| { | |
| "_name_or_path": "/fsx/dakota/ckpts/stablelm_zephyr_16_rc2_with_sk_lowlr_nowd_tinypar_hf_r4", | |
| "architectures": [ | |
| "StableLMEpochForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig", | |
| "AutoModelForCausalLM": "modeling_stablelm_epoch.StableLMEpochForCausalLM" | |
| }, | |
| "bos_token_id": 100257, | |
| "eos_token_id": 100257, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5632, | |
| "max_position_embeddings": 4096, | |
| "model_type": "stablelm_epoch", | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 32, | |
| "num_heads": 32, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 32, | |
| "rope_pct": 0.25, | |
| "rope_theta": 10000, | |
| "rotary_scaling_factor": 1.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.36.2", | |
| "use_cache": true, | |
| "use_qkv_bias": true, | |
| "vocab_size": 100352 | |
| } | |