|
{ |
|
"version": "0.1.0", |
|
"model_type": "gemma2", |
|
"quantization": "w4a16g128", |
|
"model_config": { |
|
"hidden_size": 3584, |
|
"intermediate_size": 14336, |
|
"attention_bias": false, |
|
"num_attention_heads": 16, |
|
"num_key_value_heads": 8, |
|
"head_dim": 256, |
|
"num_hidden_layers": 42, |
|
"rms_norm_eps": 1e-06, |
|
"vocab_size": 256000, |
|
"hidden_activation": "gelu_pytorch_tanh", |
|
"position_embedding_base": 10000.0, |
|
"context_window_size": 4096, |
|
"prefill_chunk_size": 128, |
|
"tensor_parallel_shards": 1, |
|
"max_batch_size": 128, |
|
"attn_logit_softcapping": 50.0, |
|
"final_logit_softcapping": 30.0, |
|
"query_pre_attn_scalar": 256, |
|
"sliding_window": 4096 |
|
}, |
|
"vocab_size": 256000, |
|
"context_window_size": 4096, |
|
"sliding_window_size": -1, |
|
"prefill_chunk_size": 128, |
|
"attention_sink_size": -1, |
|
"tensor_parallel_shards": 1, |
|
"pipeline_parallel_stages": 1, |
|
"temperature": 1.0, |
|
"presence_penalty": 0.0, |
|
"frequency_penalty": 0.0, |
|
"repetition_penalty": 1.0, |
|
"top_p": 1.0, |
|
"tokenizer_files": [ |
|
"tokenizer.model", |
|
"tokenizer.json", |
|
"tokenizer_config.json" |
|
], |
|
"tokenizer_info": { |
|
"token_postproc_method": "byte_fallback", |
|
"prepend_space_in_encode": false, |
|
"strip_space_in_decode": false |
|
}, |
|
"conv_template": { |
|
"name": "gemma_instruction", |
|
"system_template": "{system_message}", |
|
"system_message": "", |
|
"system_prefix_token_ids": [ |
|
2 |
|
], |
|
"add_role_after_system_message": true, |
|
"roles": { |
|
"user": "<start_of_turn>user", |
|
"assistant": "<start_of_turn>model" |
|
}, |
|
"role_templates": { |
|
"user": "{user_message}", |
|
"assistant": "{assistant_message}", |
|
"tool": "{tool_message}" |
|
}, |
|
"messages": [], |
|
"seps": [ |
|
"<end_of_turn>\n" |
|
], |
|
"role_content_sep": "\n", |
|
"role_empty_sep": "\n", |
|
"stop_str": [ |
|
"<end_of_turn>" |
|
], |
|
"stop_token_ids": [ |
|
1, |
|
107 |
|
], |
|
"function_string": "", |
|
"use_function_calling": false |
|
}, |
|
"pad_token_id": 0, |
|
"bos_token_id": 2, |
|
"eos_token_id": 1 |
|
} |