CroissantLLMChat-v0.1-q4f32_1-MLC / mlc-chat-config.json
llm-slayer's picture
add weights and config files
8aad511
{
"model_type": "llama",
"quantization": "q4f32_1",
"model_config": {
"hidden_size": 2048,
"intermediate_size": 5504,
"num_attention_heads": 16,
"num_hidden_layers": 24,
"rms_norm_eps": 1e-05,
"vocab_size": 32002,
"position_embedding_base": 10000.0,
"context_window_size": 2048,
"prefill_chunk_size": 2048,
"num_key_value_heads": 16,
"head_dim": 128,
"tensor_parallel_shards": 1,
"max_batch_size": 80
},
"vocab_size": 32002,
"context_window_size": 2048,
"sliding_window_size": -1,
"prefill_chunk_size": 2048,
"attention_sink_size": -1,
"tensor_parallel_shards": 1,
"mean_gen_len": 128,
"max_gen_len": 512,
"shift_fill_factor": 0.3,
"temperature": 0.3,
"presence_penalty": 0.0,
"frequency_penalty": 0.0,
"repetition_penalty": 1.05,
"top_p": 0.9,
"conv_template": {
"name": "croissantllm",
"system_template": "<s>",
"system_message": "",
"add_role_after_system_message": true,
"roles": {
"user": "<|im_start|>user",
"assistant": "<|im_start|>assistant"
},
"role_templates": {
"user": "{user_message}",
"assistant": "{assistant_message}",
"tool": "{tool_message}"
},
"messages": [],
"seps": [
"<|im_end|>\n"
],
"role_content_sep": "\n",
"role_empty_sep": "\n",
"stop_str": [
"<|im_end|>",
"</s>"
],
"stop_token_ids": [
32000,
2
],
"function_string": "",
"use_function_calling": false
},
"pad_token_id": 2,
"bos_token_id": 1,
"eos_token_id": 2,
"tokenizer_files": [
"tokenizer.json",
"tokenizer_config.json"
],
"version": "0.1.0"
}