Instructions to use SubashNeupane/lama3-8b-SOAP_Heidi_notes-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SubashNeupane/lama3-8b-SOAP_Heidi_notes-lora with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SubashNeupane/lama3-8b-SOAP_Heidi_notes-lora", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use SubashNeupane/lama3-8b-SOAP_Heidi_notes-lora 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 SubashNeupane/lama3-8b-SOAP_Heidi_notes-lora 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 SubashNeupane/lama3-8b-SOAP_Heidi_notes-lora to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for SubashNeupane/lama3-8b-SOAP_Heidi_notes-lora to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="SubashNeupane/lama3-8b-SOAP_Heidi_notes-lora", max_seq_length=2048, )
Upload config.json
#2
by ht557 - opened
- config.json +18 -0
config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": ["LLaMAForCausalLM"],
|
| 3 |
+
"model_type": "llama",
|
| 4 |
+
"vocab_size": 128000,
|
| 5 |
+
"hidden_size": 4096,
|
| 6 |
+
"num_hidden_layers": 32,
|
| 7 |
+
"num_attention_heads": 32,
|
| 8 |
+
"intermediate_size": 11008,
|
| 9 |
+
"max_position_embeddings": 2048,
|
| 10 |
+
"layer_norm_eps": 1e-5,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"rope_scaling": {
|
| 14 |
+
"type": "linear",
|
| 15 |
+
"factor": 1.1
|
| 16 |
+
},
|
| 17 |
+
"use_cache": true
|
| 18 |
+
}
|