RohamKoohestani
commited on
Commit
•
ad1bf38
1
Parent(s):
141a2b8
Upload model
Browse files- README.md +3 -3
- adapter_config.json +6 -6
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model: bigcode/starcoder2-
|
3 |
library_name: transformers
|
4 |
model_name: finetune_starcoder2
|
5 |
tags:
|
@@ -11,7 +11,7 @@ licence: license
|
|
11 |
|
12 |
# Model Card for finetune_starcoder2
|
13 |
|
14 |
-
This model is a fine-tuned version of [bigcode/starcoder2-
|
15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
16 |
|
17 |
## Quick start
|
@@ -27,7 +27,7 @@ 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/roham-koohestani/huggingface/runs/
|
31 |
|
32 |
This model was trained with SFT.
|
33 |
|
|
|
1 |
---
|
2 |
+
base_model: bigcode/starcoder2-15b
|
3 |
library_name: transformers
|
4 |
model_name: finetune_starcoder2
|
5 |
tags:
|
|
|
11 |
|
12 |
# Model Card for finetune_starcoder2
|
13 |
|
14 |
+
This model is a fine-tuned version of [bigcode/starcoder2-15b](https://huggingface.co/bigcode/starcoder2-15b).
|
15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
16 |
|
17 |
## Quick start
|
|
|
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/roham-koohestani/huggingface/runs/3ryf9ebs)
|
31 |
|
32 |
This model was trained with SFT.
|
33 |
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "bigcode/starcoder2-
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -19,13 +19,13 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"gate_proj",
|
23 |
-
"down_proj",
|
24 |
-
"q_proj",
|
25 |
"k_proj",
|
26 |
-
"
|
|
|
27 |
"up_proj",
|
28 |
-
"
|
|
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "bigcode/starcoder2-15b",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
|
|
22 |
"k_proj",
|
23 |
+
"o_proj",
|
24 |
+
"q_proj",
|
25 |
"up_proj",
|
26 |
+
"v_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"down_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": 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 sha256:3396e5b09204b736c2df744616e762d4fadbfe22056cec3f2bfb4cffb32ebab8
|
3 |
+
size 48539256
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e5c1cc5abf22171287110ec5c0234d89ed2d8c24eb5f1ac9e449c91f84efbb7
|
3 |
size 5496
|