danielhanchen commited on
Commit
4b5d09f
·
verified ·
1 Parent(s): 6857b52

Upload config

Browse files
Files changed (2) hide show
  1. README.md +1 -2
  2. config.json +5 -3
README.md CHANGED
@@ -1,15 +1,14 @@
1
  ---
2
  language:
3
  - en
4
- license: apache-2.0
5
  library_name: transformers
 
6
  tags:
7
  - unsloth
8
  - transformers
9
  - llama
10
  - llama2
11
  - llama-2
12
-
13
  ---
14
 
15
  # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
 
1
  ---
2
  language:
3
  - en
 
4
  library_name: transformers
5
+ license: apache-2.0
6
  tags:
7
  - unsloth
8
  - transformers
9
  - llama
10
  - llama2
11
  - llama-2
 
12
  ---
13
 
14
  # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "meta-llama/Llama-2-13b-hf",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -12,6 +12,7 @@
12
  "initializer_range": 0.02,
13
  "intermediate_size": 13824,
14
  "max_position_embeddings": 4096,
 
15
  "model_type": "llama",
16
  "num_attention_heads": 40,
17
  "num_hidden_layers": 40,
@@ -22,8 +23,9 @@
22
  "rope_scaling": null,
23
  "rope_theta": 10000.0,
24
  "tie_word_embeddings": false,
25
- "torch_dtype": "float16",
26
- "transformers_version": "4.37.2",
 
27
  "use_cache": true,
28
  "vocab_size": 32000
29
  }
 
1
  {
2
+ "_name_or_path": "unsloth/llama-2-13b",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
12
  "initializer_range": 0.02,
13
  "intermediate_size": 13824,
14
  "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
  "model_type": "llama",
17
  "num_attention_heads": 40,
18
  "num_hidden_layers": 40,
 
23
  "rope_scaling": null,
24
  "rope_theta": 10000.0,
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": 32000
31
  }