Instructions to use VMXVMX/llama2-project with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use VMXVMX/llama2-project with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/tmp/huggingface/hub/hf-llama-2-7b") model = PeftModel.from_pretrained(base_model, "VMXVMX/llama2-project") - Notebooks
- Google Colab
- Kaggle
Download config.json from VMXVMX/llama2-project: direct link, hf CLI and curl.
- Browser
- Download file 636 Bytes
-
https://huggingface.co/VMXVMX/llama2-project/resolve/main/config.json
- Command line
-
hf download hf://VMXVMX/llama2-project/config.json
-
curl -L -o config.json https://huggingface.co/VMXVMX/llama2-project/resolve/main/config.json
636 Bytes
| { | |
| "_name_or_path": "/tmp/huggingface/hub/hf-llama-2-7b", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 2048, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.31.0", | |
| "use_cache": true, | |
| "vocab_size": 32001 | |
| } | |