wanyuhe499
commited on
Commit
•
d102a1c
1
Parent(s):
cd748f3
End of training
Browse files
README.md
CHANGED
@@ -27,17 +27,17 @@ print(output["generated_text"])
|
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yvonnehe499-northeastern-university/huggingface/runs/
|
31 |
|
32 |
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
|
33 |
|
34 |
### Framework versions
|
35 |
|
36 |
-
- TRL: 0.
|
37 |
-
- Transformers: 4.
|
38 |
- Pytorch: 2.5.1+cu121
|
39 |
- Datasets: 3.1.0
|
40 |
-
- Tokenizers: 0.
|
41 |
|
42 |
## Citations
|
43 |
|
|
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yvonnehe499-northeastern-university/huggingface/runs/8mbpb626)
|
31 |
|
32 |
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
|
33 |
|
34 |
### Framework versions
|
35 |
|
36 |
+
- TRL: 0.12.1
|
37 |
+
- Transformers: 4.46.3
|
38 |
- Pytorch: 2.5.1+cu121
|
39 |
- Datasets: 3.1.0
|
40 |
+
- Tokenizers: 0.20.3
|
41 |
|
42 |
## Citations
|
43 |
|
adapter_config.json
CHANGED
@@ -20,8 +20,8 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6824216
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a896621a21eb9b27db486ea609e28c7968ab287d04930bfed20d951be6cfc49
|
3 |
size 6824216
|
runs/Dec06_04-43-54_83b1d48b5f83/events.out.tfevents.1733460235.83b1d48b5f83.1849.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e100ce4df6923c4fdb5e532771b2b96ffa2553de4d7bcf4534f8bf9bb5c54895
|
3 |
+
size 6448
|
tokenizer_config.json
CHANGED
@@ -2052,7 +2052,6 @@
|
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|end_of_text|>",
|
2055 |
-
"extra_special_tokens": {},
|
2056 |
"model_input_names": [
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|
|
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|end_of_text|>",
|
|
|
2055 |
"model_input_names": [
|
2056 |
"input_ids",
|
2057 |
"attention_mask"
|
training_args.bin
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 sha256:34a23d8d192ab938a92f27c4916e0ce8e9f392d36a021b5d94063fd39e045159
|
3 |
+
size 6072
|