danielhanchen commited on
Commit
9c13a68
1 Parent(s): aff1792

Upload config

Browse files
Files changed (2) hide show
  1. README.md +1 -1
  2. config.json +9 -6
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  language:
3
  - en
4
- license: llama3
5
  library_name: transformers
 
6
  tags:
7
  - unsloth
8
  - transformers
 
1
  ---
2
  language:
3
  - en
 
4
  library_name: transformers
5
+ license: llama3
6
  tags:
7
  - unsloth
8
  - transformers
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -8,21 +8,24 @@
8
  "bos_token_id": 128000,
9
  "eos_token_id": 128009,
10
  "hidden_act": "silu",
11
- "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 14336,
14
  "max_position_embeddings": 8192,
 
15
  "model_type": "llama",
16
- "num_attention_heads": 32,
17
- "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
 
19
  "pretraining_tp": 1,
20
  "rms_norm_eps": 1e-05,
21
  "rope_scaling": null,
22
  "rope_theta": 500000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
- "transformers_version": "4.38.2",
 
26
  "use_cache": true,
27
  "vocab_size": 128256
28
  }
 
1
  {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
8
  "bos_token_id": 128000,
9
  "eos_token_id": 128009,
10
  "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
  "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
  "model_type": "llama",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 80,
19
  "num_key_value_heads": 8,
20
+ "pad_token_id": 128255,
21
  "pretraining_tp": 1,
22
  "rms_norm_eps": 1e-05,
23
  "rope_scaling": null,
24
  "rope_theta": 500000.0,
25
  "tie_word_embeddings": false,
26
  "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.44.0",
28
+ "unsloth_version": "2024.8",
29
  "use_cache": true,
30
  "vocab_size": 128256
31
  }