Instructions to use Ba2han/a3b-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/a3b-test with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Ba2han/a3b-test", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use Ba2han/a3b-test with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/a3b-test to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/a3b-test to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ba2han/a3b-test to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Ba2han/a3b-test", max_seq_length=2048, )
Training in progress, step 636
Browse files- README.md +3 -3
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -4,9 +4,9 @@ library_name: transformers
|
|
| 4 |
model_name: a3b-test
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- sft
|
| 8 |
-
- trl
|
| 9 |
- unsloth
|
|
|
|
|
|
|
| 10 |
licence: license
|
| 11 |
---
|
| 12 |
|
|
@@ -28,7 +28,7 @@ print(output["generated_text"])
|
|
| 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/batuhan409/huggingface/runs/
|
| 32 |
|
| 33 |
|
| 34 |
This model was trained with SFT.
|
|
|
|
| 4 |
model_name: a3b-test
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
- unsloth
|
| 8 |
+
- trl
|
| 9 |
+
- sft
|
| 10 |
licence: license
|
| 11 |
---
|
| 12 |
|
|
|
|
| 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/batuhan409/huggingface/runs/kd74xt5m)
|
| 32 |
|
| 33 |
|
| 34 |
This model was trained with SFT.
|
adapter_config.json
CHANGED
|
@@ -28,13 +28,13 @@
|
|
| 28 |
"rank_pattern": {},
|
| 29 |
"revision": null,
|
| 30 |
"target_modules": [
|
| 31 |
-
"up_proj",
|
| 32 |
-
"k_proj",
|
| 33 |
-
"gate_proj",
|
| 34 |
"o_proj",
|
|
|
|
|
|
|
| 35 |
"v_proj",
|
| 36 |
"down_proj",
|
| 37 |
-
"
|
|
|
|
| 38 |
],
|
| 39 |
"target_parameters": null,
|
| 40 |
"task_type": null,
|
|
|
|
| 28 |
"rank_pattern": {},
|
| 29 |
"revision": null,
|
| 30 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 31 |
"o_proj",
|
| 32 |
+
"up_proj",
|
| 33 |
+
"q_proj",
|
| 34 |
"v_proj",
|
| 35 |
"down_proj",
|
| 36 |
+
"k_proj",
|
| 37 |
+
"gate_proj"
|
| 38 |
],
|
| 39 |
"target_parameters": null,
|
| 40 |
"task_type": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6756146760
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8400246a78bbbfc939966b99a2746d84c4b74b8560c2fe3aa7aa00df7ed4ea8c
|
| 3 |
size 6756146760
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6161
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:312038d83e2234047a454ae5f6d74cab6a9f55520f23bbc085e1f4a61f960260
|
| 3 |
size 6161
|