aklein4 commited on
Commit
be603bc
·
verified ·
1 Parent(s): 6ac26ed

Upload folder using huggingface_hub

Browse files
step_000000000555/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ItttModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "base_lr": 0.001,
8
+ "base_model": "HuggingFaceTB/SmolLM2-360M-Instruct",
9
+ "bos_token_id": 1,
10
+ "disable_fast_weights": false,
11
+ "dtype": "float32",
12
+ "eos_token_id": 2,
13
+ "fast_weight_size": 640,
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 960,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 2560,
19
+ "is_llama_config": true,
20
+ "max_position_embeddings": 8192,
21
+ "mlp_bias": false,
22
+ "model_type": "ittt",
23
+ "momentum_beta": 0.9,
24
+ "momentum_dtype": "bfloat16",
25
+ "num_attention_heads": 15,
26
+ "num_hidden_layers": 32,
27
+ "num_key_value_heads": 5,
28
+ "pad_token_id": 2,
29
+ "pretraining_tp": 1,
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_interleaved": false,
32
+ "rope_scaling": null,
33
+ "rope_theta": 100000,
34
+ "state_dtype": "float32",
35
+ "transformers.js_config": {
36
+ "kv_cache_dtype": {
37
+ "fp16": "float16",
38
+ "q4f16": "float16"
39
+ }
40
+ },
41
+ "transformers_version": "4.57.3",
42
+ "use_cache": true,
43
+ "vocab_size": 49152
44
+ }
step_000000000555/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c5b6349dcaf68baee4badbd843ed85de4944db1b485d573c9c66e48eee7339
3
+ size 1840727440