nicholasKluge
commited on
Commit
•
66966f4
1
Parent(s):
284acfb
Upload folder using huggingface_hub
Browse files- config.json +28 -0
- emissions.csv +2 -0
- generation_config.json +16 -0
- lr_scheduler.pt +3 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pt +3 -0
- special_tokens_map.json +46 -0
- tokenizer.json +0 -0
- tokenizer_config.json +72 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "nicholasKluge/TeenyTinyLlama-460m-Chat",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 1024,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 4096,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_hidden_layers": 24,
|
17 |
+
"num_key_value_heads": 16,
|
18 |
+
"pad_token_id": 3,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.35.2",
|
26 |
+
"use_cache": false,
|
27 |
+
"vocab_size": 32002
|
28 |
+
}
|
emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
2 |
+
2024-01-18T02:02:26,TeenyTinyLlama,39b206a4-e86a-41fa-a5f9-44deef6d7e34,49516.08560705185,2.5308193028462096,5.1111053545916445e-05,42.5,279.50887502416805,31.303916931152344,0.5845638546203586,4.576422722524138,0.43049185652675864,5.591478433671226,United States,USA,iowa,,,Linux-6.1.58+-x86_64-with-glibc2.35,3.10.12,2.3.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,-95.8517,41.2591,83.47711181640625,machine,N,1.0
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_new_tokens": 2048,
|
6 |
+
"pad_token_id": 3,
|
7 |
+
"renormalize_logits": true,
|
8 |
+
"repetition_penalty": 1.2,
|
9 |
+
"sep_token_id": null,
|
10 |
+
"temperature": 0.3,
|
11 |
+
"top_k": 30,
|
12 |
+
"top_p": 0.3,
|
13 |
+
"transformers_version": "4.35.2",
|
14 |
+
"unk_token_id": 0,
|
15 |
+
"use_cache": false
|
16 |
+
}
|
lr_scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c11d4601080fedeca24ad9723d9ac414096c8c46554c5d71c3c5dbc9fe575740
|
3 |
+
size 1076
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fda5c52702251b502b4c2892602975b6e5e6c872444b1dc2e3dcd97571adedea
|
3 |
+
size 1872998792
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8dce605797f1779bae4347bb20cfcbf04dc4e3e98c43da309cd25a6e9930f51
|
3 |
+
size 3746132218
|
rng_state.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cd5d4755143e6e9c0750b54c85f1ecb37e9aefe38e0eca4de59dba7168d44c0
|
3 |
+
size 6246
|
special_tokens_map.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<instruction>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "</instruction>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"bos_token": {
|
19 |
+
"content": "<s>",
|
20 |
+
"lstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"rstrip": false,
|
23 |
+
"single_word": false
|
24 |
+
},
|
25 |
+
"eos_token": {
|
26 |
+
"content": "</s>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
},
|
32 |
+
"pad_token": {
|
33 |
+
"content": "<pad>",
|
34 |
+
"lstrip": false,
|
35 |
+
"normalized": false,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
},
|
39 |
+
"unk_token": {
|
40 |
+
"content": "<unk>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": false,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
}
|
46 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<pad>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"32000": {
|
36 |
+
"content": "<instruction>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"32001": {
|
44 |
+
"content": "</instruction>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"additional_special_tokens": [
|
53 |
+
"<instruction>",
|
54 |
+
"</instruction>"
|
55 |
+
],
|
56 |
+
"bos_token": "<s>",
|
57 |
+
"bos_token_id": 1,
|
58 |
+
"chat_template": "{{bos_token}}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '<instruction>' + message['content'].strip() + '</instruction>'}}{% elif message['role'] == 'assistant' %}{{ message['content'].strip() + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
59 |
+
"clean_up_tokenization_spaces": false,
|
60 |
+
"eos_token": "</s>",
|
61 |
+
"eos_token_id": 2,
|
62 |
+
"legacy": false,
|
63 |
+
"model_max_length": 1000000000000000019884624838656,
|
64 |
+
"pad_token": "<pad>",
|
65 |
+
"pad_token_id": 3,
|
66 |
+
"padding_side": "right",
|
67 |
+
"sp_model_kwargs": {},
|
68 |
+
"tokenizer_class": "LlamaTokenizer",
|
69 |
+
"unk_token": "<unk>",
|
70 |
+
"unk_token_id": 0,
|
71 |
+
"use_default_system_prompt": false
|
72 |
+
}
|