Downloads · 30 days
29
5% of all-time downloads
k2-think-v2-grpo-checkpoint-320
sambal/k2-think-v2-grpo-checkpoint-320
k2-think-v2-grpo-checkpoint-320 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 320 of K2-Think-V2 GRPO training.
All-time downloads
580
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 19, 2026
- Updated
- Sep 19, 2026
- SHA
- 3b741805
Try a prompt
Model card
From the Hugging Face model README
K2-Think-V2 GRPO — checkpoint 320
Merged Hugging Face checkpoint from global step 320 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 19, 2026
- Updated
- Sep 19, 2026