tjellm commited on
Commit
313e3ba
1 Parent(s): ecd41e2

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 4096,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 11008,
11
+ "max_position_embeddings": 4096,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 32,
14
+ "num_hidden_layers": 1,
15
+ "num_key_value_heads": 32,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-06,
18
+ "rope_scaling": null,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float16",
21
+ "transformers_version": "4.32.0.dev0",
22
+ "use_cache": true,
23
+ "vocab_size": 32001
24
+ }
optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d49dc80433a4c4b88490d45d78ea62a875572cc0de59fafaf8a8c7d51cb4d3
3
+ size 1887510859
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4825eb7cac842c52557e5003e1ea5d93efca8cf55c9c084cbe135896d17ad3ea
3
+ size 1468059922
pytorch_model_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e433b9ff30c316b2549626a325e4268e9bb57ad342cc7562e5ac921b3a2598d5
3
+ size 524305219
random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:736ae544a148378300b44c58d57bb8b6660ef90efa74621032164077fd6ba89a
3
+ size 15627
scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c1782aee9d28318f7cd0330df671db55729b36015f1476122322248fe4c2fa
3
+ size 563