Training in progress, step 100
Browse files- config.json +101 -0
- model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +39 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "apple/OpenELM-450M",
|
| 3 |
+
"activation_fn_name": "swish",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"OpenELMForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "apple/OpenELM-450M--configuration_openelm.OpenELMConfig",
|
| 9 |
+
"AutoModelForCausalLM": "apple/OpenELM-450M--modeling_openelm.OpenELMForCausalLM"
|
| 10 |
+
},
|
| 11 |
+
"bos_token_id": 1,
|
| 12 |
+
"eos_token_id": 2,
|
| 13 |
+
"ffn_dim_divisor": 256,
|
| 14 |
+
"ffn_multipliers": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.68,
|
| 17 |
+
0.87,
|
| 18 |
+
1.05,
|
| 19 |
+
1.24,
|
| 20 |
+
1.42,
|
| 21 |
+
1.61,
|
| 22 |
+
1.79,
|
| 23 |
+
1.97,
|
| 24 |
+
2.16,
|
| 25 |
+
2.34,
|
| 26 |
+
2.53,
|
| 27 |
+
2.71,
|
| 28 |
+
2.89,
|
| 29 |
+
3.08,
|
| 30 |
+
3.26,
|
| 31 |
+
3.45,
|
| 32 |
+
3.63,
|
| 33 |
+
3.82,
|
| 34 |
+
4.0
|
| 35 |
+
],
|
| 36 |
+
"ffn_with_glu": true,
|
| 37 |
+
"head_dim": 64,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"max_context_length": 2048,
|
| 40 |
+
"model_dim": 1536,
|
| 41 |
+
"model_type": "openelm",
|
| 42 |
+
"normalization_layer_name": "rms_norm",
|
| 43 |
+
"normalize_qk_projections": true,
|
| 44 |
+
"num_gqa_groups": 4,
|
| 45 |
+
"num_kv_heads": [
|
| 46 |
+
3,
|
| 47 |
+
3,
|
| 48 |
+
3,
|
| 49 |
+
4,
|
| 50 |
+
4,
|
| 51 |
+
4,
|
| 52 |
+
4,
|
| 53 |
+
4,
|
| 54 |
+
4,
|
| 55 |
+
4,
|
| 56 |
+
5,
|
| 57 |
+
5,
|
| 58 |
+
5,
|
| 59 |
+
5,
|
| 60 |
+
5,
|
| 61 |
+
5,
|
| 62 |
+
6,
|
| 63 |
+
6,
|
| 64 |
+
6,
|
| 65 |
+
6
|
| 66 |
+
],
|
| 67 |
+
"num_query_heads": [
|
| 68 |
+
12,
|
| 69 |
+
12,
|
| 70 |
+
12,
|
| 71 |
+
16,
|
| 72 |
+
16,
|
| 73 |
+
16,
|
| 74 |
+
16,
|
| 75 |
+
16,
|
| 76 |
+
16,
|
| 77 |
+
16,
|
| 78 |
+
20,
|
| 79 |
+
20,
|
| 80 |
+
20,
|
| 81 |
+
20,
|
| 82 |
+
20,
|
| 83 |
+
20,
|
| 84 |
+
24,
|
| 85 |
+
24,
|
| 86 |
+
24,
|
| 87 |
+
24
|
| 88 |
+
],
|
| 89 |
+
"num_transformer_layers": 20,
|
| 90 |
+
"qkv_multipliers": [
|
| 91 |
+
0.5,
|
| 92 |
+
1.0
|
| 93 |
+
],
|
| 94 |
+
"rope_freq_constant": 10000,
|
| 95 |
+
"rope_max_length": 4096,
|
| 96 |
+
"share_input_output_layers": true,
|
| 97 |
+
"torch_dtype": "bfloat16",
|
| 98 |
+
"transformers_version": "4.40.2",
|
| 99 |
+
"use_cache": false,
|
| 100 |
+
"vocab_size": 32000
|
| 101 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8458f0f06be1edac81e8983a6455f46541578d03ef5de9b9a53611399540a412
|
| 3 |
+
size 914376544
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"model_max_length": 2048,
|
| 34 |
+
"pad_token": "</s>",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 37 |
+
"unk_token": "<unk>",
|
| 38 |
+
"use_default_system_prompt": false
|
| 39 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ac2b0a9412f20f4816ed533dedfed0faf0af8bfab116e27242242f9919f701b
|
| 3 |
+
size 5112
|