falcon-40b/config.json
Falcon LLM TII UAE f1ba7d328c Move to in-library checkpoint (#81)
- Convert to in-library checkpoint (a68ca4bd1529de99d45d23edd76fddb759a204a7)
- Preparations for transition to in-library checkpoint (3900116669a68ed777f5ce06a1d4d3cfe580693f)
- Fix typo (8bda09072cc6d9aba99b24ee2c69939a316667d9)
- Revert to Falcon naming (12c569a077dfd03ebecc377af7d4e940891ee315)
2023-07-12 21:33:10 +00:00

34 lines
1.0 KiB
JSON

{
"alibi": false,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"FalconForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_falcon.FalconConfig",
"AutoModel": "modeling_falcon.FalconModel",
"AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
"AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",
"AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
"AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"
},
"bias": false,
"bos_token_id": 11,
"eos_token_id": 11,
"hidden_dropout": 0.0,
"hidden_size": 8192,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "falcon",
"new_decoder_architecture": true,
"num_attention_heads": 128,
"num_hidden_layers": 60,
"num_kv_heads": 8,
"parallel_attn": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.27.4",
"use_cache": true,
"vocab_size": 65024
}