Publish MatterWaveAI/grt-10m with 10-task SLM-Bench evaluation (T-040)
Browse files- config.json +30 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"angle_init_scale": 0.1,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GRTForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 2,
|
| 7 |
+
"coupling_init_scale": 0.01,
|
| 8 |
+
"d_ff": null,
|
| 9 |
+
"d_model": 256,
|
| 10 |
+
"dropout": 0.0,
|
| 11 |
+
"eos_token_id": 3,
|
| 12 |
+
"ffn_mult": 4,
|
| 13 |
+
"ffn_n_rotations": 9,
|
| 14 |
+
"learnable_rope": true,
|
| 15 |
+
"log_magnitude_init": 0.0,
|
| 16 |
+
"max_seq_len": 1024,
|
| 17 |
+
"model_type": "grt",
|
| 18 |
+
"n_blocks": 6,
|
| 19 |
+
"n_heads": 4,
|
| 20 |
+
"n_mixer_rotations": 1,
|
| 21 |
+
"n_qkv_rotations": 5,
|
| 22 |
+
"num_hidden_layers": 6,
|
| 23 |
+
"output_scale_init": 30.0,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"phase_init_scale": 0.1,
|
| 26 |
+
"pos_freq_base": 10000.0,
|
| 27 |
+
"residual_gate_mode": "bounded_depth",
|
| 28 |
+
"transformers_version": "5.10.2",
|
| 29 |
+
"vocab_size": 50000
|
| 30 |
+
}
|