Instructions to use trl-internal-testing/tiny-Qwen3MoeForSequenceClassification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use trl-internal-testing/tiny-Qwen3MoeForSequenceClassification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="trl-internal-testing/tiny-Qwen3MoeForSequenceClassification")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-Qwen3MoeForSequenceClassification") model = AutoModelForSequenceClassification.from_pretrained("trl-internal-testing/tiny-Qwen3MoeForSequenceClassification", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload Qwen3MoeForSequenceClassification
Browse files- config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -26,7 +26,7 @@
|
|
| 26 |
"moe_intermediate_size": 768,
|
| 27 |
"norm_topk_prob": true,
|
| 28 |
"num_attention_heads": 4,
|
| 29 |
-
"num_experts":
|
| 30 |
"num_experts_per_tok": 8,
|
| 31 |
"num_hidden_layers": 2,
|
| 32 |
"num_key_value_heads": 4,
|
|
|
|
| 26 |
"moe_intermediate_size": 768,
|
| 27 |
"norm_topk_prob": true,
|
| 28 |
"num_attention_heads": 4,
|
| 29 |
+
"num_experts": 4,
|
| 30 |
"num_experts_per_tok": 8,
|
| 31 |
"num_hidden_layers": 2,
|
| 32 |
"num_key_value_heads": 4,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e41a17ad46be7b50b2ae4b8bade5146fdd95aef796f3ea3726cfac19abc91ee8
|
| 3 |
+
size 5589296
|