np-cr commited on
Commit
382d664
·
verified ·
1 Parent(s): 107505a

Upload folder using huggingface_hub

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|' + message['role'] + '|>' + '
2
+ ' + message['content'] + '<|end|>
3
+ ' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
4
+ ' }}{% else %}{{ eos_token }}{% endif %}
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PhimoeForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 2,
10
+ "head_dim": 16,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 64,
13
+ "initializer_range": 0.02,
14
+ "input_jitter_noise": 0.0,
15
+ "intermediate_size": 48,
16
+ "lm_head_bias": true,
17
+ "max_position_embeddings": 512,
18
+ "model_type": "phimoe",
19
+ "num_attention_heads": 4,
20
+ "num_experts_per_tok": 2,
21
+ "num_hidden_layers": 2,
22
+ "num_key_value_heads": 2,
23
+ "num_local_experts": 4,
24
+ "output_router_logits": false,
25
+ "pad_token_id": null,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_parameters": {
28
+ "rope_theta": 10000.0,
29
+ "rope_type": "default"
30
+ },
31
+ "router_aux_loss_coef": 0.001,
32
+ "router_jitter_noise": 0.01,
33
+ "sliding_window": 256,
34
+ "tie_word_embeddings": false,
35
+ "transformers_version": "5.8.0",
36
+ "use_cache": true,
37
+ "vocab_size": 1024
38
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.8.0",
8
+ "use_cache": true
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49859a635907bbcd1be041b087c22d69b7b9d0db53e015efd784d2c92fbe7b2b
3
+ size 469848
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|endoftext|>",
6
+ "is_local": false,
7
+ "legacy": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 4096,
10
+ "pad_token": "<|endoftext|>",
11
+ "padding_side": "left",
12
+ "sp_model_kwargs": {},
13
+ "tokenizer_class": "TokenizersBackend",
14
+ "unk_token": "<unk>",
15
+ "use_default_system_prompt": false
16
+ }