feihu.hf
commited on
Commit
•
46d2e43
1
Parent(s):
a522f73
update weights
Browse files- config.json +1 -1
- model-00001-of-00005.safetensors +2 -2
- model-00002-of-00005.safetensors +2 -2
- model-00003-of-00005.safetensors +2 -2
- model-00004-of-00005.safetensors +2 -2
- model-00005-of-00005.safetensors +2 -2
- model.safetensors.index.json +52 -52
config.json
CHANGED
@@ -8,7 +8,7 @@
|
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 5120,
|
10 |
"initializer_range": 0.02,
|
11 |
-
"intermediate_size":
|
12 |
"max_position_embeddings": 32768,
|
13 |
"max_window_layers": 35,
|
14 |
"model_type": "qwen2",
|
|
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 5120,
|
10 |
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 27648,
|
12 |
"max_position_embeddings": 32768,
|
13 |
"max_window_layers": 35,
|
14 |
"model_type": "qwen2",
|
model-00001-of-00005.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4de668333474d7a285deaa6bae2f7e5efd06738f5ba1bbd602d83d4213aa2e4
|
3 |
+
size 3947080608
|
model-00002-of-00005.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ada2b0935d0e40994796e48f1a404a4d60493d2fb7ba146dbabb1cd52ea63b3f
|
3 |
+
size 3985864968
|
model-00003-of-00005.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e996d2678b01df627a148d7dace3ed9e04f8a195d3bb337cdf835c8ae35a3c3f
|
3 |
+
size 3953094512
|
model-00004-of-00005.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8e4959dd115c50c563b570f61fb1adea49d502873913074ec3ef0dc77ca6eee
|
3 |
+
size 3985910056
|
model-00005-of-00005.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f548b49f2f5af13fb5bf722c1b871b7032b5bfe3bdc7ca006b941ac055907600
|
3 |
+
size 3480450840
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00005-of-00005.safetensors",
|
@@ -672,11 +672,11 @@
|
|
672 |
"model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors",
|
673 |
"model.layers.24.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
|
674 |
"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
675 |
-
"model.layers.25.mlp.down_proj.bias": "model-
|
676 |
-
"model.layers.25.mlp.down_proj.g_idx": "model-
|
677 |
-
"model.layers.25.mlp.down_proj.qweight": "model-
|
678 |
-
"model.layers.25.mlp.down_proj.qzeros": "model-
|
679 |
-
"model.layers.25.mlp.down_proj.scales": "model-
|
680 |
"model.layers.25.mlp.gate_proj.bias": "model-00003-of-00005.safetensors",
|
681 |
"model.layers.25.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors",
|
682 |
"model.layers.25.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors",
|
@@ -1300,7 +1300,7 @@
|
|
1300 |
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors",
|
1301 |
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors",
|
1302 |
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
|
1303 |
-
"model.layers.40.input_layernorm.weight": "model-
|
1304 |
"model.layers.40.mlp.down_proj.bias": "model-00003-of-00005.safetensors",
|
1305 |
"model.layers.40.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
1306 |
"model.layers.40.mlp.down_proj.qweight": "model-00003-of-00005.safetensors",
|
@@ -1311,12 +1311,12 @@
|
|
1311 |
"model.layers.40.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors",
|
1312 |
"model.layers.40.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors",
|
1313 |
"model.layers.40.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
|
1314 |
-
"model.layers.40.mlp.up_proj.bias": "model-
|
1315 |
-
"model.layers.40.mlp.up_proj.g_idx": "model-
|
1316 |
-
"model.layers.40.mlp.up_proj.qweight": "model-
|
1317 |
-
"model.layers.40.mlp.up_proj.qzeros": "model-
|
1318 |
-
"model.layers.40.mlp.up_proj.scales": "model-
|
1319 |
-
"model.layers.40.post_attention_layernorm.weight": "model-
|
1320 |
"model.layers.40.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
1321 |
"model.layers.40.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
1322 |
"model.layers.40.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors",
|
@@ -1354,26 +1354,26 @@
|
|
1354 |
"model.layers.41.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
1355 |
"model.layers.41.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
|
1356 |
"model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
1357 |
-
"model.layers.41.self_attn.k_proj.bias": "model-
