Undi95 commited on
Commit
d022cfa
1 Parent(s): 74c3035

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Undi95/ReMM-v2.2-L2-13B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 62,
16
+ "num_key_value_heads": 40,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.33.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
pytorch_model-00001-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c46829d7c0b3bf43fdbaba4961a5d06bcef7bf87870f95bc19c0db46fbe4b796
3
+ size 10313078440
pytorch_model-00002-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ebbc8ddfb773fed0875ac6301419d17cfbfae015118a5efc6ef8a5ebc19296
3
+ size 9956563040
pytorch_model-00003-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8d5de993401109c203c37d81b7f951b841dff07ce0602f02ab359f94929d94c
3
+ size 9993273424
pytorch_model-00004-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eac398bfc5266c77127b043e8ca6e8b0e6041f0b05aa0f992f1e18f842d3bba
3
+ size 9725876168
pytorch_model-00005-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8bc62473397834374b4af3dd39682c3e6436220805411a006ff1b936369d9a
3
+ size 655360128
pytorch_model.bin.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {}, "weight_map": {"model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin", "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.40.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.40.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.40.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.41.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.41.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.41.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.42.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.42.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.42.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.43.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.43.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.43.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.44.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.44.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.44.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.45.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.45.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.45.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.46.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.46.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.46.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.47.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.47.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.47.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.48.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.48.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.48.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.49.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.49.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.49.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.50.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.50.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.50.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.51.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.51.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.51.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.52.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.52.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.52.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.53.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.53.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.53.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.54.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.54.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.54.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.55.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.55.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.55.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.56.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.56.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.56.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.57.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.57.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.57.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.58.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.58.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.58.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.59.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.59.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.59.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.60.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.60.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.60.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.61.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.61.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.61.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", "model.norm.weight": "pytorch_model-00004-of-00005.bin", "lm_head.weight": "pytorch_model-00005-of-00005.bin"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "spaces_between_special_tokens": false,
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "use_default_system_prompt": true
35
+ }