Text Generation
PEFT
Safetensors
English
lora
qlora
sft
trl
text-to-sql
sql
conversational
Eval Results (legacy)
Instructions to use SASVAAI/GLM-4.7-Flash-sql-create-context with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SASVAAI/GLM-4.7-Flash-sql-create-context with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-4.7-Flash") model = PeftModel.from_pretrained(base_model, "SASVAAI/GLM-4.7-Flash-sql-create-context") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from SASVAAI/GLM-4.7-Flash-sql-create-context: direct link, hf CLI and curl.
- Browser
- Download file 335 Bytes
-
https://huggingface.co/SASVAAI/GLM-4.7-Flash-sql-create-context/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://SASVAAI/GLM-4.7-Flash-sql-create-context/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/SASVAAI/GLM-4.7-Flash-sql-create-context/resolve/main/tokenizer_config.json
335 Bytes
| { | |
| "backend": "tokenizers", | |
| "clean_up_tokenization_spaces": false, | |
| "do_lower_case": false, | |
| "eos_token": "<|endoftext|>", | |
| "is_local": false, | |
| "local_files_only": false, | |
| "model_max_length": 128000, | |
| "pad_token": "<|endoftext|>", | |
| "padding_side": "right", | |
| "remove_space": false, | |
| "tokenizer_class": "TokenizersBackend" | |
| } | |