afaji commited on
Commit
0034924
2 Parent(s): ce1c80e 79f1372

Merge master into main, resolving conflicts

Browse files
.gitattributes CHANGED
@@ -1,3 +1,4 @@
 
1
  *.7z filter=lfs diff=lfs merge=lfs -text
2
  *.arrow filter=lfs diff=lfs merge=lfs -text
3
  *.bin filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +34,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
1
+
2
  *.7z filter=lfs diff=lfs merge=lfs -text
3
  *.arrow filter=lfs diff=lfs merge=lfs -text
4
  *.bin filter=lfs diff=lfs merge=lfs -text
 
34
  *.zip filter=lfs diff=lfs merge=lfs -text
35
  *.zst filter=lfs diff=lfs merge=lfs -text
36
  *tfevents* filter=lfs diff=lfs merge=lfs -text
37
+
38
+ *.pt filter=lfs diff=lfs merge=lfs -text
39
+ *.bin filter=lfs diff=lfs merge=lfs -text
40
+
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pythia-160m-deduped_mlkv_4_12",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3584,
12
+ "layer_norm_eps": 1e-05,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "gpt_neox",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "num_key_value_heads": 12,
18
+ "num_key_value_layers": 4,
19
+ "rotary_emb_base": 10000,
20
+ "rotary_pct": 0.25,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.24.0",
24
+ "use_cache": true,
25
+ "use_parallel_residual": true,
26
+ "vocab_size": 50304
27
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953f5a60c968b438d42a8f12b1a789fefd1ade0dc6d20142e0ea0d9eb438d31b
3
+ size 649363653
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b7392365af5346dae31320c1a587445ecdceba402fdf38c2e0f265d7149a665
3
+ size 375032237
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9cb7308000ae44c9d6450092742b336c8f6c581184ad117a2f66e5702e619ee
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e82754af80791e311852eff61293b1cd71ea606e027d9f77d966b00000dc58
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|padding|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "name_or_path": "pythia-160m-deduped_mlkv_4_12",
6
+ "special_tokens_map_file": "/admin/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/special_tokens_map.json",
7
+ "tokenizer_class": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f96886f88e6f68d16faa95181b7e3597d83d14b6f880524b53a7bf819f99e4e1
3
+ size 3451