Happyb commited on
Commit
49bd705
·
verified ·
1 Parent(s): 79407b8

Upload 3 files

Browse files
config.json CHANGED
@@ -1,13 +1,12 @@
1
  {
2
- "_name_or_path": "/scratch/gpfs/awettig/wura/checkpoints/lcft_Llama-3.1-8B_datasets_wura_unimax_0.6+math_bsz512_steps2400_lr1e-5_warmup0.1",
3
  "architectures": [
4
- "LlamaForSequenceClassification"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
  "eos_token_id": 128001,
10
- "head_dim": 128,
11
  "hidden_act": "silu",
12
  "hidden_size": 4096,
13
  "initializer_range": 0.02,
@@ -31,7 +30,7 @@
31
  "rope_theta": 500000.0,
32
  "tie_word_embeddings": false,
33
  "torch_dtype": "float32",
34
- "transformers_version": "4.47.0",
35
  "use_cache": true,
36
  "vocab_size": 128256
37
  }
 
1
  {
2
+ "_name_or_path": "/home/awettig/pli/models/meta-llama/Llama-3.1-8B",
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
  "eos_token_id": 128001,
 
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
 
30
  "rope_theta": 500000.0,
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "float32",
33
+ "transformers_version": "4.44.2",
34
  "use_cache": true,
35
  "vocab_size": 128256
36
  }
model-00007-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cf6bcb07654a6d3acb4ef5100ce156b1e4809f852e05b2b8b27cc49b92c4448
3
- size 469844616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66de43ff7d696feb6962470bafe06020287d2ad3cb6e8ff8cd886b92d55bf5c
3
+ size 2571158184
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
- size 17209920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4
3
+ size 9085657