This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from openbmb/MiniCPM5-1B.
| File path | Size |
|---|---|
| model.safetensors | 8.4MB |
Example usage:
from transformers import pipeline
model_id = "tiny-random/minicpm5"
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:
import json
import torch
from huggingface_hub import hf_hub_download
from transformers import (
AutoConfig,
AutoModelForCausalLM,
AutoTokenizer,
GenerationConfig,
pipeline,
set_seed,
)
source_model_id = "openbmb/MiniCPM5-1B"
save_folder = "/tmp/tiny-random/minicpm5"
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": 16,
"intermediate_size": 64,
"num_attention_heads": 16,
"num_key_value_heads": 2,
"head_dim": 32,
"num_hidden_layers": 2,
})
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,
)
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)
Printing the model:
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(130560, 16, padding_idx=1)
(layers): ModuleList(
(0-1): 2 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=16, out_features=512, bias=False)
(k_proj): Linear(in_features=16, out_features=64, bias=False)
(v_proj): Linear(in_features=16, out_features=64, bias=False)
(o_proj): Linear(in_features=512, out_features=16, bias=False)
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=16, out_features=64, bias=False)
(up_proj): Linear(in_features=16, out_features=64, bias=False)
(down_proj): Linear(in_features=64, out_features=16, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm((16,), eps=1e-06)
(post_attention_layernorm): LlamaRMSNorm((16,), eps=1e-06)
)
)
(norm): LlamaRMSNorm((16,), eps=1e-06)
(rotary_emb): LlamaRotaryEmbedding()
)
(lm_head): Linear(in_features=16, out_features=130560, bias=False)
)
Test environment:
- torch: 2.10.0+cu128
- transformers: 5.9.0