create_model
#1
by
haoyang-amd
- opened
- config.json +35 -0
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/group/amdneuralopt/huggingface/pretrained_models/databricks/dbrx-instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DbrxForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attn_config": {
|
| 7 |
+
"clip_qkv": 8,
|
| 8 |
+
"kv_n_heads": 8,
|
| 9 |
+
"model_type": "",
|
| 10 |
+
"rope_theta": 500000
|
| 11 |
+
},
|
| 12 |
+
"d_model": 6144,
|
| 13 |
+
"emb_pdrop": 0.0,
|
| 14 |
+
"ffn_config": {
|
| 15 |
+
"ffn_hidden_size": 10752,
|
| 16 |
+
"model_type": "",
|
| 17 |
+
"moe_jitter_eps": 0,
|
| 18 |
+
"moe_loss_weight": 0.05,
|
| 19 |
+
"moe_num_experts": 16,
|
| 20 |
+
"moe_top_k": 4
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"max_seq_len": 32768,
|
| 24 |
+
"model_type": "dbrx",
|
| 25 |
+
"n_heads": 48,
|
| 26 |
+
"n_layers": 1,
|
| 27 |
+
"num_key_value_heads": 8,
|
| 28 |
+
"output_router_logits": false,
|
| 29 |
+
"resid_pdrop": 0.0,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.45.2",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 100352
|
| 35 |
+
}
|