Yhhxhfh commited on
Commit
eb8f22e
·
verified ·
1 Parent(s): e889c2a

Upload 2 files

Browse files
Files changed (2) hide show
  1. config.json +31 -32
  2. generation_config.json +12 -0
config.json CHANGED
@@ -1,41 +1,40 @@
1
  {
2
- "activation_function": "gelu_new",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
- "attn_pdrop": 0.1,
7
- "bos_token_id": 50256,
8
- "embd_pdrop": 0.1,
9
- "eos_token_id": 50256,
 
 
 
 
 
 
 
10
  "initializer_range": 0.02,
11
- "layer_norm_epsilon": 1e-05,
 
 
12
  "model_type": "llama",
13
- "n_ctx": 1024,
14
- "n_embd": 768,
15
- "n_head": 12,
16
- "n_inner": null,
17
- "n_layer": 12,
18
- "n_positions": 1024,
19
- "reorder_and_upcast_attn": false,
20
- "resid_pdrop": 0.1,
21
- "scale_attn_by_inverse_layer_idx": false,
22
- "scale_attn_weights": true,
23
- "summary_activation": null,
24
- "summary_first_dropout": 0.1,
25
- "summary_proj_to_labels": true,
26
- "summary_type": "cls_index",
27
- "summary_use_proj": true,
28
- "task_specific_params": {
29
- "text-generation": {
30
- "temperature": 1.0,
31
- "top_p": 0.9,
32
- "top_k": 50,
33
- "do_sample": true,
34
- "max_length": -1
35
- }
36
  },
37
- "torch_dtype": "float32",
 
 
38
  "transformers_version": "4.44.2",
39
- "use_cache": true,
40
- "vocab_size": 50257
41
  }
 
1
  {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
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
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
  "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
  "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
 
 
 
 
 
 
 
 
 
 
 
 
33
  },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
  "transformers_version": "4.44.2",
38
+ "use_cache": false,
39
+ "vocab_size": 128256
40
  }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.44.2"
12
+ }