JameSand/stampede3-qwen3-4b-base-adam-1e-6-global_step_100
4B • Updated
Zhizhou Sha
JameSand
AI & ML interests
None yet
Recent Activity
commented on
a paper
28 days ago
MCP-AgentBench: Evaluating Real-World Language Agent Performance with
MCP-Mediated Tools commented on
a paper
29 days ago
PaSS: Parallel Speculative Sampling Organizations
JameSand/llama-adamw-lr1e-6-20260110_015014-global_step_200
4B • Updated
JameSand/llama-sgd-lr1e-2-20260110_020449-global_step_200
4B • Updated
JameSand/llama-muon-muonlr1e-4-spectral_norm-muonadamlr1e-6-20260110_005142-global_step_200
4B • Updated
• 1
JameSand/Llama-3.2-3B-Instruct-muon-2e-2-muonadamlr1e-6-muonadjustlrNone-iter_0000200
Text Generation • 3B • Updated
JameSand/Llama-3.2-3B-Instruct-muon-2e-2-muonadamlr1e-6-muonadjustlrrms_norm-iter_0000200
Text Generation • 3B • Updated
JameSand/Llama-BF16-math-step200
4B • Updated
JameSand/Llama-FP16-math-step200
4B • Updated
JameSand/Llama-FP32-math-step200
4B • Updated
JameSand/qwen2.5_0.5b_pissa32_lr3e_5_step100_merged
0.5B • Updated
JameSand/qwen2.5_0.5b_pissa32_lr3e_5_step100_base_and_lora_adapter
0.6B • Updated
JameSand/qwen2.5_0.5b_lora32_lr3e_5_step100_merged
0.5B • Updated
JameSand/qwen2.5_0.5b_lora32_lr3e_5_step100_base_and_lora_adapter
0.6B • Updated
• 2