MLX
English
llama

fix-config

#4
by pcuenq HF staff - opened
Files changed (2) hide show
  1. config.json +9 -25
  2. params.json +0 -10
config.json CHANGED
@@ -1,27 +1,11 @@
1
  {
2
- "_name_or_path": "/mnt/petrelfs/libo1.p/alignment-handbook/data/tinyllama-2T-sft-full",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 2048,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 5632,
13
- "max_position_embeddings": 2048,
14
- "model_type": "llama",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 22,
17
- "num_key_value_heads": 4,
18
- "pretraining_tp": 1,
19
- "rms_norm_eps": 1e-05,
20
- "rope_scaling": null,
21
- "rope_theta": 10000.0,
22
- "tie_word_embeddings": false,
23
- "torch_dtype": "bfloat16",
24
- "transformers_version": "4.35.0",
25
- "use_cache": false,
26
- "vocab_size": 32000
27
  }
 
1
  {
2
+ "dim": 2048,
3
+ "hidden_dim": 5632,
4
+ "n_heads": 32,
5
+ "n_kv_heads": 4,
6
+ "n_layers": 22,
7
+ "vocab_size": 32000,
8
+ "norm_eps": 1e-05,
9
+ "rope_traditional": false,
10
+ "model_type": "llama"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  }
params.json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "dim": 2048,
3
- "hidden_dim": 5632,
4
- "n_heads": 32,
5
- "n_kv_heads": 4,
6
- "n_layers": 22,
7
- "vocab_size": 32000,
8
- "norm_eps": 1e-05,
9
- "rope_traditional": false
10
- }