Instructions to use minhchuxuan/llama-2.7b-dolly-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use minhchuxuan/llama-2.7b-dolly-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/workspace/LMOps/minillm/checkpoints/Sheared-LLaMA-2.7B-Pruned/") model = PeftModel.from_pretrained(base_model, "minhchuxuan/llama-2.7b-dolly-lora") - Notebooks
- Google Colab
- Kaggle
File size: 632 Bytes
72aa863 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 | {
"_name_or_path": "princeton-nlp/Sheared-LLaMA-2.7B",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"num_key_value_heads": 20,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.28.1",
"use_cache": true,
"vocab_size": 32000
}
|