|
{ |
|
"model_type": "llama", |
|
"quantization": "q4f32_1", |
|
"model_config": { |
|
"hidden_size": 4096, |
|
"intermediate_size": 11008, |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 30, |
|
"rms_norm_eps": 1e-06, |
|
"vocab_size": 102400, |
|
"position_embedding_base": 10000.0, |
|
"context_window_size": 4096, |
|
"prefill_chunk_size": 4096, |
|
"num_key_value_heads": 32, |
|
"head_dim": 128, |
|
"tensor_parallel_shards": 1, |
|
"max_batch_size": 80 |
|
}, |
|
"vocab_size": 102400, |
|
"context_window_size": 4096, |
|
"sliding_window_size": -1, |
|
"prefill_chunk_size": 4096, |
|
"attention_sink_size": -1, |
|
"tensor_parallel_shards": 1, |
|
"mean_gen_len": 128, |
|
"max_gen_len": 512, |
|
"shift_fill_factor": 0.3, |
|
"temperature": 0.7, |
|
"presence_penalty": 0.0, |
|
"frequency_penalty": 0.0, |
|
"repetition_penalty": 1.0, |
|
"top_p": 0.95, |
|
"conv_template": { |
|
"name": "gorilla", |
|
"system_template": "{system_message}", |
|
"system_message": "A chat between a curious user and an artificial intelligence assistant. The assistant provides helpful, detailed, and polite responses to the user's inquiries.", |
|
"roles": { |
|
"user": "USER", |
|
"assistant": "ASSISTANT", |
|
"tool": "USER" |
|
}, |
|
"role_templates": { |
|
"user": "<<question>> {user_message} <<function>> {function_string}", |
|
"assistant": "{assistant_message}", |
|
"tool": "{tool_message}" |
|
}, |
|
"messages": [], |
|
"seps": [ |
|
"\n", |
|
"</s>" |
|
], |
|
"role_content_sep": ": ", |
|
"role_empty_sep": ":", |
|
"stop_str": [ |
|
"</s>" |
|
], |
|
"stop_token_ids": [ |
|
2 |
|
], |
|
"function_string": "", |
|
"use_function_calling": false |
|
}, |
|
"pad_token_id": 0, |
|
"bos_token_id": 100000, |
|
"eos_token_id": 100015, |
|
"tokenizer_files": [ |
|
"tokenizer.json", |
|
"tokenizer_config.json" |
|
], |
|
"version": "0.1.0" |
|
} |