Upload folder using huggingface_hub
Browse files- config.json +27 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +42 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"TransformerLM"
|
| 4 |
+
],
|
| 5 |
+
"aux_loss_alpha": 0.1,
|
| 6 |
+
"dim": 512,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"flash_attn": true,
|
| 9 |
+
"hidden_dim": 1408,
|
| 10 |
+
"max_seq_len": 1024,
|
| 11 |
+
"model_type": "transformerlm",
|
| 12 |
+
"multiple_of": 64,
|
| 13 |
+
"n_heads": 8,
|
| 14 |
+
"n_kv_heads": 2,
|
| 15 |
+
"n_layers": 8,
|
| 16 |
+
"n_routed_experts": 4,
|
| 17 |
+
"n_shared_experts": true,
|
| 18 |
+
"norm_eps": 1e-05,
|
| 19 |
+
"norm_topk_prob": true,
|
| 20 |
+
"num_experts_per_tok": 2,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"scoring_func": "softmax",
|
| 23 |
+
"seq_aux": true,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.51.3",
|
| 26 |
+
"vocab_size": 6400
|
| 27 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29dd223098555aa61b2e818e1e9f82278ecf600fbeecc3c4752857d6f71e533b
|
| 3 |
+
size 103344012
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"bos_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"unk_token": "<unk>",
|
| 8 |
+
"pad_token": "<unk>",
|
| 9 |
+
"model_max_length": 32768,
|
| 10 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 11 |
+
"clean_up_tokenization_spaces": false,
|
| 12 |
+
"additional_special_tokens": [],
|
| 13 |
+
"spaces_between_special_tokens": false,
|
| 14 |
+
"sp_model_kwargs": {},
|
| 15 |
+
"added_tokens_decoder": {
|
| 16 |
+
"0": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
"1": {
|
| 25 |
+
"content": "<s>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false,
|
| 30 |
+
"special": true
|
| 31 |
+
},
|
| 32 |
+
"2": {
|
| 33 |
+
"content": "</s>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false,
|
| 38 |
+
"special": true
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{{ '<s>system\\n' + system_message + '</s>\\n' }}{% else %}{{ '<s>system\\nYou are a helpful AI assistant.</s>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<s>user\\n' + content + '</s>\\n<s>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% endif %}{% endfor %}"
|
| 42 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|