ZhangShenao
commited on
Commit
•
7916af6
1
Parent(s):
dcd212e
End of training
Browse files- README.md +8 -1
- config.json +1 -1
README.md
CHANGED
@@ -2,9 +2,16 @@
|
|
2 |
license: other
|
3 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: 0.0_llama_nodpo_3iters_bs128_531lr_iter_1
|
10 |
results: []
|
@@ -15,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# 0.0_llama_nodpo_3iters_bs128_531lr_iter_1
|
17 |
|
18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
2 |
license: other
|
3 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
- trl
|
7 |
- dpo
|
8 |
- generated_from_trainer
|
9 |
+
- trl
|
10 |
+
- dpo
|
11 |
+
- generated_from_trainer
|
12 |
+
datasets:
|
13 |
+
- updated
|
14 |
+
- original
|
15 |
model-index:
|
16 |
- name: 0.0_llama_nodpo_3iters_bs128_531lr_iter_1
|
17 |
results: []
|
|
|
22 |
|
23 |
# 0.0_llama_nodpo_3iters_bs128_531lr_iter_1
|
24 |
|
25 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the updated and the original datasets.
|
26 |
|
27 |
## Model description
|
28 |
|
config.json
CHANGED
@@ -23,6 +23,6 @@
|
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
"transformers_version": "4.40.2",
|
26 |
-
"use_cache":
|
27 |
"vocab_size": 128256
|
28 |
}
|
|
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
"transformers_version": "4.40.2",
|
26 |
+
"use_cache": true,
|
27 |
"vocab_size": 128256
|
28 |
}
|