Instructions to use harman/gemma2-9b_ultrafeedback-RM_pairpm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use harman/gemma2-9b_ultrafeedback-RM_pairpm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="harman/gemma2-9b_ultrafeedback-RM_pairpm")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("harman/gemma2-9b_ultrafeedback-RM_pairpm") model = AutoModel.from_pretrained("harman/gemma2-9b_ultrafeedback-RM_pairpm", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from harman/gemma2-9b_ultrafeedback-RM_pairpm: direct link, hf CLI and curl.
- Browser
- Download file 1.05 kB
-
https://huggingface.co/harman/gemma2-9b_ultrafeedback-RM_pairpm/resolve/main/config.json
- Command line
-
hf download hf://harman/gemma2-9b_ultrafeedback-RM_pairpm/config.json
-
curl -L -o config.json https://huggingface.co/harman/gemma2-9b_ultrafeedback-RM_pairpm/resolve/main/config.json
1.05 kB
| { | |
| "_name_or_path": "/home/hrman/CARMA/pm_models_trl/gemma2-9b_ultrafeedback-binarized-preferences-cleaned-neutral_lamda_0_loss-type_custom_logprob_with_neutrals_lamda_lr1e-6_v1_debug/checkpoint-237/", | |
| "architectures": [ | |
| "Gemma2Model" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": 50.0, | |
| "bos_token_id": 2, | |
| "cache_implementation": "hybrid", | |
| "eos_token_id": 1, | |
| "final_logit_softcapping": 30.0, | |
| "head_dim": 256, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 3584, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "model_type": "gemma2", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 42, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "sliding_window_size": 4096, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.3", | |
| "use_cache": false, | |
| "vocab_size": 256000 | |
| } | |