Instructions to use Alex6657/AgentTailor-BookCrossing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Alex6657/AgentTailor-BookCrossing with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("GritLM/GritLM-7B") model = PeftModel.from_pretrained(base_model, "Alex6657/AgentTailor-BookCrossing") - Notebooks
- Google Colab
- Kaggle
Download training_base_config.json from Alex6657/AgentTailor-BookCrossing: direct link, hf CLI and curl.
- Browser
- Download file 1 kB
-
https://huggingface.co/Alex6657/AgentTailor-BookCrossing/resolve/main/training_base_config.json
- Command line
-
hf download hf://Alex6657/AgentTailor-BookCrossing/training_base_config.json
-
curl -L -o training_base_config.json https://huggingface.co/Alex6657/AgentTailor-BookCrossing/resolve/main/training_base_config.json
1 kB
| { | |
| "_name_or_path": "GritLM/GritLM-7B", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoModel": "modeling_gritlm7b.MistralModel", | |
| "AutoModelForCausalLM": "modeling_gritlm7b.MistralForCausalLM", | |
| "AutoModelForSequenceClassification": "modeling_gritlm7b.MistralForSequenceClassification" | |
| }, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "id2label": { | |
| "0": "LABEL_0" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "label2id": { | |
| "LABEL_0": 0 | |
| }, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.45.2", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |