Text Generation
Transformers
Safetensors
starcoder2
conversational
text-generation-inference
Inference Endpoints
4-bit precision
awq
starchat2-15b-v0.1-AWQ / generation_config.json
stelterlab's picture
Initial version
349ad40
raw
history blame contribute delete
140 Bytes
{
"_from_model_config": true,
"bos_token_id": 50256,
"do_sample": true,
"eos_token_id": 50256,
"transformers_version": "4.40.1"
}