Upload MptForCausalLM
Browse files- config.json +22 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"apply_residual_connection_post_layernorm": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MptForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_dropout": 0.0,
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "mpt",
|
| 14 |
+
"n_head": 32,
|
| 15 |
+
"n_layer": 32,
|
| 16 |
+
"pretraining_tp": 1,
|
| 17 |
+
"slow_but_exact": false,
|
| 18 |
+
"torch_dtype": "bfloat16",
|
| 19 |
+
"transformers_version": "4.31.0.dev0",
|
| 20 |
+
"use_cache": true,
|
| 21 |
+
"vocab_size": 50432
|
| 22 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.31.0.dev0"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cb7eef30ee563dd4a141c01e92f26505f44045de6f5434eebac276349858f2b
|
| 3 |
+
size 17144
|