nicholasKluge commited on
Commit
caba268
·
verified ·
1 Parent(s): 63b7ccf

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 96,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1536,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "is_llama_config": true,
15
+ "max_position_embeddings": 4096,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 28,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 49109,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_interleaved": false,
25
+ "rope_scaling": null,
26
+ "rope_theta": 50000.0,
27
+ "tie_word_embeddings": true,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.53.2",
30
+ "use_cache": false,
31
+ "vocab_size": 49152
32
+ }
evals.yaml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ evaluations:
2
+ ARC Challenge: 0.2352437981180496
3
+ Bangla MMLU: 0.2395254237288135
4
+ BoolQ-BN: 0.5208333333333334
5
+ CommonsenseQA-BN: 0.3022113022113022
6
+ HellaSwag: 0.3030729279376758
7
+ MMLU: 0.2640876748180257
8
+ OpenBookQA-BN: 0.3279678068410462
9
+ PIQA-BN: 0.5870511425462459
10
+ TruthfulQA MC1: 0.2407170294494238
11
+ step: 48219
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "pad_token_id": 49109,
5
+ "transformers_version": "4.53.2",
6
+ "do_sample": true,
7
+ "max_new_tokens": 1024,
8
+ "renormalize_logits": true,
9
+ "repetition_penalty": 1.2,
10
+ "temperature": 0.1,
11
+ "top_k": 50,
12
+ "top_p": 1.0,
13
+ "use_cache": false
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a8336f741dd2293048bca5ee7f7116a3e6e8da83fba9b6b4ff60b2532290e7
3
+ size 1340284304
special_tokens_map.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<tools>",
4
+ "</tools>",
5
+ "<tool_call>",
6
+ "</tool_call>",
7
+ "<tool_response>",
8
+ "</tool_response>",
9
+ "<think>",
10
+ "</think>",
11
+ "<answer>",
12
+ "</answer>",
13
+ "<context>",
14
+ "</context>",
15
+ "<|fim_prefix|>",
16
+ "<|fim_suffix|>",
17
+ "<|fim_middle|>",
18
+ "<|repo_name|>",
19
+ "<|image|>",
20
+ "<|image_pad|>",
21
+ "<|image_placeholder|>",
22
+ " ",
23
+ " ",
24
+ " ",
25
+ " ",
26
+ " ",
27
+ " ",
28
+ " ",
29
+ " ",
30
+ " ",
31
+ " ",
32
+ " ",
33
+ " ",
34
+ " ",
35
+ " ",
36
+ " ",
37
+ " ",
38
+ " ",
39
+ " ",
40
+ " ",
41
+ " ",
42
+ " ",
43
+ " ",
44
+ " "
45
+ ],
46
+ "bos_token": {
47
+ "content": "<|im_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "eos_token": {
54
+ "content": "<|im_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ },
60
+ "pad_token": {
61
+ "content": "<|pad|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "unk_token": {
68
+ "content": "<|unk|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ }
74
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff