Instructions to use analyd/TranR-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use analyd/TranR-14B with Transformers:

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

pipe = pipeline("text-generation", model="analyd/TranR-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("analyd/TranR-14B")
model = AutoModelForCausalLM.from_pretrained("analyd/TranR-14B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use analyd/TranR-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "analyd/TranR-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "analyd/TranR-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/analyd/TranR-14B

SGLang

How to use analyd/TranR-14B 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 "analyd/TranR-14B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "analyd/TranR-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "analyd/TranR-14B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "analyd/TranR-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use analyd/TranR-14B with Docker Model Runner:
```
docker model run hf.co/analyd/TranR-14B
```

TranR-14B / README.md

TranR

Add model files

47e7656 5 months ago

preview code

Raw History Blame Contribute Delete

1.47 kB

metadata

base_model: Qwen/Qwen3-14B
library_name: transformers
pipeline_tag: text-generation

TranR-14B

vLLM

export MODEL_DIR=/path/to/TranR-14B
export PYTHONPATH="$MODEL_DIR/runtime_patches/qwen_rnn:$PYTHONPATH"
export QWEN_RNN_ENABLED=1
export QWEN_RNN_MODEL_DIR="$MODEL_DIR"

python -m vllm.entrypoints.openai.api_server \
  --model "$MODEL_DIR" \
  --served-model-name TranR-14B \
  --tensor-parallel-size 4 \
  --max-model-len 40960 \
  --dtype auto \
  --trust-remote-code \
  --enable-reasoning \
  --reasoning-parser deepseek_r1

Transformers

import os
import sys
import torch

model_dir = "/path/to/TranR-14B"
os.environ["QWEN_RNN_ENABLED"] = "1"
os.environ["QWEN_RNN_MODEL_DIR"] = model_dir
sys.path.insert(0, f"{model_dir}/runtime_patches/qwen_rnn")
import sitecustomize

from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_dir,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

messages = [{"role": "user", "content": "Solve: 1+1="}]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True,
)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=32768)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))