Andrea Tomassi
j3st3r666
·
AI & ML interests
None yet
Organizations
None yet
Great model. 3090 + vLLM sweet spot: 35+ token/sec @ 24k context
🔥 9
#3 opened 5 months ago
by
j3st3r666
q2ks version for 80B Thinking
#6 opened 7 months ago
by
j3st3r666
Tool calling issue: got "True" as a String instead of a valid JSON format such as true (the primitive, unquoted value)
3
#25 opened 8 months ago
by
j3st3r666