RaymondAISG
commited on
Commit
•
79b43c3
1
Parent(s):
c47e2cf
Upload LlamaForCausalLM
Browse files- README.md +1 -1
- config.json +8 -1
- generation_config.json +2 -6
- model-00001-of-00004.safetensors +2 -2
- model-00002-of-00004.safetensors +2 -2
- model-00003-of-00004.safetensors +2 -2
README.md
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
---
|
2 |
-
license: llama3
|
3 |
language:
|
4 |
- en
|
5 |
- id
|
6 |
- ta
|
7 |
- th
|
8 |
- vi
|
|
|
9 |
---
|
10 |
# LLaMA3 8B SEA-LIONv2
|
11 |
|
|
|
1 |
---
|
|
|
2 |
language:
|
3 |
- en
|
4 |
- id
|
5 |
- ta
|
6 |
- th
|
7 |
- vi
|
8 |
+
license: llama3
|
9 |
---
|
10 |
# LLaMA3 8B SEA-LIONv2
|
11 |
|
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"LlamaForCausalLM"
|
4 |
],
|
@@ -8,20 +9,26 @@
|
|
8 |
"eos_token_id": 128001,
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 4096,
|
|
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 14336,
|
13 |
"max_position_embeddings": 8192,
|
|
|
14 |
"model_type": "llama",
|
|
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
|
|
|
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-05,
|
20 |
"rope_scaling": null,
|
21 |
"rope_theta": 500000.0,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
-
"transformers_version": "4.
|
|
|
25 |
"use_cache": true,
|
26 |
"use_flash_attention_2": true,
|
27 |
"vocab_size": 128256
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/data/users/raymond/hr2",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
9 |
"eos_token_id": 128001,
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
+
"init_device": "cpu",
|
13 |
"initializer_range": 0.02,
|
14 |
"intermediate_size": 14336,
|
15 |
"max_position_embeddings": 8192,
|
16 |
+
"mlp_bias": false,
|
17 |
"model_type": "llama",
|
18 |
+
"name": "hf_causal_lm",
|
19 |
"num_attention_heads": 32,
|
20 |
"num_hidden_layers": 32,
|
21 |
"num_key_value_heads": 8,
|
22 |
+
"pretrained": true,
|
23 |
+
"pretrained_model_name_or_path": "/mnt/fs-arf-01/cpt_checkpoints/meta-llama/Meta-Llama-3-8B",
|
24 |
"pretraining_tp": 1,
|
25 |
"rms_norm_eps": 1e-05,
|
26 |
"rope_scaling": null,
|
27 |
"rope_theta": 500000.0,
|
28 |
"tie_word_embeddings": false,
|
29 |
"torch_dtype": "bfloat16",
|
30 |
+
"transformers_version": "4.42.3",
|
31 |
+
"trust_remote_code": true,
|
32 |
"use_cache": true,
|
33 |
"use_flash_attention_2": true,
|
34 |
"vocab_size": 128256
|
generation_config.json
CHANGED
@@ -1,10 +1,6 @@
|
|
1 |
{
|
|
|
2 |
"bos_token_id": 128000,
|
3 |
"eos_token_id": 128001,
|
4 |
-
"
|
5 |
-
"temperature": 0.6,
|
6 |
-
"max_length": 4096,
|
7 |
-
"top_p": 0.9,
|
8 |
-
"use_cache": true,
|
9 |
-
"transformers_version": "4.43.1"
|
10 |
}
|
|
|
1 |
{
|
2 |
+
"_from_model_config": true,
|
3 |
"bos_token_id": 128000,
|
4 |
"eos_token_id": 128001,
|
5 |
+
"transformers_version": "4.42.3"
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
model-00001-of-00004.safetensors
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 sha256:43d9d421ba1c3534b3783a8bf06aab1bc9721fb0a9ef6d2752a645010068f4ff
|
3 |
+
size 4976698672
|
model-00002-of-00004.safetensors
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 sha256:57eb52fdf10560a5aff0aac261b50b6c2cb2251338c86267de8df192e20cee35
|
3 |
+
size 4999802720
|
model-00003-of-00004.safetensors
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:f0dcccfd909f49333a915617c85fdf9854704641a8e46926a433299ea5ee6189
|
3 |
+
size 4915916176
|