Text Generation
PEFT
Safetensors
English
qwen3
pathi-ai
pathi-labs
pathi-lite-instruct-1.7B
qwen
causal-language-model
conversational
instruction-tuning
lora
fine-tuned
Instructions to use pathilabs/Pathi-Lite-Instruct-1.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use pathilabs/Pathi-Lite-Instruct-1.7B with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Download config.json from pathilabs/Pathi-Lite-Instruct-1.7B: direct link, hf CLI and curl.
- Browser
- Download file 1.42 kB
-
https://huggingface.co/pathilabs/Pathi-Lite-Instruct-1.7B/resolve/main/config.json
- Command line
-
hf download hf://pathilabs/Pathi-Lite-Instruct-1.7B/config.json
-
curl -L -o config.json https://huggingface.co/pathilabs/Pathi-Lite-Instruct-1.7B/resolve/main/config.json
1.42 kB
| { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "float16", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 28, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 1000000, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.16.1", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |