m8than commited on
Commit
5753fb1
·
verified ·
1 Parent(s): 3ea6172

Upload folder using huggingface_hub

Browse files
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/Reflection-Llama-3.1-70B-ep2-working",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "hidden_act": "silu",
15
+ "hidden_size": 8192,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 28672,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 64,
22
+ "num_hidden_layers": 80,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "quantization_config": {
26
+ "activation_scheme": "dynamic",
27
+ "ignored_layers": [
28
+ "lm_head"
29
+ ],
30
+ "quant_method": "fp8"
31
+ },
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": {
34
+ "factor": 8.0,
35
+ "high_freq_factor": 4.0,
36
+ "low_freq_factor": 1.0,
37
+ "original_max_position_embeddings": 8192,
38
+ "rope_type": "llama3"
39
+ },
40
+ "rope_theta": 500000.0,
41
+ "tie_word_embeddings": false,
42
+ "torch_dtype": "float16",
43
+ "transformers_version": "4.37.0",
44
+ "use_cache": true,
45
+ "vocab_size": 128262
46
+ }
config.json CHANGED
@@ -32,7 +32,10 @@
32
  "rms_norm_eps": 1e-05,
33
  "rope_scaling": {
34
  "factor": 8.0,
35
- "type": "dynamic"
 
 
 
36
  },
37
  "rope_theta": 500000.0,
38
  "tie_word_embeddings": false,
 
32
  "rms_norm_eps": 1e-05,
33
  "rope_scaling": {
34
  "factor": 8.0,
35
+ "high_freq_factor": 4.0,
36
+ "low_freq_factor": 1.0,
37
+ "original_max_position_embeddings": 8192,
38
+ "rope_type": "llama3"
39
  },
40
  "rope_theta": 500000.0,
41
  "tie_word_embeddings": false,