|
{ |
|
"_attn_implementation_autoset": true, |
|
"_name_or_path": "NousResearch/CodeLlama-7b-hf-flash", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"auto_map": { |
|
"AutoConfig": "NousResearch/CodeLlama-7b-hf-flash--configuration_llama.LlamaConfig", |
|
"AutoModel": "NousResearch/CodeLlama-7b-hf-flash--modeling_flash_llama.LlamaModel", |
|
"AutoModelForCausalLM": "NousResearch/CodeLlama-7b-hf-flash--modeling_flash_llama.LlamaForCausalLM", |
|
"AutoModelForSequenceClassification": "NousResearch/CodeLlama-7b-hf-flash--modeling_flash_llama.LlamaForSequenceClassification" |
|
}, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 11008, |
|
"max_position_embeddings": 16384, |
|
"model_type": "llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 32, |
|
"pretraining_tp": 1, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 1000000, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.46.0", |
|
"use_cache": false, |
|
"vocab_size": 32016 |
|
} |
|
|