Upload LlamaForCausalLM
Browse files- config.json +4 -1
- generation_config.json +1 -1
- pytorch_model-00001-of-00002.bin +1 -1
- pytorch_model-00002-of-00002.bin +1 -1
config.json
CHANGED
@@ -13,11 +13,14 @@
|
|
13 |
"model_type": "llama",
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
|
|
16 |
"pad_token_id": 0,
|
|
|
17 |
"rms_norm_eps": 1e-06,
|
|
|
18 |
"tie_word_embeddings": false,
|
19 |
"torch_dtype": "float16",
|
20 |
-
"transformers_version": "4.
|
21 |
"use_cache": true,
|
22 |
"vocab_size": 32000
|
23 |
}
|
|
|
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-00001-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9976637886
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f9c768c284b90e1e1d724b9b1becd6e48bf52fa06d350c40d98353e5d622825
|
3 |
size 9976637886
|
pytorch_model-00002-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3500316627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb33599b09b0bf025f58e2d34c4c5d53f5f3946b10f72d66d9b9d59b1532410d
|
3 |
size 3500316627
|