add model
Browse files- config.json +10 -5
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -13,10 +13,10 @@
|
|
| 13 |
"layer_norm_epsilon": 1e-05,
|
| 14 |
"model_type": "gpt2",
|
| 15 |
"n_ctx": 1024,
|
| 16 |
-
"n_embd":
|
| 17 |
-
"n_head":
|
| 18 |
"n_inner": null,
|
| 19 |
-
"n_layer":
|
| 20 |
"n_positions": 1024,
|
| 21 |
"reorder_and_upcast_attn": false,
|
| 22 |
"resid_pdrop": 0.1,
|
|
@@ -29,7 +29,12 @@
|
|
| 29 |
"summary_use_proj": true,
|
| 30 |
"task_specific_params": {
|
| 31 |
"conversational": {
|
| 32 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
}
|
| 34 |
},
|
| 35 |
"torch_dtype": "float32",
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "deepparag/Aeona-Beta",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
| 13 |
"layer_norm_epsilon": 1e-05,
|
| 14 |
"model_type": "gpt2",
|
| 15 |
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
"n_inner": null,
|
| 19 |
+
"n_layer": 12,
|
| 20 |
"n_positions": 1024,
|
| 21 |
"reorder_and_upcast_attn": false,
|
| 22 |
"resid_pdrop": 0.1,
|
| 29 |
"summary_use_proj": true,
|
| 30 |
"task_specific_params": {
|
| 31 |
"conversational": {
|
| 32 |
+
"do_sample": true,
|
| 33 |
+
"max_length": 1000,
|
| 34 |
+
"no_repeat_ngram_size": 4,
|
| 35 |
+
"temperature": 0.85,
|
| 36 |
+
"top_k": 100,
|
| 37 |
+
"top_p": 0.7
|
| 38 |
}
|
| 39 |
},
|
| 40 |
"torch_dtype": "float32",
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60a4d0be2466a51acc917e7fabee99929bc9b03508ccddc8d08209b62da85468
|
| 3 |
+
size 510394089
|