root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

convert.py : export rope freq_base when converting CodeLlama from an HF model (#2773)

Browse Source
This commit is contained in:
slaren 2023-08-25 14:08:53 +02:00 committed by GitHub
parent 29674ab4e8
commit 12e2e33a97
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 18 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
convert.py
View File

@ -167,6 +167,7 @@ class Params:
n_head = config["num_attention_heads"] n_head = config["num_attention_heads"]
n_head_kv = config["num_key_value_heads"] if "num_key_value_heads" in config else n_head n_head_kv = config["num_key_value_heads"] if "num_key_value_heads" in config else n_head
f_norm_eps = config["rms_norm_eps"] f_norm_eps = config["rms_norm_eps"]
f_rope_freq_base = config["rope_theta"] if "rope_theta" in config else None
n_mult = Params.find_n_mult(n_ff, n_embd) n_mult = Params.find_n_mult(n_ff, n_embd)
@ -188,6 +189,7 @@ class Params:
n_head = n_head, n_head = n_head,
n_head_kv = n_head_kv, n_head_kv = n_head_kv,
f_norm_eps = f_norm_eps, f_norm_eps = f_norm_eps,
f_rope_freq_base = f_rope_freq_base,
) )
# LLaMA v2 70B params.json # LLaMA v2 70B params.json