File size: 4,022 Bytes
496320f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 |
---
library_name: transformers
pipeline_tag: text-generation
inference: true
widget:
- text: Hello!
example_title: Hello world
group: Python
base_model:
- baidu/ERNIE-4.5-0.3B-PT
---
This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [baidu/ERNIE-4.5-0.3B-PT](https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT).
### Example usage:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
# Load model and tokenizer
model_id = "tiny-random/ernie-4.5"
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="auto",
torch_dtype="bfloat16",
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_id)
# Generate answer
prompt = "What is AI?"
input_ids = tokenizer.apply_chat_template(
[{"role": "user", "content": prompt}],
add_generation_prompt=True,
return_tensors="pt",
tokenize=True,
).to(model.device)
output = model.generate(
input_ids,
do_sample=True,
max_new_tokens=32,
)
print(tokenizer.decode(output[0], skip_special_tokens=False))
```
### Codes to create this repo:
```python
import json
from pathlib import Path
import accelerate
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
AutoConfig,
AutoModelForCausalLM,
AutoProcessor,
GenerationConfig,
set_seed,
)
source_model_id = "baidu/ERNIE-4.5-0.3B-PT"
save_folder = "/tmp/tiny-random/ernie-4.5"
processor = AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True)
processor.save_pretrained(save_folder)
with open(hf_hub_download(source_model_id, filename='config.json', repo_type='model'), 'r', encoding='utf-8') as f:
config_json = json.load(f)
config_json['hidden_size'] = 8
config_json['intermediate_size'] = 32
config_json['head_dim'] = 32
config_json['num_attention_heads'] = 16
config_json['num_hidden_layers'] = 2
config_json['num_key_value_heads'] = 8
config_json['tie_word_embeddings'] = True
config_json['use_cache'] = True
with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
json.dump(config_json, f, indent=2)
config = AutoConfig.from_pretrained(
save_folder,
trust_remote_code=True,
)
print(config)
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(config)
torch.set_default_dtype(torch.float32)
if file_exists(filename="generation_config.json", repo_id=source_model_id, repo_type='model'):
model.generation_config = GenerationConfig.from_pretrained(
source_model_id, trust_remote_code=True,
)
model.generation_config.do_sample = True
print(model.generation_config)
model = model.cpu()
with torch.no_grad():
for name, p in sorted(model.named_parameters()):
torch.nn.init.normal_(p, 0, 0.1)
print(name, p.shape)
model.save_pretrained(save_folder)
print(model)
```
### Printing the model:
```text
Ernie4_5ForCausalLM(
(model): Ernie4_5Model(
(embed_tokens): Embedding(103424, 8, padding_idx=0)
(layers): ModuleList(
(0-1): 2 x Ernie4_5DecoderLayer(
(self_attn): Ernie4_5Attention(
(q_proj): Linear(in_features=8, out_features=512, bias=False)
(k_proj): Linear(in_features=8, out_features=256, bias=False)
(v_proj): Linear(in_features=8, out_features=256, bias=False)
(o_proj): Linear(in_features=512, out_features=8, bias=False)
)
(mlp): Ernie4_5MLP(
(gate_proj): Linear(in_features=8, out_features=32, bias=False)
(up_proj): Linear(in_features=8, out_features=32, bias=False)
(down_proj): Linear(in_features=32, out_features=8, bias=False)
(act_fn): SiLU()
)
(input_layernorm): Ernie4_5RMSNorm((8,), eps=1e-05)
(post_attention_layernorm): Ernie4_5RMSNorm((8,), eps=1e-05)
)
)
(norm): Ernie4_5RMSNorm((8,), eps=1e-05)
(rotary_emb): Ernie4_5RotaryEmbedding()
)
(lm_head): Linear(in_features=8, out_features=103424, bias=False)
)
``` |