Update config.json
Browse files- config.json +20 -10
config.json
CHANGED
|
@@ -4,28 +4,38 @@
|
|
| 4 |
"GPT2LMHeadModel"
|
| 5 |
],
|
| 6 |
"attn_pdrop": 0.1,
|
| 7 |
-
"bos_token_id":
|
| 8 |
-
"pad_token_id": 0,
|
| 9 |
"embd_pdrop": 0.1,
|
|
|
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"layer_norm_epsilon": 1e-05,
|
| 12 |
"model_type": "gpt2",
|
| 13 |
-
"n_ctx":
|
| 14 |
-
"n_embd":
|
| 15 |
-
"n_head":
|
| 16 |
-
"
|
| 17 |
-
"
|
|
|
|
|
|
|
| 18 |
"resid_pdrop": 0.1,
|
|
|
|
|
|
|
| 19 |
"summary_activation": null,
|
| 20 |
-
|
| 21 |
"summary_proj_to_labels": true,
|
| 22 |
"summary_type": "cls_index",
|
| 23 |
"summary_use_proj": true,
|
| 24 |
"task_specific_params": {
|
| 25 |
"text-generation": {
|
| 26 |
"do_sample": true,
|
| 27 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
-
"
|
|
|
|
|
|
|
| 31 |
}
|
|
|
|
| 4 |
"GPT2LMHeadModel"
|
| 5 |
],
|
| 6 |
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
|
|
|
| 8 |
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": null,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"layer_norm_epsilon": 1e-05,
|
| 12 |
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 256,
|
| 14 |
+
"n_embd": 384,
|
| 15 |
+
"n_head": 6,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 6,
|
| 18 |
+
"n_positions": 256,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
"summary_proj_to_labels": true,
|
| 26 |
"summary_type": "cls_index",
|
| 27 |
"summary_use_proj": true,
|
| 28 |
"task_specific_params": {
|
| 29 |
"text-generation": {
|
| 30 |
"do_sample": true,
|
| 31 |
+
"max_new_tokens": 128,
|
| 32 |
+
"temperature": 0.9,
|
| 33 |
+
"top_k": 12,
|
| 34 |
+
"top_p": 0.95,
|
| 35 |
+
"repetition_penalty": 1.1
|
| 36 |
}
|
| 37 |
},
|
| 38 |
+
"tie_word_embeddings": true,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 32000
|
| 41 |
}
|