|
1358 |
-
"model.layers.41.self_attn.k_proj.g_idx": "model-
|
1359 |
-
"model.layers.41.self_attn.k_proj.qweight": "model-
|
1360 |
-
"model.layers.41.self_attn.k_proj.qzeros": "model-
|
1361 |
-
"model.layers.41.self_attn.k_proj.scales": "model-
|
1362 |
-
"model.layers.41.self_attn.o_proj.bias": "model-
|
1363 |
-
"model.layers.41.self_attn.o_proj.g_idx": "model-
|
1364 |
-
"model.layers.41.self_attn.o_proj.qweight": "model-
|
1365 |
-
"model.layers.41.self_attn.o_proj.qzeros": "model-
|
1366 |
-
"model.layers.41.self_attn.o_proj.scales": "model-
|
1367 |
-
"model.layers.41.self_attn.q_proj.bias": "model-
|
1368 |
-
"model.layers.41.self_attn.q_proj.g_idx": "model-
|
1369 |
-
"model.layers.41.self_attn.q_proj.qweight": "model-
|
1370 |
-
"model.layers.41.self_attn.q_proj.qzeros": "model-
|
1371 |
-
"model.layers.41.self_attn.q_proj.scales": "model-
|
1372 |
-
"model.layers.41.self_attn.v_proj.bias": "model-
|
1373 |
-
"model.layers.41.self_attn.v_proj.g_idx": "model-
|
1374 |
-
"model.layers.41.self_attn.v_proj.qweight": "model-
|
1375 |
-
"model.layers.41.self_attn.v_proj.qzeros": "model-
|
1376 |
-
"model.layers.41.self_attn.v_proj.scales": "model-
|
1377 |
"model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
1378 |
"model.layers.42.mlp.down_proj.bias": "model-00004-of-00005.safetensors",
|
1379 |
"model.layers.42.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors",
|
@@ -1929,23 +1929,23 @@
|
|
1929 |
"model.layers.55.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors",
|
1930 |
"model.layers.55.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors",
|
1931 |
"model.layers.55.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
|
1932 |
-
"model.layers.56.input_layernorm.weight": "model-
|
1933 |
"model.layers.56.mlp.down_proj.bias": "model-00004-of-00005.safetensors",
|
1934 |
"model.layers.56.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors",
|
1935 |
"model.layers.56.mlp.down_proj.qweight": "model-00004-of-00005.safetensors",
|
1936 |
"model.layers.56.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors",
|
1937 |
"model.layers.56.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
|
1938 |
-
"model.layers.56.mlp.gate_proj.bias": "model-
|
1939 |
-
"model.layers.56.mlp.gate_proj.g_idx": "model-
|
1940 |
-
"model.layers.56.mlp.gate_proj.qweight": "model-
|
1941 |
-
"model.layers.56.mlp.gate_proj.qzeros": "model-
|
1942 |
-
"model.layers.56.mlp.gate_proj.scales": "model-
|
1943 |
-
"model.layers.56.mlp.up_proj.bias": "model-
|
1944 |
-
"model.layers.56.mlp.up_proj.g_idx": "model-
|
1945 |
-
"model.layers.56.mlp.up_proj.qweight": "model-
|
1946 |
-
"model.layers.56.mlp.up_proj.qzeros": "model-
|
1947 |
-
"model.layers.56.mlp.up_proj.scales": "model-
|
1948 |
-
"model.layers.56.post_attention_layernorm.weight": "model-
|
1949 |
"model.layers.56.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
1950 |
"model.layers.56.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
1951 |
"model.layers.56.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors",
|
@@ -1983,11 +1983,11 @@
|
|
1983 |
"model.layers.57.mlp.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
1984 |
"model.layers.57.mlp.up_proj.scales": "model-00005-of-00005.safetensors",
|
1985 |
"model.layers.57.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
1986 |
-
"model.layers.57.self_attn.k_proj.bias": "model-
|
1987 |
-
"model.layers.57.self_attn.k_proj.g_idx": "model-
|
1988 |
-
"model.layers.57.self_attn.k_proj.qweight": "model-
|
1989 |
-
"model.layers.57.self_attn.k_proj.qzeros": "model-
|
1990 |
-
"model.layers.57.self_attn.k_proj.scales": "model-
|
1991 |
"model.layers.57.self_attn.o_proj.bias": "model-00005-of-00005.safetensors",
|
1992 |
"model.layers.57.self_attn.o_proj.g_idx": "model-00005-of-00005.safetensors",
|
1993 |
"model.layers.57.self_attn.o_proj.qweight": "model-00005-of-00005.safetensors",
|
@@ -2344,8 +2344,8 @@
|
|
2344 |
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00005.safetensors",
|
2345 |
"model.layers.9.mlp.gate_proj.bias": "model-00002-of-00005.safetensors",
|
2346 |
"model.layers.9.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors",
|
2347 |
-
"model.layers.9.mlp.gate_proj.qweight": "model-
