|
import os |
|
import glob |
|
import json |
|
import shutil |
|
import safetensors |
|
from safetensors.torch import save_file |
|
|
|
def fix_gemma_merge(): |
|
|
|
print("Decapitating extra head...") |
|
|
|
unsorted_files = glob.glob("model-*-of-*.safetensors") |
|
files = sorted(unsorted_files) |
|
|
|
print(files) |
|
|
|
f_map = {} |
|
k_map = {} |
|
t_map = {} |
|
|
|
for f in files: |
|
st = safetensors.safe_open(f, framework="pt") |
|
f_map[f] = st |
|
k_map[f] = st.keys() |
|
for key in k_map[f]: |
|
t_map[key] = st.get_tensor(key) |
|
|
|
|
|
for f in f_map: |
|
print(f"file: {f}") |
|
print(f"keys: {k_map[f]}") |
|
print(f"associated tensors:") |
|
for k in k_map[f]: |
|
print(f"t_map[{k}].shape: {t_map[k].shape}") |
|
|
|
|
|
|
|
map_1 = {} |
|
map_2 = {} |
|
map_3 = {} |
|
map_4 = {} |
|
|
|
for w in w_map: |
|
print(f"{w} -> {w_map[w]}") |
|
|
|
if w_map[w] == "model-00001-of-00004.safetensors": |
|
map_1[w] = t_map[w] |
|
elif w_map[w] == "model-00002-of-00004.safetensors": |
|
map_2[w] = t_map[w] |
|
elif w_map[w] == "model-00003-of-00004.safetensors": |
|
map_3[w] = t_map[w] |
|
elif w_map[w] == "model-00004-of-00004.safetensors": |
|
map_4[w] = t_map[w] |
|
|
|
print("") |
|
print("") |
|
|
|
print("Resharding...") |
|
save_file(map_1, "1model-00001-of-00004.safetensors") |
|
save_file(map_2, "1model-00002-of-00004.safetensors") |
|
save_file(map_3, "1model-00003-of-00004.safetensors") |
|
save_file(map_4, "1model-00004-of-00004.safetensors") |
|
|
|
print("Moving old safetensors to old/") |
|
os.makedirs("old", exist_ok=True) |
|
shutil.move("model-00001-of-00005.safetensors", "old") |
|
shutil.move("model-00002-of-00005.safetensors", "old") |
|
shutil.move("model-00003-of-00005.safetensors", "old") |
|
shutil.move("model-00004-of-00005.safetensors", "old") |
|
shutil.move("model-00005-of-00005.safetensors", "old") |
|
shutil.move("model.safetensors.index.json", "old") |
|
|
|
with open("model.safetensors.index.json", "w") as of: |
|
json.dump(gemma_9b_safetensor_index, of) |
|
shutil.move("1model-00001-of-00004.safetensors", "model-00001-of-00004.safetensors") |
|
shutil.move("1model-00002-of-00004.safetensors", "model-00002-of-00004.safetensors") |
|
shutil.move("1model-00003-of-00004.safetensors", "model-00003-of-00004.safetensors") |
|
shutil.move("1model-00004-of-00004.safetensors", "model-00004-of-00004.safetensors") |
|
|
|
w_map = { |
|
"model.embed_tokens.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.norm.weight": "model-00004-of-00004.safetensors" |
|
} |
|
|
|
gemma_9b_safetensor_index = { |
|
"metadata": { |
|
"total_size": 18483411968 |
|
}, |
|
"weight_map": { |
|
"model.embed_tokens.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", |
|
"model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", |
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", |
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", |
|
"model.norm.weight": "model-00004-of-00004.safetensors" |
|
} |
|
} |
|
|
|
print(__name__) |
|
if __name__ == "__main__": |
|
fix_gemma_merge() |
|
|
