danielhanchen commited on
Commit
0febdb3
1 Parent(s): 25418ba

Upload config

Browse files
Files changed (1) hide show
  1. config.json +3 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "Qwen/Qwen2-72B-Instruct",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
@@ -16,6 +16,7 @@
16
  "num_attention_heads": 64,
17
  "num_hidden_layers": 80,
18
  "num_key_value_heads": 8,
 
19
  "quantization_config": {
20
  "_load_in_4bit": true,
21
  "_load_in_8bit": false,
@@ -37,6 +38,7 @@
37
  "tie_word_embeddings": false,
38
  "torch_dtype": "bfloat16",
39
  "transformers_version": "4.44.0",
 
40
  "use_cache": true,
41
  "use_sliding_window": false,
42
  "vocab_size": 152064
 
1
  {
2
+ "_name_or_path": "unsloth/Qwen2-72B-Instruct",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
 
16
  "num_attention_heads": 64,
17
  "num_hidden_layers": 80,
18
  "num_key_value_heads": 8,
19
+ "pad_token_id": 151643,
20
  "quantization_config": {
21
  "_load_in_4bit": true,
22
  "_load_in_8bit": false,
 
38
  "tie_word_embeddings": false,
39
  "torch_dtype": "bfloat16",
40
  "transformers_version": "4.44.0",
41
+ "unsloth_version": "2024.8",
42
  "use_cache": true,
43
  "use_sliding_window": false,
44
  "vocab_size": 152064