423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-23 06:12:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update llamafy_internlm2.py

Browse Source 
Former-commit-id: c84a387c2c0e6ac5a33fd233bcfba4363eccb4cb
This commit is contained in:
hiyouga 2024-01-18 00:49:31 +08:00
parent 85a2e81dc2
commit 925b61ff99
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tests/llamafy_internlm2.py
View File

@ -49,8 +49,8 @@ def save_weight(
proj_size = value.size(0)
num_q_heads = internlm2_config_dict["num_attention_heads"]
num_kv_heads = internlm2_config_dict["num_key_value_heads"]
q_size = proj_size // (num_q_heads + num_kv_heads) * num_q_heads
kv_size = proj_size // (num_q_heads + num_kv_heads) * num_kv_heads
q_size = proj_size // (num_q_heads + 2 * num_kv_heads) * num_q_heads
kv_size = proj_size // (num_q_heads + 2 * num_kv_heads) * num_kv_heads
llama2_state_dict[key.replace("attention.wqkv", "self_attn.q_proj")] = value[:q_size, ...]
llama2_state_dict[key.replace("attention.wqkv", "self_attn.k_proj")] = value[q_size:q_size+kv_size, ...]
llama2_state_dict[key.replace("attention.wqkv", "self_attn.v_proj")] = value[q_size+kv_size:, ...]