Upload LlamaForCausalLM
Browse files- README.md +3 -3
- config.json +4 -5
- generation_config.json +3 -7
- model-00001-of-00004.safetensors +2 -2
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +2 -2
- model.safetensors.index.json +1 -1
README.md
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
license: apache-2.0
|
|
|
4 |
datasets:
|
5 |
- Trelis/orpo-dpo-mix-40k-SHORT
|
6 |
-
language:
|
7 |
-
- en
|
8 |
pipeline_tag: text-classification
|
9 |
---
|
10 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: apache-2.0
|
5 |
+
library_name: transformers
|
6 |
datasets:
|
7 |
- Trelis/orpo-dpo-mix-40k-SHORT
|
|
|
|
|
8 |
pipeline_tag: text-classification
|
9 |
---
|
10 |
|
config.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
-
"bos_token_id":
|
9 |
-
"eos_token_id":
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
@@ -17,7 +17,6 @@
|
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
"num_key_value_heads": 8,
|
20 |
-
"pad_token_id": 128257,
|
21 |
"pretraining_tp": 1,
|
22 |
"rms_norm_eps": 1e-05,
|
23 |
"rope_scaling": null,
|
@@ -26,5 +25,5 @@
|
|
26 |
"torch_dtype": "float16",
|
27 |
"transformers_version": "4.41.0",
|
28 |
"use_cache": true,
|
29 |
-
"vocab_size":
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/kaggle/input/llama-3/transformers/8b-hf/1",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128001,
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
|
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
"num_key_value_heads": 8,
|
|
|
20 |
"pretraining_tp": 1,
|
21 |
"rms_norm_eps": 1e-05,
|
22 |
"rope_scaling": null,
|
|
|
25 |
"torch_dtype": "float16",
|
26 |
"transformers_version": "4.41.0",
|
27 |
"use_cache": true,
|
28 |
+
"vocab_size": 128256
|
29 |
}
|
generation_config.json
CHANGED
@@ -1,10 +1,6 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"eos_token_id":
|
5 |
-
"max_length": 4096,
|
6 |
-
"pad_token_id": 128257,
|
7 |
-
"temperature": 0.6,
|
8 |
-
"top_p": 0.9,
|
9 |
"transformers_version": "4.41.0"
|
10 |
}
|
|
|
1 |
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 128000,
|
4 |
+
"eos_token_id": 128001,
|
|
|
|
|
|
|
|
|
5 |
"transformers_version": "4.41.0"
|
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:b6948f1132949c27c365b689f126fef076fe4182f553b8c0399639e0135241f4
|
3 |
+
size 4976698592
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802616
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:414dede41da3a92b825a85b6ee22119d538c20305258f5c6e724626793293179
|
3 |
size 4999802616
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a15f0b0b0857d4017400881f4241d51835ac6c0d622db305c026954141d11faa
|
3 |
size 4915916080
|
model-00004-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 sha256:350ac0df99121df394b7795107dbe8e4e1beb0ae066b6f8a89e9c504f6553dab
|
3 |
+
size 1168138808
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00004-of-00004.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 16060522496
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00004-of-00004.safetensors",
|