RichardErkhov commited on
Commit
e4945d2
·
verified ·
1 Parent(s): 243cf52

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +45 -0
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CodeQwen1.5-7B-Chat",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13440,
13
+ "max_position_embeddings": 65536,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 4,
19
+ "quantization_config": {
20
+ "_load_in_4bit": true,
21
+ "_load_in_8bit": false,
22
+ "bnb_4bit_compute_dtype": "float32",
23
+ "bnb_4bit_quant_storage": "uint8",
24
+ "bnb_4bit_quant_type": "fp4",
25
+ "bnb_4bit_use_double_quant": false,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": null,
29
+ "llm_int8_threshold": 6.0,
30
+ "load_in_4bit": true,
31
+ "load_in_8bit": false,
32
+ "quant_method": "bitsandbytes"
33
+ },
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_theta": 1000000,
36
+ "rotary_emb_base": 1000000,
37
+ "seq_length": 65536,
38
+ "sliding_window": 65536,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "float16",
41
+ "transformers_version": "4.39.3",
42
+ "use_cache": true,
43
+ "use_sliding_window": false,
44
+ "vocab_size": 92416
45
+ }