Instructions to use huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120")

# Load model directly
from transformers import AutoTokenizer, LlamaForCausalLMEagle3

tokenizer = AutoTokenizer.from_pretrained("huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120")
model = LlamaForCausalLMEagle3.from_pretrained("huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120

SGLang

How to use huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120 with Docker Model Runner:
```
docker model run hf.co/huluhuluu/qwen3-1p7b-eagle3-stage2-adapter-w4-epoch-7-step-187120
```

Qwen3-1.7B EAGLE3 Stage2 Adapter W4

This repository contains one SpecForge EAGLE3 draft-model checkpoint for use with Qwen/Qwen3-1.7B. It is a draft model for speculative decoding, not a standalone target language model.

Checkpoint

Field	Value
Source run	`qwen3-1.7b-eagle3-stage2-adapter-w4`
Checkpoint	`epoch_7_step_187120`
Epoch	`7`
Global step	`187120`
Files	`config.json`, `model.safetensors`, `training_state.pt`

Training Parameters

Parameter	Value
Base model	`Qwen/Qwen3-1.7B`
Method	SpecForge EAGLE3 online training with stage2 adapter
Dataset	ShareGPT-format SpecForge training set
Learning rate	`1e-4`
Batch size	`1`
Target batch size	`1`
Epochs configured	`8`
Max length	`2048`
Warmup ratio	`0.015`
Max grad norm	`0.5`
TTT length	`7`
Save interval	`5000`
Eval interval	`5000`
Seed	`0`
TP / DP size	`1 / 4`
Attention backend	`sdpa`
Target model backend	`sglang`
SGLang attention backend	`flashinfer`
Dataset build workers	`64`

Draft Model Configuration

Field	Value
Architecture	`LlamaForCausalLMEagle3`
dtype	`bfloat16`
Hidden size	`2048`
Intermediate size	`6144`
Draft layers	`1`
Attention heads	`16`
KV heads	`8`
Draft vocab size	`32000`
Vocab size	`151936`
Max position embeddings	`40960`
Stage2 adapter	enabled
Stage2 adapter bottleneck	`256`
Stage2 max depth	`7`
Stage2 depth power	`2.0`