Upload CompressedLlamaForCausalLM
Browse files- config.json +3 -1
- model-00001-of-00003.safetensors +2 -2
- model-00002-of-00003.safetensors +2 -2
- model-00003-of-00003.safetensors +2 -2
- model.safetensors.index.json +6 -9
config.json
CHANGED
@@ -19,8 +19,10 @@
|
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_scaling": null,
|
21 |
"rope_theta": 10000.0,
|
22 |
-
"share_layers": "none",
|
23 |
"tie_word_embeddings": false,
|
|
|
|
|
|
|
24 |
"torch_dtype": "float32",
|
25 |
"transformers_version": "4.35.2",
|
26 |
"use_cache": true,
|
|
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_scaling": null,
|
21 |
"rope_theta": 10000.0,
|
|
|
22 |
"tie_word_embeddings": false,
|
23 |
+
"tied_layers": {
|
24 |
+
"1": 0
|
25 |
+
},
|
26 |
"torch_dtype": "float32",
|
27 |
"transformers_version": "4.35.2",
|
28 |
"use_cache": true,
|
model-00001-of-00003.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 sha256:410627979de4319c4623cd5dbc988483c182d26e893f6d230a6ef6134bd482a7
|
3 |
+
size 4923632128
|
model-00002-of-00003.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 sha256:2d81c6fa49d323e616f26b3a824a2f73049c2596008583b13a3d7a38115647a4
|
3 |
+
size 4956426376
|
model-00003-of-00003.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 sha256:2c138227dedead48e31613d734e633baf4096b895901d045ef51944dd19c2631
|
3 |
+
size 3494086776
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|
@@ -15,9 +15,6 @@
|
|
15 |
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
18 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
20 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
21 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
22 |
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
@@ -106,8 +103,8 @@
|
|
106 |
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
107 |
"model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
108 |
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
109 |
-
"model.layers.19.mlp.gate_proj.weight": "model-
|
110 |
-
"model.layers.19.mlp.up_proj.weight": "model-
|
111 |
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
112 |
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
113 |
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
@@ -232,11 +229,11 @@
|
|
232 |
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
233 |
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
234 |
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
235 |
-
"model.layers.9.mlp.gate_proj.weight": "model-
|
236 |
-
"model.layers.9.mlp.up_proj.weight": "model-
|
237 |
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
238 |
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
239 |
-
"model.layers.9.self_attn.o_proj.weight": "model-
|
240 |
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
241 |
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
242 |
"model.norm.weight": "model-00003-of-00003.safetensors"
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 13374118400
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|
|
|
15 |
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
|
|
|
|
|
|
18 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
19 |
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
20 |
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
|
|
103 |
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
104 |
"model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
105 |
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
106 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
108 |
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
109 |
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
110 |
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
229 |
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
230 |
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
231 |
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
232 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
233 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
234 |
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
235 |
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
236 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
237 |
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
238 |
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
239 |
"model.norm.weight": "model-00003-of-00003.safetensors"
|