Dogge commited on
Commit
f06d86f
1 Parent(s): 08f6617

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +6 -6
  2. generation_config.json +1 -1
  3. tokenizer_config.json +1 -1
config.json CHANGED
@@ -1,20 +1,20 @@
1
  {
2
- "_name_or_path": "unsloth/llama-3-8b-Instruct",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
- "eos_token_id": 128001,
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,
 
1
  {
2
+ "_name_or_path": "unsloth/llama-3-70b-Instruct-bnb-4bit",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
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
  "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 80,
18
  "num_key_value_heads": 8,
19
  "pretraining_tp": 1,
20
  "rms_norm_eps": 1e-05,
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 128000,
4
- "eos_token_id": 128001,
5
  "transformers_version": "4.40.0"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 128000,
4
+ "eos_token_id": 128009,
5
  "transformers_version": "4.40.0"
6
  }
tokenizer_config.json CHANGED
@@ -2052,7 +2052,7 @@
2052
  "bos_token": "<|begin_of_text|>",
2053
  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
  "clean_up_tokenization_spaces": true,
2055
- "eos_token": "<|end_of_text|>",
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
 
2052
  "bos_token": "<|begin_of_text|>",
2053
  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
  "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"