File size: 4,603 Bytes
2c5a759 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 | ---
library_name: transformers
base_model:
- sapientinc/HRM-Text-1B
---
This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [sapientinc/HRM-Text-1B](https://huggingface.co/sapientinc/HRM-Text-1B).
| File path | Size |
|------|------|
| model.safetensors | 2.3MB |
### Example usage:
```python
from transformers import pipeline
model_id = "tiny-random/hrm-text"
pipe = pipeline(
"text-generation", model=model_id, device="cuda",
trust_remote_code=True, max_new_tokens=16,
)
print(pipe("Hello World!"))
```
### Codes to create this repo:
<details>
<summary>Click to expand</summary>
```python
import json
import torch
from huggingface_hub import file_exists, hf_hub_download
from transformers import (
AutoConfig,
AutoModelForCausalLM,
AutoTokenizer,
GenerationConfig,
pipeline,
set_seed,
)
source_model_id = "sapientinc/HRM-Text-1B"
save_folder = "/tmp/tiny-random/hrm-text"
tokenizer = AutoTokenizer.from_pretrained(
source_model_id, trust_remote_code=True,
)
tokenizer.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: dict = json.load(f)
config_json.update({
"hidden_size": 8,
"intermediate_size": 64,
"num_attention_heads": 4,
"num_key_value_heads": 4,
"head_dim": 32,
"num_hidden_layers": 8,
})
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,
)
model = AutoModelForCausalLM.from_config(
config,
dtype=torch.bfloat16,
trust_remote_code=True,
)
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,
)
set_seed(42)
model = model.cpu()
with torch.no_grad():
for name, p in sorted(model.named_parameters()):
torch.nn.init.normal_(p, 0, 0.2)
print(name, p.shape)
model.save_pretrained(save_folder)
```
</details>
### Printing the model:
<details><summary>Click to expand</summary>
```text
HrmTextForCausalLM(
(model): HrmTextModel(
(embed_tokens): Embedding(65536, 8, padding_idx=5)
(rotary_emb): HrmTextRotaryEmbedding()
(L_module): HrmTextStack(
(layers): ModuleList(
(0-7): 8 x HrmTextDecoderLayer(
(self_attn): HrmTextAttention(
(q_proj): Linear(in_features=8, out_features=128, bias=False)
(k_proj): Linear(in_features=8, out_features=128, bias=False)
(v_proj): Linear(in_features=8, out_features=128, bias=False)
(o_proj): Linear(in_features=128, out_features=8, bias=False)
(gate_proj): Linear(in_features=8, out_features=128, bias=False)
)
(mlp): HrmTextMLP(
(gate_proj): Linear(in_features=8, out_features=64, bias=False)
(up_proj): Linear(in_features=8, out_features=64, bias=False)
(down_proj): Linear(in_features=64, out_features=8, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): HrmTextRMSNorm(eps=1e-06)
(post_attention_layernorm): HrmTextRMSNorm(eps=1e-06)
)
)
(final_norm): HrmTextRMSNorm(eps=1e-06)
)
(H_module): HrmTextStack(
(layers): ModuleList(
(0-7): 8 x HrmTextDecoderLayer(
(self_attn): HrmTextAttention(
(q_proj): Linear(in_features=8, out_features=128, bias=False)
(k_proj): Linear(in_features=8, out_features=128, bias=False)
(v_proj): Linear(in_features=8, out_features=128, bias=False)
(o_proj): Linear(in_features=128, out_features=8, bias=False)
(gate_proj): Linear(in_features=8, out_features=128, bias=False)
)
(mlp): HrmTextMLP(
(gate_proj): Linear(in_features=8, out_features=64, bias=False)
(up_proj): Linear(in_features=8, out_features=64, bias=False)
(down_proj): Linear(in_features=64, out_features=8, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): HrmTextRMSNorm(eps=1e-06)
(post_attention_layernorm): HrmTextRMSNorm(eps=1e-06)
)
)
(final_norm): HrmTextRMSNorm(eps=1e-06)
)
)
(lm_head): Linear(in_features=8, out_features=65536, bias=False)
)
```
</details>
### Test environment:
- torch: 2.10.0+cu128
- transformers: 5.9.0 |