|
2348 |
-
"model.layers.9.mlp.gate_proj.qzeros": "model-
|
2349 |
"model.layers.9.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
|
2350 |
"model.layers.9.mlp.up_proj.bias": "model-00002-of-00005.safetensors",
|
2351 |
"model.layers.9.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 19352135680
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00005-of-00005.safetensors",
|
|
|
672 |
"model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00005.safetensors",
|
673 |
"model.layers.24.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
|
674 |
"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
675 |
+
"model.layers.25.mlp.down_proj.bias": "model-00003-of-00005.safetensors",
|
676 |
+
"model.layers.25.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
677 |
+
"model.layers.25.mlp.down_proj.qweight": "model-00003-of-00005.safetensors",
|
678 |
+
"model.layers.25.mlp.down_proj.qzeros": "model-00003-of-00005.safetensors",
|
679 |
+
"model.layers.25.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
|
680 |
"model.layers.25.mlp.gate_proj.bias": "model-00003-of-00005.safetensors",
|
681 |
"model.layers.25.mlp.gate_proj.g_idx": "model-00003-of-00005.safetensors",
|
682 |
"model.layers.25.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors",
|
|
|
1300 |
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00005.safetensors",
|
1301 |
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00005.safetensors",
|
1302 |
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
|
1303 |
+
"model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
1304 |
"model.layers.40.mlp.down_proj.bias": "model-00003-of-00005.safetensors",
|
1305 |
"model.layers.40.mlp.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
1306 |
"model.layers.40.mlp.down_proj.qweight": "model-00003-of-00005.safetensors",
|
|
|
1311 |
"model.layers.40.mlp.gate_proj.qweight": "model-00003-of-00005.safetensors",
|
1312 |
"model.layers.40.mlp.gate_proj.qzeros": "model-00003-of-00005.safetensors",
|
1313 |
"model.layers.40.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
|
1314 |
+
"model.layers.40.mlp.up_proj.bias": "model-00004-of-00005.safetensors",
|
1315 |
+
"model.layers.40.mlp.up_proj.g_idx": "model-00004-of-00005.safetensors",
|
1316 |
+
"model.layers.40.mlp.up_proj.qweight": "model-00004-of-00005.safetensors",
|
1317 |
+
"model.layers.40.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
1318 |
+
"model.layers.40.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
|
1319 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
1320 |
"model.layers.40.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
1321 |
"model.layers.40.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
1322 |
"model.layers.40.self_attn.k_proj.qweight": "model-00003-of-00005.safetensors",
|
|
|
1354 |
"model.layers.41.mlp.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
1355 |
"model.layers.41.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
|
1356 |
"model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
1357 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
1358 |
+
"model.layers.41.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
1359 |
+
"model.layers.41.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors",
|
1360 |
+
"model.layers.41.self_attn.k_proj.qzeros": "model-00004-of-00005.safetensors",
|
1361 |
+
"model.layers.41.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
|
1362 |
+
"model.layers.41.self_attn.o_proj.bias": "model-00004-of-00005.safetensors",
|
1363 |
+
"model.layers.41.self_attn.o_proj.g_idx": "model-00004-of-00005.safetensors",
|
1364 |
+
"model.layers.41.self_attn.o_proj.qweight": "model-00004-of-00005.safetensors",
|
1365 |
+
"model.layers.41.self_attn.o_proj.qzeros": "model-00004-of-00005.safetensors",
|
1366 |
+
"model.layers.41.self_attn.o_proj.scales": "model-00004-of-00005.safetensors",
|
1367 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
1368 |
+
"model.layers.41.self_attn.q_proj.g_idx": "model-00004-of-00005.safetensors",
|
1369 |
+
"model.layers.41.self_attn.q_proj.qweight": "model-00004-of-00005.safetensors",
|
1370 |
+
"model.layers.41.self_attn.q_proj.qzeros": "model-00004-of-00005.safetensors",
|
1371 |
+
