Hugging Face's logo

pints-ai
/
Llama-3.1-8B-Instruct-RAG_XML_tuned-2

Model card Files Community
zpdeaccount commited on
Commit
c4f5d9d
·
verified ·
1 Parent(s): 27f5611

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-12/config.json +38 -0
  2. checkpoint-12/pytorch_model.bin +3 -0
  3. checkpoint-12/random_states_0.pkl +3 -0
  4. checkpoint-12/scheduler.bin +3 -0
  5. checkpoint-14/config.json +38 -0
  6. checkpoint-14/pytorch_model.bin +3 -0
  7. checkpoint-14/random_states_0.pkl +3 -0
  8. checkpoint-14/scheduler.bin +3 -0
  9. checkpoint-16/config.json +38 -0
  10. checkpoint-16/pytorch_model.bin +3 -0
  11. checkpoint-16/random_states_0.pkl +3 -0
  12. checkpoint-16/scheduler.bin +3 -0
  13. checkpoint-18/config.json +38 -0
  14. checkpoint-18/pytorch_model.bin +3 -0
  15. checkpoint-18/random_states_0.pkl +3 -0
  16. checkpoint-18/scheduler.bin +3 -0
  17. checkpoint-20/config.json +38 -0
  18. checkpoint-20/pytorch_model.bin +3 -0
  19. checkpoint-20/random_states_0.pkl +3 -0
  20. checkpoint-20/scheduler.bin +3 -0
checkpoint-12/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
+ "rope_theta": 500000.0,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.42.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
checkpoint-12/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee8414f12acaf4f8933f000df8702246ea0d865e54efd2fcddb75a970bf5943
3
+ size 32121081646
checkpoint-12/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bacbf9f878f31f457ca768202bf3675c164d070417ae5e6695ab64d00f7b9639
3
+ size 14344
checkpoint-12/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af347201fee4751116e1a5d93fba120dfb9f0d1caf0a127bc8eb4c078207437
3
+ size 1064
checkpoint-14/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
+ "rope_theta": 500000.0,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.42.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
checkpoint-14/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7893652aa6f01b7a2aee3f57dd31ad38c7179ff3b7f670826e0903b355c6c16a
3
+ size 32121081646
checkpoint-14/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b7fc0bc4841e058b500da4bef5fbf5478ba6466daa3a086f0f09777bcfa8dcb
3
+ size 14344
checkpoint-14/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34f0ce6e9bfbcd302b72d41137906a6b6a15960508f1d8b6f2db4be5294b7a2e
3
+ size 1064
checkpoint-16/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
+ "rope_theta": 500000.0,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.42.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
checkpoint-16/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6a6d4dd4ae1c7a7db74635303b990c087dcc6d1daaa93031d2bc98356037b74
3
+ size 32121081646
checkpoint-16/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:199e5be02aa57e74f522005219dcbbf4692f15e0b65173837ce2ab661749b9cf
3
+ size 14344
checkpoint-16/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f37ded0d75686e8acfacf487aad41e95d02fa0c5ee9da16a795c41cd8a7f8c
3
+ size 1064
checkpoint-18/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
+ "rope_theta": 500000.0,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.42.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
checkpoint-18/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9e26f6fedb06fffb096a7e82d934d2cb982aee371b8081de82b77be6fd5d31b
3
+ size 32121081646
checkpoint-18/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da6507ac745950b4a5ccea274b4cfa74f3ce26b95a4728f90369adb3f9f7623
3
+ size 14344
checkpoint-18/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca83f9abb5ebc7c370b3662a2468eaf17d3759786fa6385ba3d6397c5f2f1045
3
+ size 1064
checkpoint-20/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 131072,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
+ "rope_theta": 500000.0,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.42.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
checkpoint-20/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adcd7431cf03d503a301d171290152a760c4c4a42cd8914393e56d7a08687aa5
3
+ size 32121081646
checkpoint-20/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b849493c8c38ae3611c3c4e2362dfae3ea033ecaec63c50f2fccef2698f9e38a
3
+ size 14344
checkpoint-20/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c4594deca9821e93924340834de5670e43466e3babbec2056078fb6531604d
3
+ size 1064