40 lines
1.8 KiB
JSON
40 lines
1.8 KiB
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 128000,
|
||
|
|
"chat_template": "{{- bos_token }}\n{%- if not date_string is defined %}\n{%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n{%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- endif %}\n\n{#- Remove system message handling entirely #}\n{%- if messages[0]['role'] == 'system' %}\n{%- set messages = messages[1:] %}\n{%- endif %}\n\n{#- Process messages with role mapping #}\n{%- for message in messages %}\n{%- if message['role'] == 'user' %}\n {{- '<|start_header_id|>text<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}\n{%- elif message['role'] == 'assistant' %}\n {{- '<|start_header_id|>corrected<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}\n{%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n{{- '<|start_header_id|>corrected<|end_header_id|>\n\n' }}\n{%- endif %}",
|
||
|
|
"eos_token_id": 128001,
|
||
|
|
"head_dim": 64,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 2048,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 8192,
|
||
|
|
"max_position_embeddings": 131072,
|
||
|
|
"mlp_bias": false,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 16,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"pad_token_id": 128004,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_scaling": {
|
||
|
|
"factor": 32.0,
|
||
|
|
"high_freq_factor": 4.0,
|
||
|
|
"low_freq_factor": 1.0,
|
||
|
|
"original_max_position_embeddings": 8192,
|
||
|
|
"rope_type": "llama3"
|
||
|
|
},
|
||
|
|
"rope_theta": 500000.0,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.52.4",
|
||
|
|
"unsloth_fixed": true,
|
||
|
|
"unsloth_version": "2025.5.9",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 128256
|
||
|
|
}
|