pbw-Berwin commited on
Commit
787deb5
1 Parent(s): e959954

init commit for model weights and tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.29.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32001
26
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.29.2"
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76a29dbbdbbe31143cb8ae5f4f043e9ef5258a08d51888d46c8ebb175fc6dd1e
3
+ size 26953810889
pytorch_model.bin.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.0.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.0.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.0.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.0.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.0.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.1.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.1.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.1.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.1.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.2.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.2.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.2.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.2.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.3.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.3.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.3.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.3.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.4.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.4.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.4.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.4.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.5.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.5.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.5.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.5.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.6.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.6.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.6.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.6.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.7.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.7.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.7.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.7.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.8.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.8.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.8.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.8.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.9.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.9.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.9.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.9.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.10.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.10.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.10.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.10.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.11.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.11.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.11.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.11.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.12.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.12.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.12.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.12.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.13.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.13.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.13.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.13.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.14.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.14.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.14.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.14.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.15.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.15.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.15.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.15.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.16.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.16.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.16.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.16.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.17.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.17.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.17.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.17.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.18.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.18.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.18.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.18.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.19.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.19.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.19.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.19.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.20.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.20.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.20.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.20.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.21.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.21.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.21.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.21.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.22.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.22.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.22.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.22.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.23.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.23.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.23.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.23.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.24.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.24.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.24.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.24.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.25.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.25.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.25.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.25.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.26.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.26.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.26.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.26.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.27.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.27.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.27.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.27.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.28.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.28.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.28.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.28.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.29.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.29.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.29.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.29.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.30.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.30.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.30.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.30.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model_00000-of-00001.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.31.self_attn.k_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.31.self_attn.v_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model_00000-of-00001.bin", "model.layers.31.input_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.layers.31.post_attention_layernorm.weight": "pytorch_model_00000-of-00001.bin", "model.embed_tokens.weight": "pytorch_model_00000-of-00001.bin", "model.norm.weight": "pytorch_model_00000-of-00001.bin", "lm_head.weight": "pytorch_model_00000-of-00001.bin"}
pytorch_model_00000-of-00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:002ed0b5865a98805894a86b44d4cb7d88272faa8eba2f48caeb385da4942913
3
+ size 26953831368
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "</s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "</s>"
6
+ }
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
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 1024,
23
+ "pad_token": null,
24
+ "padding_side": "left",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }