Upload BiatronForCausalLM
Browse files- config.json +29 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BiatronForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_output_gate": false,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"head_dim": 64,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_size": 960,
|
| 14 |
+
"initializer_range": 0.0134,
|
| 15 |
+
"intermediate_size": 3840,
|
| 16 |
+
"max_position_embeddings": 4096,
|
| 17 |
+
"mlp_bias": true,
|
| 18 |
+
"model_type": "Biatron",
|
| 19 |
+
"norm_eps": 1e-05,
|
| 20 |
+
"num_attention_heads": 15,
|
| 21 |
+
"num_hidden_layers": 32,
|
| 22 |
+
"num_key_value_heads": 5,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"partial_rotary_factor": 1,
|
| 25 |
+
"rope_theta": 10000.0,
|
| 26 |
+
"transformers_version": "4.57.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 32000
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.57.1"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f51d2afe464609027800e0b48a9d5f83c20eb212cb301bc3342774be0f5610a
|
| 3 |
+
size 691362936
|