debug
Browse files
repocoder-13b-32k-v2/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/workspace/ckpts/codellama-13b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 5120,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 13824,
|
| 12 |
+
"max_position_embeddings": 16384,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 40,
|
| 15 |
+
"num_hidden_layers": 40,
|
| 16 |
+
"num_key_value_heads": 40,
|
| 17 |
+
"pretraining_tp": 1,
|
| 18 |
+
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_scaling": {
|
| 20 |
+
"factor": 2.0,
|
| 21 |
+
"type": "linear"
|
| 22 |
+
},
|
| 23 |
+
"rope_theta": 1000000,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.34.0.dev0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 32016
|
| 29 |
+
}
|