Training in progress, epoch 0
Browse files- arcade100k.tiktoken +0 -0
- config.json +33 -0
- model.safetensors +3 -0
- special_tokens_map.json +4 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
arcade100k.tiktoken
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stabilityai/stablelm-2-1_6b",
|
3 |
+
"architectures": [
|
4 |
+
"StableLMEpochForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig",
|
9 |
+
"AutoModelForCausalLM": "modeling_stablelm_epoch.StableLMEpochForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 100257,
|
12 |
+
"eos_token_id": 100257,
|
13 |
+
"hidden_act": "silu",
|
14 |
+
"hidden_size": 2048,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 5632,
|
17 |
+
"max_position_embeddings": 4096,
|
18 |
+
"model_type": "stablelm_epoch",
|
19 |
+
"norm_eps": 1e-05,
|
20 |
+
"num_attention_heads": 32,
|
21 |
+
"num_heads": 32,
|
22 |
+
"num_hidden_layers": 24,
|
23 |
+
"num_key_value_heads": 32,
|
24 |
+
"rope_pct": 0.25,
|
25 |
+
"rope_theta": 10000,
|
26 |
+
"rotary_scaling_factor": 1.0,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "bfloat16",
|
29 |
+
"transformers_version": "4.37.2",
|
30 |
+
"use_cache": false,
|
31 |
+
"use_qkv_bias": true,
|
32 |
+
"vocab_size": 100352
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:269ef0a03089d7670a54a18093954ba039ee27de41c56b0f9b0be836d5dabae7
|
3 |
+
size 3289069520
|
special_tokens_map.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "<|endoftext|>",
|
3 |
+
"pad_token": "<|endoftext|>"
|
4 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {},
|
3 |
+
"auto_map": {
|
4 |
+
"AutoTokenizer": [
|
5 |
+
"stabilityai/stablelm-2-1_6b--tokenization_arcade100k.Arcade100kTokenizer",
|
6 |
+
null
|
7 |
+
]
|
8 |
+
},
|
9 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
10 |
+
"clean_up_tokenization_spaces": true,
|
11 |
+
"eos_token": "<|endoftext|>",
|
12 |
+
"errors": "replace",
|
13 |
+
"model_max_length": 2048,
|
14 |
+
"pad_token": "<|endoftext|>",
|
15 |
+
"tokenizer_class": "Arcade100kTokenizer"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:371893eee44b87e04e4f6f079b08d9f2edd297499684e0ff2a66ecb67c97d2c7
|
3 |
+
size 5880
|