Upload H3ForCausalLM
Browse files- config.json +28 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"H3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attn_layer_idx": [
|
| 6 |
+
8,
|
| 7 |
+
16
|
| 8 |
+
],
|
| 9 |
+
"bos_token_id": 50256,
|
| 10 |
+
"embedding_dropout": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"glu_act": false,
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"layer_norm_epsilon": 1e-05,
|
| 16 |
+
"model_type": "h3",
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"rescale_prenorm_residual": true,
|
| 21 |
+
"residual_dropout": 0.0,
|
| 22 |
+
"residual_in_fp32": false,
|
| 23 |
+
"ssm_measure": "diag-lin",
|
| 24 |
+
"ssm_mode": "diag",
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.28.0.dev0",
|
| 27 |
+
"vocab_size": 50264
|
| 28 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.28.0.dev0"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:989555957c117849e3f9593269dea5d812352e43ef53cb4fe082f6e0b70bc553
|
| 3 |
+
size 5310335882
|