DeepSeek-R1-Distill-Qwen-1.5B-MLC / mlc-chat-config.json
sauravpanda's picture
Upload folder using huggingface_hub
afdc38c verified
raw
history blame
1.95 kB
{
"version": "0.1.0",
"model_type": "qwen2",
"quantization": "q0f32",
"model_config": {
"hidden_act": "silu",
"hidden_size": 1536,
"intermediate_size": 8960,
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_theta": 10000,
"vocab_size": 151936,
"tie_word_embeddings": false,
"context_window_size": 131072,
"prefill_chunk_size": 8192,
"tensor_parallel_shards": 1,
"head_dim": 128,
"dtype": "float32",
"max_batch_size": 128
},
"vocab_size": 151936,
"context_window_size": 131072,
"sliding_window_size": -1,
"prefill_chunk_size": 8192,
"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.json",
"tokenizer_config.json"
],
"tokenizer_info": {
"token_postproc_method": "byte_level",
"prepend_space_in_encode": false,
"strip_space_in_decode": false
},
"conv_template": {
"name": "deepseek_v2",
"system_template": "{system_message}",
"system_message": "",
"system_prefix_token_ids": [
100000
],
"add_role_after_system_message": true,
"roles": {
"user": "User",
"assistant": "Assistant"
},
"role_templates": {
"user": "{user_message}",
"assistant": "{assistant_message}",
"tool": "{tool_message}"
},
"messages": [],
"seps": [
"\n\n",
"<\uff5cend\u2581of\u2581sentence\uff5c>"
],
"role_content_sep": ": ",
"role_empty_sep": ":",
"stop_str": [
"<\uff5cend\u2581of\u2581sentence\uff5c>"
],
"stop_token_ids": [
100001
],
"function_string": "",
"use_function_calling": false
},
"pad_token_id": 0,
"bos_token_id": 151643,
"eos_token_id": 151643
}