lyy666666 commited on
Commit
224a743
·
verified ·
1 Parent(s): 0a9c740

Delete kud-llama3.3-70b_economic_root_relearn_klr_gdr_economic_1_512_2e-5/checkpoint-1-full

Browse files
kud-llama3.3-70b_economic_root_relearn_klr_gdr_economic_1_512_2e-5/checkpoint-1-full/config.json DELETED
@@ -1,39 +0,0 @@
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
- "head_dim": 128,
14
- "hidden_act": "silu",
15
- "hidden_size": 8192,
16
- "initializer_range": 0.02,
17
- "intermediate_size": 28672,
18
- "max_position_embeddings": 131072,
19
- "mlp_bias": false,
20
- "model_type": "llama",
21
- "num_attention_heads": 64,
22
- "num_hidden_layers": 80,
23
- "num_key_value_heads": 8,
24
- "pretraining_tp": 1,
25
- "rms_norm_eps": 1e-05,
26
- "rope_scaling": {
27
- "factor": 8.0,
28
- "high_freq_factor": 4.0,
29
- "low_freq_factor": 1.0,
30
- "original_max_position_embeddings": 8192,
31
- "rope_type": "llama3"
32
- },
33
- "rope_theta": 500000.0,
34
- "tie_word_embeddings": false,
35
- "torch_dtype": "float32",
36
- "transformers_version": "4.51.0",
37
- "use_cache": true,
38
- "vocab_size": 128256
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
kud-llama3.3-70b_economic_root_relearn_klr_gdr_economic_1_512_2e-5/checkpoint-1-full/generation_config.json DELETED
@@ -1,12 +0,0 @@
1
- {
2
- "bos_token_id": 128000,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128008,
7
- 128009
8
- ],
9
- "temperature": 0.6,
10
- "top_p": 0.9,
11
- "transformers_version": "4.51.0"
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
kud-llama3.3-70b_economic_root_relearn_klr_gdr_economic_1_512_2e-5/checkpoint-1-full/model-00001-of-00062.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d95da28f0c482ae0595dd11f27ac4f0dd44e1c141bcfe55d1a56594d32f2f45f
3
- size 4806672984