Upload LlamaForCausalLM
Browse files- config.json +2 -3
- generation_config.json +2 -1
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -3,7 +3,6 @@
|
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
-
"attention_bias": false,
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
@@ -15,13 +14,13 @@
|
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 22,
|
17 |
"num_key_value_heads": 4,
|
|
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-05,
|
20 |
"rope_scaling": null,
|
21 |
-
"rope_theta": 10000.0,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "float32",
|
24 |
-
"transformers_version": "4.
|
25 |
"use_cache": true,
|
26 |
"vocab_size": 32000
|
27 |
}
|
|
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
|
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 22,
|
16 |
"num_key_value_heads": 4,
|
17 |
+
"pad_token_id": 0,
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-05,
|
20 |
"rope_scaling": null,
|
|
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.31.0",
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 32000
|
26 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,6 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"
|
|
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.31.0"
|
7 |
}
|
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 sha256:97faca1e99939788dda0cfeaf366391ac0ca0ac50c455861156a2bbb6c7f9b04
|
3 |
+
size 4400268618
|