Text Generation
Transformers
Safetensors
English
qwen3
mergekit
Merge
esper
esper-3
dmind
dmind-1-mini
cobalt
cobalt-2
grayline
valiant
valiant-labs
qwen
qwen-3
qwen-3-14b
14b
reasoning
web3
code
code-instruct
python
javascript
dev-ops
jenkins
terraform
scripting
powershell
azure
aws
gcp
cloud
problem-solving
architect
engineer
developer
creative
analytical
expert
rationality
math
math-reasoning
math-instruct
uncensored
unfiltered
amoral-ai
conversational
chat
instruct
text-generation-inference
| { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 17408, | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 40, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.3", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |