config.json

{
  "architectures": [
    "MixtralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mixtral",
  "num_attention_heads": 32,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "num_local_experts": 8,
  "output_router_logits": false,
  "rms_norm_eps": 1e-05,
  "rope_theta": 1000000.0,
  "router_aux_loss_coef": 0.02,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.36.0.dev0",
  "use_cache": true,
  "vocab_size": 32000
}
{
  "_name_or_path": "/fsx/bigcode/experiments/pretraining/conversions/starcoderpy/large-model",
  "activation_function": "gelu",
  "architectures": [
    "GPTBigCodeForCausalLM"
  ],
  "attention_softmax_in_fp32": true,
  "multi_query": true,
  "attn_pdrop": 0.1,
  "bos_token_id": 0,
  "embd_pdrop": 0.1,
  "eos_token_id": 0,
  "inference_runner": 0,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "max_batch_size": null,
  "max_sequence_length": null,
  "model_type": "gpt_bigcode",
  "n_embd": 6144,
  "n_head": 48,
  "n_inner": 24576,
  "n_layer": 40,
  "n_positions": 8192,
  "pad_key_length": true,
  "pre_allocate_kv_cache": false,
  "resid_pdrop": 0.1,
  "scale_attention_softmax_in_fp32": true,
  "scale_attn_weights": true,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "torch_dtype": "float32",
  "transformers_version": "4.28.1",
  "use_cache": true,
  "validate_runner_input": true,
  "vocab_size": 49152
}