This tiny model is for debugging. It is randomly initialized with the config adapted from zai-org/GLM-4.5.
Note: The transformers implementation does not have multi-token prediction (MTP) support. So you might see some "weights not loaded" warnings. This is expected.
Example usage:
- vLLM
model_id=yujiepan/glm-4.5-tiny-random
vllm serve $model_id \
--tensor-parallel-size 1 \
--tool-call-parser glm4_moe \
--reasoning-parser glm4_moe \
--enable-auto-tool-choice
- SGLang
# Multi-token prediction is supported
model_id=yujiepan/glm-4.5-tiny-random
python3 -m sglang.launch_server \
--model-path $model_id \
--tp-size 1 \
--cuda-graph-max-bs 4 \
--tool-call-parser glm45 \
--reasoning-parser glm45 \
--speculative-algorithm EAGLE \
--speculative-num-steps 3 \
--speculative-eagle-topk 1 \
--speculative-num-draft-tokens 4 \
--mem-fraction-static 0.4
- Transformers
from transformers import pipeline
model_id = "yujiepan/glm-4.5-tiny-random"
pipe = pipeline(
"text-generation", model=model_id, device="cuda",
trust_remote_code=True, max_new_tokens=20,
)
print(pipe("Hello World!"))
Codes to create this repo:
from copy import deepcopy
import torch
import torch.nn as nn
from transformers import (
AutoConfig,
AutoModelForCausalLM,
AutoTokenizer,
GenerationConfig,
pipeline,
set_seed,
)
from transformers.models.glm4_moe.modeling_glm4_moe import Glm4MoeDecoderLayer, Glm4MoeRMSNorm
source_model_id = "zai-org/GLM-4.5"
save_folder = "/tmp/yujiepan/glm-4.5-tiny-random"
tokenizer = AutoTokenizer.from_pretrained(
source_model_id, trust_remote_code=True,
)
tokenizer.save_pretrained(save_folder)
config = AutoConfig.from_pretrained(
source_model_id, trust_remote_code=True,
)
config.hidden_size = 16
config.head_dim = 64
config.intermediate_size = 64
config.num_attention_heads = 4
config.num_hidden_layers = 2 # 1 dense, 1 moe
config.num_key_value_heads = 2
config.moe_intermediate_size = 64
config.n_routed_experts = 16
config.n_shared_experts = 1
config.first_k_dense_replace = 1
config.num_experts_per_tok = 8
config.num_nextn_predict_layers = 1 # after layer 0 and 1, there will be a another MTP layer
config.tie_word_embeddings = True
torch.set_default_dtype(torch.bfloat16)
model = AutoModelForCausalLM.from_config(
config,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
)
class SharedHead(nn.Module):
def __init__(self, config) -> None:
super().__init__()
self.norm = Glm4MoeRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
# self.head = deepcopy(model.get_output_embeddings())
class Glm4MoeDecoderMTP(Glm4MoeDecoderLayer):
def __init__(self, config, layer_idx):
super().__init__(config, layer_idx=layer_idx)
self.enorm = Glm4MoeRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
self.hnorm = Glm4MoeRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
self.eh_proj = nn.Linear(config.hidden_size * 2, config.hidden_size, bias=False)
self.shared_head = SharedHead(config=config)
# self.embed_tokens = deepcopy(model.get_input_embeddings())
last_extra_layer = Glm4MoeDecoderMTP(config, layer_idx=config.num_hidden_layers)
model.model.layers.append(last_extra_layer)
model.generation_config = GenerationConfig.from_pretrained(
source_model_id, trust_remote_code=True,
)
set_seed(42)
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)