Hugging Face's logo

k1h0
/
Tplb_llama3

Safetensors
llama
Model card Files
xet
 Community
k1h0 commited on
Commit
dcfe898
·
verified ·
1 Parent(s): 7f8688c

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. config.json +30 -0
  2. generation_config.json +7 -0
  3. global_step1000/mp_rank_00_model_states.pt +3 -0
  4. global_step1000/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  5. global_step1000/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  6. global_step1000/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  7. global_step1000/zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  8. latest +1 -0
  9. model.safetensors +3 -0
  10. rng_state_0.pth +3 -0
  11. rng_state_1.pth +3 -0
  12. rng_state_2.pth +3 -0
  13. rng_state_3.pth +3 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2048,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 32,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.48.2",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.48.2"
7
+ }
global_step1000/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73eadc1ae84092c9e38e5b15c83d46957caf3e0288c24aa9d8ad86baf44224f5
3
+ size 2141543788
global_step1000/zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9977424fcf8886b719e8aab3ee1f0d9e4d424bef3541e6dc199faaa3e20dc1b
3
+ size 3212195949
global_step1000/zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8442b25d2a80d54cbdd7620bf01922a68c66eaf9abfd4ed7eb9b9c41ab8c058
3
+ size 3212197805
global_step1000/zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32b1982a81e6a73dcf0a5ca2a7bed89956e97868df8a674f4711e043766e9cae
3
+ size 3212197613
global_step1000/zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fefd668f85f38ee9c90f04111ccb8df995ac8f0e47fc67a946902bf52003413
3
+ size 3212196205
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step1000
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:214a13556d7202fa785283a4abbaae32e3abcc88465202fe982500be6f23e573
3
+ size 4282950264
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
3
+ size 15024
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
3
+ size 15024
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
3
+ size 15024
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
3
+ size 15024