oz1115/phi3_adapter
Browse files- README.md +2 -3
- adapter_config.json +5 -5
- adapter_model.safetensors +2 -2
- training_args.bin +2 -2
README.md
CHANGED
@@ -14,7 +14,6 @@ model-index:
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/gsitm/Phi3-mini-ft-python-code/runs/4ipkuc1m)
|
18 |
# phi-3-mini-LoRA
|
19 |
|
20 |
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
|
@@ -53,8 +52,8 @@ The following hyperparameters were used during training:
|
|
53 |
|
54 |
### Framework versions
|
55 |
|
56 |
-
- PEFT 0.
|
57 |
-
- Transformers 4.
|
58 |
- Pytorch 2.3.1+cu121
|
59 |
- Datasets 2.20.0
|
60 |
- Tokenizers 0.19.1
|
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
|
|
17 |
# phi-3-mini-LoRA
|
18 |
|
19 |
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
|
|
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
+
- PEFT 0.12.0
|
56 |
+
- Transformers 4.44.0
|
57 |
- Pytorch 2.3.1+cu121
|
58 |
- Datasets 2.20.0
|
59 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
|
|
24 |
"gate_proj",
|
25 |
-
"o_proj",
|
26 |
-
"down_proj",
|
27 |
"up_proj",
|
28 |
-
"
|
29 |
-
"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj",
|
25 |
"gate_proj",
|
|
|
|
|
26 |
"up_proj",
|
27 |
+
"k_proj",
|
28 |
+
"down_proj",
|
29 |
+
"o_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb80643a545cfea1849c0bc41d053a65c91e54d29b0d113d0c19b2b36e577e77
|
3 |
+
size 35668592
|
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 sha256:2bd4a17bcfa6c52aa314915c6974375ef3da2d909e13b84844489a83eb99a22e
|
3 |
+
size 5432
|