Text Generation
Transformers
Safetensors
English
gemma4
image-text-to-text
gemma
google
dense
transformer
31b
nvfp4
fp4
4-bit precision
quantized
modelopt
awq
awq-full
activation-aware
weight-quantization
uncensored
abliterated
unfiltered
refusal-removed
deckard
heretic
vision
multimodal
tool-calling
function-calling
reasoning
thinking
chat
instruct
agentic
coding
creative-writing
dgx-spark
blackwell
gb10
grace-blackwell
nvidia
gpu
arm64
aarch64
vllm
openai-api
openai-compatible
fp8-kv-cache
prefix-caching
chunked-prefill
sliding-window-attention
english
production-ready
speculative-decoding
eagle
conversational
8-bit precision
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 2, | |
| "eos_token_id": [ | |
| 1, | |
| 106 | |
| ], | |
| "pad_token_id": 0, | |
| "transformers_version": "5.5.3", | |
| "use_cache": true | |
| } | |