abhinavkulkarni
commited on
Commit
·
d30e37b
1
Parent(s):
7dd4893
Upload LlamaForCausalLM
Browse files- config.json +3 -3
- generation_config.json +1 -1
- pytorch_model.bin +1 -1
config.json
CHANGED
@@ -9,18 +9,18 @@
|
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 11008,
|
12 |
-
"max_position_embeddings":
|
13 |
"model_type": "llama",
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
16 |
"num_key_value_heads": 32,
|
17 |
"pad_token_id": 0,
|
18 |
"pretraining_tp": 1,
|
19 |
-
"rms_norm_eps": 1e-
|
20 |
"rope_scaling": null,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "float16",
|
23 |
-
"transformers_version": "4.
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 32000
|
26 |
}
|
|
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 4096,
|
13 |
"model_type": "llama",
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
16 |
"num_key_value_heads": 32,
|
17 |
"pad_token_id": 0,
|
18 |
"pretraining_tp": 1,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
"rope_scaling": null,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.31.0",
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 32000
|
26 |
}
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 0,
|
6 |
-
"transformers_version": "4.
|
7 |
}
|
|
|
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 3889575897
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4b37309c09f20316215c98bdf1205070718ae2c0fccd25d4c9e799cc84d7a65
|
3 |
size 3889575897
|