natankatz commited on
Commit
11201eb
·
1 Parent(s): b7184de

Upload LlamaForCausalLM

Browse files
config.json CHANGED
@@ -22,5 +22,5 @@
22
  "torch_dtype": "float16",
23
  "transformers_version": "4.34.0.dev0",
24
  "use_cache": true,
25
- "vocab_size": 32016
26
  }
 
22
  "torch_dtype": "float16",
23
  "transformers_version": "4.34.0.dev0",
24
  "use_cache": true,
25
+ "vocab_size": 42414
26
  }
pytorch_model-00001-of-00002.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0f36d62f1ba2fa5891ec8801c97e94d39ecfa4a0264a3e7c7b246426c0d18fd
3
- size 9976754202
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a206bc33ad9407f02e9819a4ecc2f6cb2f5d597317e96f31352ffdfb5f638933
3
+ size 9971739657
pytorch_model-00002-of-00002.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31563012efe341673ff59ad934c7cfac37d98760b511e13be704afc855eb7172
3
- size 3500442883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8922244af2d785fea6c862d5364b863bb5939907bd106e5284b0042cb7bc09b0
3
+ size 3675818233
pytorch_model.bin.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 13477093376
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-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",
 
1
  {
2
  "metadata": {
3
+ "total_size": 13647454208
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-00002-of-00002.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-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-00002-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",