Text Classification
Transformers
Safetensors
mistral
trl
reward-trainer
Generated from Trainer
text-embeddings-inference
Instructions to use bidit/mistral-reward with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bidit/mistral-reward with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="bidit/mistral-reward")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("bidit/mistral-reward") model = AutoModelForSequenceClassification.from_pretrained("bidit/mistral-reward", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "bidit/mistral-supervised", | |
| "architectures": [ | |
| "MistralForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 48, | |
| "hidden_act": "silu", | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "max_position_embeddings": 512, | |
| "model_type": "mistral", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 4, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 768, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.44.2", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |