Upload LlamaForCausalLM
Browse files- config.json +2 -2
- pytorch_model-00001-of-00002.bin +2 -2
- pytorch_model-00002-of-00002.bin +2 -2
- pytorch_model.bin.index.json +4 -4
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
@@ -22,5 +22,5 @@
|
|
| 22 |
"torch_dtype": "float16",
|
| 23 |
"transformers_version": "4.34.0.dev0",
|
| 24 |
"use_cache": true,
|
| 25 |
-
"vocab_size":
|
| 26 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "codellama/CodeLlama-7b-hf",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 22 |
"torch_dtype": "float16",
|
| 23 |
"transformers_version": "4.34.0.dev0",
|
| 24 |
"use_cache": true,
|
| 25 |
+
"vocab_size": 32016
|
| 26 |
}
|
pytorch_model-00001-of-00002.bin
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 sha256:100f053e17a1f5ac4efaba5b58a5e7e17754dd80161464182d882dca41d09616
|
| 3 |
+
size 9976754202
|
pytorch_model-00002-of-00002.bin
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:bf47d24595f15830b9b655c2f590afd19e4b96402cbeac615f860f6db143418a
|
| 3 |
+
size 3500442883
|
pytorch_model.bin.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
|
@@ -149,11 +149,11 @@
|
|
| 149 |
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 150 |
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 151 |
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 152 |
-
"model.layers.23.input_layernorm.weight": "pytorch_model-
|
| 153 |
-
"model.layers.23.mlp.down_proj.weight": "pytorch_model-
|
| 154 |
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 155 |
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 156 |
-
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-
|
| 157 |
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 158 |
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 159 |
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 13477093376
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
|
|
|
| 149 |
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 150 |
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 151 |
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 154 |
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 155 |
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 157 |
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 158 |
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 159 |
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|