Hugging Face's logo

unparallelled
/
BluScriptCP

Safetensors
Model card Files
xet
 Community
unparallelled commited on
Commit
00e505f
·
verified ·
1 Parent(s): 28e4611

lc8k_135m_2026-10-24/armA_yarn2_eval step 420 (eval, bf16)

Browse files
Files changed (6) hide show
  1. lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/blu_meta.json +17 -0
  2. lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/config.json +76 -0
  3. lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/model.safetensors +3 -0
  4. lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/special_tokens_map.json +6 -0
  5. lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/tokenizer.json +0 -0
  6. lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/tokenizer_config.json +9 -0
lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/blu_meta.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": "49280",
3
+ "head_dim": "128",
4
+ "context_length": "8192",
5
+ "d_model": "512",
6
+ "n_layers": "37",
7
+ "format": "blutrain",
8
+ "linear_layout": "in_out",
9
+ "qk_eps": "1e-06",
10
+ "q_heads": "4",
11
+ "rms_eps": "1e-05",
12
+ "kv_heads": "2",
13
+ "weight_tying": "1",
14
+ "ffn_hidden": "1408",
15
+ "rope_theta": "50000.0",
16
+ "embed_scale": "1"
17
+ }
lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "float32",
9
+ "eos_token_id": 0,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 512,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1408,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention"
53
+ ],
54
+ "max_position_embeddings": 8192,
55
+ "max_window_layers": 28,
56
+ "model_type": "qwen3",
57
+ "num_attention_heads": 4,
58
+ "num_hidden_layers": 37,
59
+ "num_key_value_heads": 2,
60
+ "pad_token_id": 0,
61
+ "rms_norm_eps": 1e-05,
62
+ "rope_parameters": {
63
+ "rope_type": "yarn",
64
+ "rope_theta": 50000.0,
65
+ "factor": 2.0,
66
+ "original_max_position_embeddings": 4096,
67
+ "beta_fast": 32.0,
68
+ "beta_slow": 1.0
69
+ },
70
+ "sliding_window": null,
71
+ "tie_word_embeddings": false,
72
+ "transformers_version": "5.19.0",
73
+ "use_cache": true,
74
+ "use_sliding_window": false,
75
+ "vocab_size": 49280
76
+ }
lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcb66c14bcc0a1d354f64e28e0be935fb640909dcab422f9928feb144e1a28f8
3
+ size 319302040
lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>",
5
+ "pad_token": "<|endoftext|>"
6
+ }
lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
lc8k_135m_2026-10-24/armA_yarn2_eval/step_420/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "PreTrainedTokenizerFast",
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>",
6
+ "pad_token": "<|endoftext|>",
7
+ "add_bos_token": true,
8
+ "model_max_length": 8192
9
+ }