sharpenb's picture
36cee8a421322a4288d1be91114993bfb815d2ef040362bcb959c47f900a334b
a19649f verified
raw
history blame
2.01 kB
{
"_name_or_path": "/covalent/.cache/models/tmp4ec5jw8hng5c2ksp",
"alibi": false,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"FalconForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_falcon.FalconConfig",
"AutoModel": "nqzfaizal77ai/swiftstrike-aero-init-580m--modeling_falcon.FalconModel",
"AutoModelForCausalLM": "nqzfaizal77ai/swiftstrike-aero-init-580m--modeling_falcon.FalconForCausalLM",
"AutoModelForQuestionAnswering": "nqzfaizal77ai/swiftstrike-aero-init-580m--modeling_falcon.FalconForQuestionAnswering",
"AutoModelForSequenceClassification": "nqzfaizal77ai/swiftstrike-aero-init-580m--modeling_falcon.FalconForSequenceClassification",
"AutoModelForTokenClassification": "nqzfaizal77ai/swiftstrike-aero-init-580m--modeling_falcon.FalconForTokenClassification"
},
"bias": false,
"bos_token_id": 11,
"eos_token_id": 11,
"hidden_dropout": 0.0,
"hidden_size": 1280,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "falcon",
"multi_query": true,
"new_decoder_architecture": false,
"num_attention_heads": 20,
"num_hidden_layers": 30,
"num_kv_heads": 71,
"parallel_attn": true,
"quantization_config": {
"_load_in_4bit": false,
"_load_in_8bit": true,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": false,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": [
"lm_head"
],
"llm_int8_threshold": 6.0,
"load_in_4bit": false,
"load_in_8bit": true,
"quant_method": "bitsandbytes"
},
"torch_dtype": "float16",
"transformers_version": "4.46.2",
"use_cache": true,
"vocab_size": 65024,
"api_key": null
}