"model.layers.41.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
|
1372 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
1373 |
+
"model.layers.41.self_attn.v_proj.g_idx": "model-00004-of-00005.safetensors",
|
1374 |
+
"model.layers.41.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors",
|
1375 |
+
"model.layers.41.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors",
|
1376 |
+
"model.layers.41.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
|
1377 |
"model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
1378 |
"model.layers.42.mlp.down_proj.bias": "model-00004-of-00005.safetensors",
|
1379 |
"model.layers.42.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
1929 |
"model.layers.55.self_attn.v_proj.qweight": "model-00004-of-00005.safetensors",
|
1930 |
"model.layers.55.self_attn.v_proj.qzeros": "model-00004-of-00005.safetensors",
|
1931 |
"model.layers.55.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
|
1932 |
+
"model.layers.56.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
1933 |
"model.layers.56.mlp.down_proj.bias": "model-00004-of-00005.safetensors",
|
1934 |
"model.layers.56.mlp.down_proj.g_idx": "model-00004-of-00005.safetensors",
|
1935 |
"model.layers.56.mlp.down_proj.qweight": "model-00004-of-00005.safetensors",
|
1936 |
"model.layers.56.mlp.down_proj.qzeros": "model-00004-of-00005.safetensors",
|
1937 |
"model.layers.56.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
|
1938 |
+
"model.layers.56.mlp.gate_proj.bias": "model-00005-of-00005.safetensors",
|
1939 |
+
"model.layers.56.mlp.gate_proj.g_idx": "model-00005-of-00005.safetensors",
|
1940 |
+
"model.layers.56.mlp.gate_proj.qweight": "model-00005-of-00005.safetensors",
|
1941 |
+
"model.layers.56.mlp.gate_proj.qzeros": "model-00005-of-00005.safetensors",
|
1942 |
+
"model.layers.56.mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
|
1943 |
+
"model.layers.56.mlp.up_proj.bias": "model-00005-of-00005.safetensors",
|
1944 |
+
"model.layers.56.mlp.up_proj.g_idx": "model-00005-of-00005.safetensors",
|
1945 |
+
"model.layers.56.mlp.up_proj.qweight": "model-00005-of-00005.safetensors",
|
1946 |
+
"model.layers.56.mlp.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
1947 |
+
"model.layers.56.mlp.up_proj.scales": "model-00005-of-00005.safetensors",
|
1948 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
1949 |
"model.layers.56.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
1950 |
"model.layers.56.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
1951 |
"model.layers.56.self_attn.k_proj.qweight": "model-00004-of-00005.safetensors",
|
|
|
1983 |
"model.layers.57.mlp.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
1984 |
"model.layers.57.mlp.up_proj.scales": "model-00005-of-00005.safetensors",
|
1985 |
"model.layers.57.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
1986 |
+
"model.layers.57.self_attn.k_proj.bias": "model-00005-of-00005.safetensors",
|
1987 |
+
"model.layers.57.self_attn.k_proj.g_idx": "model-00005-of-00005.safetensors",
|
1988 |
+
"model.layers.57.self_attn.k_proj.qweight": "model-00005-of-00005.safetensors",
|
1989 |
+
"model.layers.57.self_attn.k_proj.qzeros": "model-00005-of-00005.safetensors",
|
1990 |
+
"model.layers.57.self_attn.k_proj.scales": "model-00005-of-00005.safetensors",
|
1991 |
"model.layers.57.self_attn.o_proj.bias": "model-00005-of-00005.safetensors",
|
1992 |
"model.layers.57.self_attn.o_proj.g_idx": "model-00005-of-00005.safetensors",
|
1993 |
"model.layers.57.self_attn.o_proj.qweight": "model-00005-of-00005.safetensors",
|
|
|
2344 |
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00005.safetensors",
|
2345 |
"model.layers.9.mlp.gate_proj.bias": "model-00002-of-00005.safetensors",
|
2346 |
"model.layers.9.mlp.gate_proj.g_idx": "model-00002-of-00005.safetensors",
|
2347 |
+
"model.layers.9.mlp.gate_proj.qweight": "model-00002-of-00005.safetensors",
|
2348 |
+
"model.layers.9.mlp.gate_proj.qzeros": "model-00002-of-00005.safetensors",
|
2349 |
"model.layers.9.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
|
2350 |
"model.layers.9.mlp.up_proj.bias": "model-00002-of-00005.safetensors",
|
2351 |
"model.layers.9.mlp.up_proj.g_idx": "model-00002-of-00005.safetensors",
|