ashwinij2/Deepseek_converted_model
08
1{
2 "_name_or_path": "converted_model",
3 "architectures": [
4 "Qwen2ForCausalLM"
5 ],
6 "attention_dropout": 0.0,
7 "bos_token_id": 151643,
8 "eos_token_id": 151643,
9 "hidden_act": "silu",
10 "hidden_size": 1536,
11 "initializer_range": 0.02,
12 "intermediate_size": 8960,
13 "max_position_embeddings": 131072,
14 "max_window_layers": 21,
15 "model_type": "qwen2",
16 "num_attention_heads": 12,
17 "num_hidden_layers": 28,
18 "num_key_value_heads": 2,
19 "rms_norm_eps": 1e-06,
20 "rope_scaling": null,
21 "rope_theta": 10000,
22 "sliding_window": 4096,
23 "tie_word_embeddings": false,
24 "torch_dtype": "float32",
25 "transformers_version": "4.49.0",
26 "use_cache": true,
27 "use_mrope": false,
28 "use_sliding_window": false,
29 "vocab_size": 151936
30}
31 