Hugging Face's logo

jburtoft
/
TencentARC-LLaMA-Pro-8B-Neuron

Text Generation
Transformers
llama
Model card Files
xet
Community
1
jburtoft commited on
Commit
15cc7c7
·
1 Parent(s): 247cf38

e35676c03827755f28ad10e6b5d9c726f695481721e8cbcc64513fb93ce927a9

Browse files
Files changed (21) hide show
  1. checkpoint/config.json +27 -0
  2. checkpoint/generation_config.json +10 -0
  3. checkpoint/pytorch_model.bin/key_to_filename.json +3 -0
  4. checkpoint/pytorch_model.bin/p0.model.embed_tokens.weight +3 -0
  5. checkpoint/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight +3 -0
  6. checkpoint/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight +3 -0
  7. checkpoint/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight +3 -0
  8. checkpoint/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight +3 -0
  9. checkpoint/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight +3 -0
  10. checkpoint/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight +3 -0
  11. checkpoint/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight +3 -0
  12. checkpoint/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight +3 -0
  13. checkpoint/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight +3 -0
  14. checkpoint/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight +3 -0
  15. checkpoint/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight +3 -0
  16. checkpoint/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight +3 -0
  17. checkpoint/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight +3 -0
  18. checkpoint/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight +3 -0
  19. checkpoint/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight +3 -0
  20. checkpoint/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight +3 -0
  21. checkpoint/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight +3 -0
checkpoint/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TencentARC/LLaMA-Pro-8B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 32,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.35.0",
25
+ "use_cache": false,
26
+ "vocab_size": 32000
27
+ }
checkpoint/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": "4.35.0"
10
+ }
checkpoint/pytorch_model.bin/key_to_filename.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:accc6d0b7e8ac18844510c952c638af18d0928c1f979af789d331fe83a76804b
3
+ size 33029
checkpoint/pytorch_model.bin/p0.model.embed_tokens.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da5c4acb278381b1fc040ff34ca7cdfa8264895cfad4fee5c90436c423a8f459
3
+ size 524288789
checkpoint/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4486401b9f7b27193d310385d3468fdd234936513b93a4d2e9662d745b9b74
3
+ size 67109756
checkpoint/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a22f8644d0a6940f854aaf7882e60579972973c97575f7e25622f97280f977
3
+ size 67109759
checkpoint/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60b0aa129eed6e7b322683997c497603c5bba07fb4f64e7246b295867b0d726
3
+ size 67109765
checkpoint/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f0b4439d5547443880eb1f905d2dd042af727be5643dd1af18b95f70a655f3
3
+ size 67109765
checkpoint/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4822a5f66485049b1fece7846843d1c247a65d19f768b6ef40f714673e881e98
3
+ size 67109765
checkpoint/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0856a9791eaa39152016e2e421fa676930357a80792390d85d3dd74b4b8ca4d4
3
+ size 67109765
checkpoint/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c211235eb452ff666a16ff5a2e21caec7f8e762d55012374dfb0b452f5d5ca6
3
+ size 180355964
checkpoint/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ac0d9c9396b45e4c56cc8b9f62cd3c5e2c1bb3919fb37063d60ea4ab8c667b5
3
+ size 180355958
checkpoint/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866961cf803df96b5ddbbca8595c500f1b4a4b589b3d02b5870ff1787c0e43f8
3
+ size 180355964
checkpoint/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efd40808bf978950d0c675d28d2d11c3ae1a6235fff6a951ce5243348fe4de7c
3
+ size 17282
checkpoint/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499e731f678449428e42c0d25cc653e285d0e91326540dae7d1df3410f38489e
3
+ size 17309
checkpoint/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4108adf9590af98cff9a6174270eb18c64e099f462936c79348371982ef86699
3
+ size 67109765
checkpoint/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4afe803e9188698fe5b29e551e418da34e536dd5fc42d53f2d4d02acb06780a0
3
+ size 67109759
checkpoint/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f94694b15cffe8519794399e50acfd8310fba30d09e0fa773dd36aaaf9cf2737
3
+ size 67109765
checkpoint/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17a77e7767e6ca9e0ce0d99da596221a8116fa6106d38a5d27ce209cca74bae
3
+ size 67109765
checkpoint/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f20884410b51337b8b3e8166c5b94b05bb7d6749791dab73768eea7491f111ae
3
+ size 67109765
checkpoint/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:738de823fe9ddcd098a6e52bbb47f5683a045dfd1b2e209cac5e90bdbb936304
3
+ size 180355964