.ipynb_checkpoints/config-checkpoint.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "_name_or_path": "Qwen/Qwen2-72B-Instruct",
3
- "architectures": [
4
- "Qwen2ForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151645,
9
- "hidden_act": "silu",
10
- "hidden_size": 8192,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 29568,
13
- "max_position_embeddings": 32768,
14
- "max_window_layers": 80,
15
- "model_type": "qwen2",
16
- "num_attention_heads": 64,
17
- "num_hidden_layers": 80,
18
- "num_key_value_heads": 8,
19
- "rms_norm_eps": 1e-06,
20
- "rope_theta": 1000000.0,
21
- "sliding_window": 131072,
22
- "tie_word_embeddings": false,
23
- "torch_dtype": "bfloat16",
24
- "transformers_version": "4.41.0",
25
- "use_cache": true,
26
- "use_sliding_window": false,
27
- "vocab_size": 151646
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
.ipynb_checkpoints/generation_config-checkpoint.json DELETED
@@ -1,11 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": 151645,
5
- "pad_token_id": 151643,
6
- "repetition_penalty": 1.05,
7
- "temperature": 0.7,
8
- "top_k": 20,
9
- "top_p": 0.8,
10
- "transformers_version": "4.41.0"
11
- }