Upload config.json
Browse files- config.json +40 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "core42/jais-13b-chat",
|
| 3 |
+
"activation_function": "swiglu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"JAISLMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "core42/jais-13b-chat--configuration_jais.JAISConfig",
|
| 10 |
+
"AutoModel": "core42/jais-13b-chat--modeling_jais.JAISModel",
|
| 11 |
+
"AutoModelForCausalLM": "core42/jais-13b-chat--modeling_jais.JAISLMHeadModel",
|
| 12 |
+
"AutoModelForQuestionAnswering": "core42/jais-13b-chat--modeling_jais.JAISForQuestionAnswering",
|
| 13 |
+
"AutoModelForSequenceClassification": "core42/jais-13b-chat--modeling_jais.JAISForSequenceClassification",
|
| 14 |
+
"AutoModelForTokenClassification": "core42/jais-13b-chat--modeling_jais.JAISForTokenClassification"
|
| 15 |
+
},
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"embd_pdrop": 0.0,
|
| 18 |
+
"embeddings_scale": 14.6,
|
| 19 |
+
"eos_token_id": 0,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"layer_norm_epsilon": 1e-05,
|
| 22 |
+
"model_type": "jais",
|
| 23 |
+
"n_embd": 5120,
|
| 24 |
+
"n_head": 40,
|
| 25 |
+
"n_inner": 13653,
|
| 26 |
+
"n_layer": 40,
|
| 27 |
+
"n_positions": 2048,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"position_embedding_type": "alibi",
|
| 30 |
+
"reorder_and_upcast_attn": false,
|
| 31 |
+
"resid_pdrop": 0.0,
|
| 32 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 33 |
+
"scale_attn_weights": true,
|
| 34 |
+
"scale_qk_dot_by_d": true,
|
| 35 |
+
"torch_dtype": "float16",
|
| 36 |
+
"transformers_version": "4.31.0",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 84992,
|
| 39 |
+
"width_scale": 0.11100000000000002
|
| 40 |
+
}
|