namannn commited on
Commit
9e204a7
·
verified ·
1 Parent(s): 4f6e917

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -16,7 +16,7 @@
16
  "max_position_embeddings": 4096,
17
  "model_type": "baichuan",
18
  "num_attention_heads": 32,
19
- "num_hidden_layers": 24,
20
  "pad_token_id": 0,
21
  "rms_norm_eps": 1e-06,
22
  "tie_word_embeddings": false,
 
16
  "max_position_embeddings": 4096,
17
  "model_type": "baichuan",
18
  "num_attention_heads": 32,
19
+ "num_hidden_layers": 25,
20
  "pad_token_id": 0,
21
  "rms_norm_eps": 1e-06,
22
  "tie_word_embeddings": false,
model-00005-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b63070a92f06996e9761e6e96f4a173cb0009b8282a432927dc6b82df6b7319
3
- size 2038515408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3fbb8e427a4d4cb32de7d1c2ba2ccc34d15985676c939502a75df9d97c9079
3
+ size 2848050024
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 21525977088
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00005-of-00005.safetensors",
@@ -141,6 +141,14 @@
141
  "model.layers.23.self_attn.W_pack.weight": "model-00005-of-00005.safetensors",
142
  "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
143
  "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00005-of-00005.safetensors",
 
 
 
 
 
 
 
 
144
  "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
145
  "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
146
  "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 22335510784
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00005-of-00005.safetensors",
 
141
  "model.layers.23.self_attn.W_pack.weight": "model-00005-of-00005.safetensors",
142
  "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
143
  "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00005-of-00005.safetensors",
144
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00005.safetensors",
145
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
146
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
147
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
148
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
149
+ "model.layers.24.self_attn.W_pack.weight": "model-00005-of-00005.safetensors",
150
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
151
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00005-of-00005.safetensors",
152
  "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
153
  "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
154
  "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",