight": false, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 2048, | |
| "model_type": "internlm", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "pad_token_id": 2, | |
| "quantization_bit": 4, | |
| "return_dict": false, | |
| "rms_norm_eps": 1e-06, | |
| "task_specific_params": {}, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.31.0", | |
| "use_cache": true, | |
| "vocab_size": 103168 | |
| } | |