Upload config
Browse files- config.json +3 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
@@ -21,6 +21,7 @@
|
|
| 21 |
"num_attention_heads": 128,
|
| 22 |
"num_hidden_layers": 126,
|
| 23 |
"num_key_value_heads": 8,
|
|
|
|
| 24 |
"pretraining_tp": 1,
|
| 25 |
"quantization_config": {
|
| 26 |
"_load_in_4bit": true,
|
|
@@ -49,6 +50,7 @@
|
|
| 49 |
"tie_word_embeddings": false,
|
| 50 |
"torch_dtype": "bfloat16",
|
| 51 |
"transformers_version": "4.44.2",
|
|
|
|
| 52 |
"use_cache": true,
|
| 53 |
"vocab_size": 128256
|
| 54 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "unsloth/Meta-Llama-3.1-405B-Instruct",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 21 |
"num_attention_heads": 128,
|
| 22 |
"num_hidden_layers": 126,
|
| 23 |
"num_key_value_heads": 8,
|
| 24 |
+
"pad_token_id": 128004,
|
| 25 |
"pretraining_tp": 1,
|
| 26 |
"quantization_config": {
|
| 27 |
"_load_in_4bit": true,
|
|
|
|
| 50 |
"tie_word_embeddings": false,
|
| 51 |
"torch_dtype": "bfloat16",
|
| 52 |
"transformers_version": "4.44.2",
|
| 53 |
+
"unsloth_version": "2024.9",
|
| 54 |
"use_cache": true,
|
| 55 |
"vocab_size": 128256
|
| 56 |
}
|