Downloads · 30 days
20
4% of all-time downloads
k2-think-v2-grpo-checkpoint-480
sambal/k2-think-v2-grpo-checkpoint-480
k2-think-v2-grpo-checkpoint-480 is a text generation model from sambal. Use it when you need the model to write or continue text. It is set up for transformers.
Merged Hugging Face checkpoint from global step 480 of K2-Think-V2 GRPO training.
All-time downloads
509
Public
Parameters
72.6B
290 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors290 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Sep 18, 2026
- Updated
- Sep 18, 2026
- SHA
- 036f6d10
Try a prompt
Model card
From the Hugging Face model README
K2-Think-V2 GRPO — checkpoint 480
Merged Hugging Face checkpoint from global step 480 of K2-Think-V2 GRPO training.
- Architecture:
LlamaForCausalLM - Weight precision: FP32 (
float32), preserved from the merged checkpoint - Format: full model weights, split across 62 safetensors shards (not a LoRA adapter)
- Includes the checkpoint's original configuration, tokenizer, and chat template
The checkpoint is uploaded without quantization or changes to its weights or tokenizer.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Sep 18, 2026
- Updated
- Sep 18, 2026