Views
No views yet
atrost/nanochat-d24-nested-k4-alpha01-sft/d24_nested_k4_alpha01_sft at step 000485.nestedk4{"attn_alpha_init_value": 1.0, "dec_alpha_init_value": 1.0, "ffn_alpha_init_value": 1.0, "n_embd": 1536, "n_head": 24, "n_kv_head": 24, "n_layer": 24, "nested_block_heads": 6, "sequence_len": 2048, "vocab_size": 32768, "window_pattern": "L"}1from nanochat.hf_utils import stage_hf_checkpoint
2
3stage_hf_checkpoint(
4 repo_id="atrost/nanochat-d24-nested-k4-alpha01-sft-k4",
5 path_in_repo="d24_nested_k4_alpha01_sft_k4",
6 model_tag="d24_nested_k4_alpha01_sft_k4",
7 step=485,
8 base_dir="/tmp/nanochat-eval",
9)NANOCHAT_BASE_DIR=/tmp/nanochat-eval python -m scripts.base_eval --model-tag d24_nested_k4_alpha01_sft_k4 --step 485