zai-org/GLM-4.7
Text Generation
•
358B
•
Updated
•
31.2k
•
•
1.4k
andthattoo
andthattoo
AI & ML interests
RL, Inference, Evolutionary Compute
Recent Activity
liked
a model
10 days ago
zai-org/GLM-4.7
liked
a model
21 days ago
nvidia/gpt-oss-120b-Eagle3-throughput
Organizations
liked
a
model
10 days ago
upvoted
an
article
21 days ago
Article
Introducing Pivotal Token Search (PTS): Targeting Critical Decision Points in LLM Training
•
11
liked
2
models
21 days ago
liked
a
model
22 days ago
liked
a
model
29 days ago
liked
a
model
about 1 month ago
liked
3
models
2 months ago
upvoted
an
article
2 months ago
Article
Building the Open Agent Ecosystem Together: Introducing OpenEnv
- +8
•
138
liked
a
model
2 months ago
liked
2
models
3 months ago
How is it trained?
2
#5 opened 3 months ago
by
l-lyubenov
published
an
article
3 months ago
Article
mem-agent: Equipping LLM Agents with Memory Using RL
•
32
liked
a
dataset
3 months ago
liked
a
model
4 months ago
Adding `transformers` as the library tag
#4 opened 4 months ago
by
ariG23498
commented on
mem-agent: Persistent, Human Readable Memory Agent Trained with Online RL
4 months ago
I would suggest running 4-bit with 8GB RAM on M1, and bf16 with M4 Pro 64GB. Interestingly, 4-bit is surprisingly good on our benchmark. We are considering larger models since they can handle more complex n-hop queries with less hallucination (14B and 30B MoE Qwen). We'll also be releasing the training and data-generation code next week