Translation
Transformers
Safetensors
Turkish
English
lfm2_moe
text-generation
Generated from Trainer
sft
trl
unsloth
custom_code
Instructions to use Ba2han/Karga_EN-TR-8B-A1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/Karga_EN-TR-8B-A1B with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="Ba2han/Karga_EN-TR-8B-A1B", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/Karga_EN-TR-8B-A1B", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Ba2han/Karga_EN-TR-8B-A1B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Update config.json
Browse files- config.json +0 -1
config.json
CHANGED
|
@@ -51,7 +51,6 @@
|
|
| 51 |
"num_hidden_layers": 24,
|
| 52 |
"num_key_value_heads": 8,
|
| 53 |
"pad_token_id": 0,
|
| 54 |
-
"output_router_logits": true,
|
| 55 |
"rope_theta": 1000000.0,
|
| 56 |
"routed_scaling_factor": 1.0,
|
| 57 |
"transformers_version": "4.57.0.dev0",
|
|
|
|
| 51 |
"num_hidden_layers": 24,
|
| 52 |
"num_key_value_heads": 8,
|
| 53 |
"pad_token_id": 0,
|
|
|
|
| 54 |
"rope_theta": 1000000.0,
|
| 55 |
"routed_scaling_factor": 1.0,
|
| 56 |
"transformers_version": "4.57.0.dev0",
|