Instructions to use Alexis-Az/Math-Problem-LlaMA-3.2-1.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Alexis-Az/Math-Problem-LlaMA-3.2-1.7B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Alexis-Az/Math-Problem-LlaMA-3.2-1.7B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use Alexis-Az/Math-Problem-LlaMA-3.2-1.7B 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 Alexis-Az/Math-Problem-LlaMA-3.2-1.7B 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 Alexis-Az/Math-Problem-LlaMA-3.2-1.7B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Alexis-Az/Math-Problem-LlaMA-3.2-1.7B to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Alexis-Az/Math-Problem-LlaMA-3.2-1.7B", max_seq_length=2048, )
Update adapter_config.json
Browse filesautomapping changed from {
"base_model_class": "LlamaForCausalLM",
"parent_library": "transformers.models.llama.modeling_llama"
} to null for use with unsloths autoloader. Changed task type to "CAUSAL_LM" from null
- adapter_config.json +2 -5
adapter_config.json
CHANGED
|
@@ -1,9 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping":
|
| 4 |
-
"base_model_class": "LlamaForCausalLM",
|
| 5 |
-
"parent_library": "transformers.models.llama.modeling_llama"
|
| 6 |
-
},
|
| 7 |
"base_model_name_or_path": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
|
| 8 |
"bias": "none",
|
| 9 |
"fan_in_fan_out": false,
|
|
@@ -34,7 +31,7 @@
|
|
| 34 |
"v_proj",
|
| 35 |
"k_proj"
|
| 36 |
],
|
| 37 |
-
"task_type":
|
| 38 |
"use_dora": false,
|
| 39 |
"use_rslora": false
|
| 40 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
|
|
|
|
|
|
|
|
|
| 4 |
"base_model_name_or_path": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
|
|
|
| 31 |
"v_proj",
|
| 32 |
"k_proj"
|
| 33 |
],
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
| 36 |
"use_rslora": false
|
| 37 |
}
|