Instructions to use shau1905/python_qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shau1905/python_qa with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shau1905/python_qa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use shau1905/python_qa 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 shau1905/python_qa 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 shau1905/python_qa to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for shau1905/python_qa to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="shau1905/python_qa", max_seq_length=2048, )
Update adapter_config.json
Browse files- adapter_config.json +6 -27
adapter_config.json
CHANGED
|
@@ -1,29 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": {
|
| 4 |
-
"base_model_class": "MistralForCausalLM",
|
| 5 |
-
"parent_library": "transformers.models.mistral.modeling_mistral",
|
| 6 |
-
"unsloth_fixed": true
|
| 7 |
-
},
|
| 8 |
"base_model_name_or_path": "unsloth/phi-3-mini-4k-instruct-bnb-4bit",
|
| 9 |
-
"bias": "none",
|
| 10 |
-
"fan_in_fan_out": false,
|
| 11 |
-
"inference_mode": true,
|
| 12 |
-
"init_lora_weights": true,
|
| 13 |
-
"layer_replication": null,
|
| 14 |
-
"layers_pattern": null,
|
| 15 |
-
"layers_to_transform": null,
|
| 16 |
-
"loftq_config": {},
|
| 17 |
-
"lora_alpha": 32,
|
| 18 |
-
"lora_dropout": 0.05,
|
| 19 |
-
"megatron_config": null,
|
| 20 |
-
"megatron_core": "megatron.core",
|
| 21 |
-
"modules_to_save": null,
|
| 22 |
"peft_type": "LORA",
|
| 23 |
-
"
|
| 24 |
"r": 16,
|
| 25 |
-
"
|
| 26 |
-
"
|
|
|
|
|
|
|
| 27 |
"target_modules": [
|
| 28 |
"k_proj",
|
| 29 |
"v_proj",
|
|
@@ -32,9 +15,5 @@
|
|
| 32 |
"q_proj",
|
| 33 |
"down_proj",
|
| 34 |
"up_proj"
|
| 35 |
-
]
|
| 36 |
-
"target_parameters": null,
|
| 37 |
-
"task_type": "CAUSAL_LM",
|
| 38 |
-
"use_dora": false,
|
| 39 |
-
"use_rslora": false
|
| 40 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"base_model_name_or_path": "unsloth/phi-3-mini-4k-instruct-bnb-4bit",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"peft_type": "LORA",
|
| 4 |
+
"task_type": "CAUSAL_LM",
|
| 5 |
"r": 16,
|
| 6 |
+
"lora_alpha": 32,
|
| 7 |
+
"lora_dropout": 0.05,
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"inference_mode": true,
|
| 10 |
"target_modules": [
|
| 11 |
"k_proj",
|
| 12 |
"v_proj",
|
|
|
|
| 15 |
"q_proj",
|
| 16 |
"down_proj",
|
| 17 |
"up_proj"
|
| 18 |
+
]
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|