config_old.json

{
  "architectures": [
    "Gemma2ForCausalLM"
  ],
  "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,
  "generation_config": {
    "_from_model_config": true,
    "assistant_confidence_threshold": 0.4,
    "assistant_early_exit": null,
    "assistant_lookbehind": 10,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 2,
    "cache_config": null,
    "cache_implementation": "hybrid",
    "constraints": null,
    "decoder_start_token_id": null,
    "disable_compile": false,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dola_layers": null,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "encoder_repetition_penalty": 1.0,
    "eos_token_id": 1,
    "epsilon_cutoff": 0.0,
    "eta_cutoff": 0.0,
    "exponential_decay_length_penalty": null,
    "force_words_ids": null,
    "forced_bos_token_id": null,
    "forced_decoder_ids": null,
    "forced_eos_token_id": null,
    "generation_kwargs": {},
    "guidance_scale": null,
    "is_assistant": false,
    "length_penalty": 1.0,
    "low_memory": null,
    "max_length": 20,
    "max_matching_ngram_size": null,
    "max_new_tokens": null,
    "max_time": null,
    "min_length": 0,
    "min_new_tokens": null,
    "min_p": null,
    "no_repeat_ngram_size": 0,
    "num_assistant_tokens": 20,
    "num_assistant_tokens_schedule": "constant",
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_logits": null,
    "output_scores": false,
    "pad_token_id": 0,
    "penalty_alpha": null,
    "prompt_lookup_num_tokens": null,
    "remove_invalid_values": false,
    "renormalize_logits": false,
    "repetition_penalty": 1.0,
    "return_dict_in_generate": false,
    "return_legacy_cache": null,
    "sequence_bias": null,
    "stop_strings": null,
    "suppress_tokens": null,
    "target_lookbehind": 10,
    "temperature": null,
    "token_healing": false,
    "top_k": 50,
    "top_p": null,
    "transformers_version": "4.50.1",
    "typical_p": 1.0,
    "use_cache": true,
    "watermarking_config": null
  },
  "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": "bfloat16",
  "transformers_version": "4.50.1",
  "use_cache": true,
  "vocab_size": 256000
}