Hugging Face's logo

trl-internal-testing
/
tiny-Qwen3MoeForCausalLM

Text Generation
Transformers
Safetensors
qwen3_moe
trl
conversational
Model card Files
xet
Community
qgallouedec HF Staff commited on
Commit
96ec1eb
·
verified ·
1 Parent(s): 2a6bb72

Upload Qwen3MoeForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +2 -2
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -5,6 +5,7 @@
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "decoder_sparse_step": 1,
 
8
  "hidden_act": "silu",
9
  "hidden_size": 8,
10
  "initializer_range": 0.02,
@@ -26,8 +27,7 @@
26
  "router_aux_loss_coef": 0.001,
27
  "sliding_window": null,
28
  "tie_word_embeddings": false,
29
- "torch_dtype": "float32",
30
- "transformers_version": "4.55.0.dev0",
31
  "use_cache": true,
32
  "use_sliding_window": false,
33
  "vocab_size": 151669
 
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "decoder_sparse_step": 1,
8
+ "dtype": "float32",
9
  "hidden_act": "silu",
10
  "hidden_size": 8,
11
  "initializer_range": 0.02,
 
27
  "router_aux_loss_coef": 0.001,
28
  "sliding_window": null,
29
  "tie_word_embeddings": false,
30
+ "transformers_version": "4.57.0.dev0",
 
31
  "use_cache": true,
32
  "use_sliding_window": false,
33
  "vocab_size": 151669
generation_config.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
  "_from_model_config": true,
3
- "transformers_version": "4.55.0.dev0"
4
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "transformers_version": "4.57.0.dev0"
4
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42f53cb02c1c8752d607be27d59500c0d0f075024878392cadcd87f7f35e4bdf
3
  size 10303536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72c9fcc77ba2cc57ece3e2e4d524b88d0cd4d10d6cb66f3fe469eb1b0ca04f5
3
  size 10303536