End of training
Browse files- README.md +3 -3
- adapter_config.json +6 -4
- adapter_model.safetensors +1 -1
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -28,7 +28,7 @@ print(output["generated_text"])
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
| 31 |
-
|
| 32 |
|
| 33 |
|
| 34 |
This model was trained with SFT.
|
|
@@ -37,8 +37,8 @@ This model was trained with SFT.
|
|
| 37 |
|
| 38 |
- TRL: 0.15.2
|
| 39 |
- Transformers: 4.51.3
|
| 40 |
-
- Pytorch: 2.
|
| 41 |
-
- Datasets: 3.5.
|
| 42 |
- Tokenizers: 0.21.1
|
| 43 |
|
| 44 |
## Citations
|
|
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
| 31 |
+
[<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/webstechh-tetsa/huggingface/runs/8t79tqby)
|
| 32 |
|
| 33 |
|
| 34 |
This model was trained with SFT.
|
|
|
|
| 37 |
|
| 38 |
- TRL: 0.15.2
|
| 39 |
- Transformers: 4.51.3
|
| 40 |
+
- Pytorch: 2.7.0
|
| 41 |
+
- Datasets: 3.5.1
|
| 42 |
- Tokenizers: 0.21.1
|
| 43 |
|
| 44 |
## Citations
|
adapter_config.json
CHANGED
|
@@ -3,6 +3,7 @@
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "defog/llama-3-sqlcoder-8b",
|
| 5 |
"bias": "none",
|
|
|
|
| 6 |
"eva_config": null,
|
| 7 |
"exclude_modules": null,
|
| 8 |
"fan_in_fan_out": false,
|
|
@@ -23,15 +24,16 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"k_proj",
|
| 27 |
-
"o_proj",
|
| 28 |
-
"q_proj",
|
| 29 |
"v_proj",
|
|
|
|
|
|
|
| 30 |
"gate_proj",
|
| 31 |
"up_proj",
|
| 32 |
-
"down_proj"
|
|
|
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 35 |
"use_dora": false,
|
| 36 |
"use_rslora": false
|
| 37 |
}
|
|
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "defog/llama-3-sqlcoder-8b",
|
| 5 |
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
"eva_config": null,
|
| 8 |
"exclude_modules": null,
|
| 9 |
"fan_in_fan_out": false,
|
|
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 27 |
"v_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
"gate_proj",
|
| 31 |
"up_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"k_proj"
|
| 34 |
],
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
"use_dora": false,
|
| 38 |
"use_rslora": false
|
| 39 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8af501ec4dcc60de2e50963034c89711c7552d28e17cd1d2d4a089eab141306
|
| 3 |
size 167832240
|
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:c700d8f656378dcbc04c6cc2fefddc11310ebf6bc0ff8d9313cf6dad59e50c79
|
| 3 |
+
size 6033
|