Upload config
Browse files- config.json +22 -0
config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "mamba_hypernetwork",
|
| 3 |
+
"vocab_size": 128000,
|
| 4 |
+
"hidden_dim": 1024,
|
| 5 |
+
"state_dim": 16,
|
| 6 |
+
"expand": 4,
|
| 7 |
+
"num_llm_layers": 8,
|
| 8 |
+
"lora_rank": 16,
|
| 9 |
+
"q_proj_dim": 3072,
|
| 10 |
+
"v_proj_dim": 1024,
|
| 11 |
+
"llm_name": "meta-llama/Llama-3.2-3B-Instruct",
|
| 12 |
+
"reward_model": "phammminhhieu/persona-reward-model",
|
| 13 |
+
"training_config": {
|
| 14 |
+
"batch_size": 2,
|
| 15 |
+
"K": 4,
|
| 16 |
+
"epochs": 3,
|
| 17 |
+
"lr": 0.0005,
|
| 18 |
+
"lambda_grpo": 0.05,
|
| 19 |
+
"lambda_kl": 0.1,
|
| 20 |
+
"temperature": 0.8
|
| 21 |
+
}
|
| 22 |
+
}
|