Instructions to use formapproval/Sheared-LLaMA-2.7B-weblinx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use formapproval/Sheared-LLaMA-2.7B-weblinx with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("formapproval/Sheared-LLaMA-2.7B-weblinx", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use formapproval/Sheared-LLaMA-2.7B-weblinx 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 formapproval/Sheared-LLaMA-2.7B-weblinx 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 formapproval/Sheared-LLaMA-2.7B-weblinx to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for formapproval/Sheared-LLaMA-2.7B-weblinx to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="formapproval/Sheared-LLaMA-2.7B-weblinx", max_seq_length=2048, )
Model save
Browse files
README.md
CHANGED
|
@@ -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/kyoto-kaira/huggingface/runs/
|
| 32 |
|
| 33 |
|
| 34 |
This model was trained with SFT.
|
|
|
|
| 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/kyoto-kaira/huggingface/runs/wkp5d2bb)
|
| 32 |
|
| 33 |
|
| 34 |
This model was trained with SFT.
|
adapter_config.json
CHANGED
|
@@ -26,13 +26,13 @@
|
|
| 26 |
"rank_pattern": {},
|
| 27 |
"revision": null,
|
| 28 |
"target_modules": [
|
| 29 |
-
"gate_proj",
|
| 30 |
"k_proj",
|
| 31 |
-
"
|
| 32 |
"q_proj",
|
| 33 |
"v_proj",
|
| 34 |
"down_proj",
|
| 35 |
-
"o_proj"
|
|
|
|
| 36 |
],
|
| 37 |
"task_type": "CAUSAL_LM",
|
| 38 |
"use_dora": false,
|
|
|
|
| 26 |
"rank_pattern": {},
|
| 27 |
"revision": null,
|
| 28 |
"target_modules": [
|
|
|
|
| 29 |
"k_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
"q_proj",
|
| 32 |
"v_proj",
|
| 33 |
"down_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"up_proj"
|
| 36 |
],
|
| 37 |
"task_type": "CAUSAL_LM",
|
| 38 |
"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 200338096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16467acf008c2d39ffd00c9df39382098be0f57186481e0786510b9ee50a6c1d
|
| 3 |
size 200338096
|
runs/Dec26_03-08-03_29893ae5caf8/events.out.tfevents.1735182491.29893ae5caf8.1785.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e2d25d1f0330761642cec83192fc37e33e5a7f33a679f8fbfcad5c281a0b4c8
|
| 3 |
+
size 6849
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd6efe5817e16fb34ae74f9d2c7cbc1af47a91c98c963e2f72e0858122f53d82
|
| 3 |
size 5688
|