Instructions to use Raghav-Singhal/pathlang-1p7b-runB-en-first with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Raghav-Singhal/pathlang-1p7b-runB-en-first with Transformers:

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

pipe = pipeline("text-generation", model="Raghav-Singhal/pathlang-1p7b-runB-en-first")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Raghav-Singhal/pathlang-1p7b-runB-en-first")
model = AutoModelForCausalLM.from_pretrained("Raghav-Singhal/pathlang-1p7b-runB-en-first", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Raghav-Singhal/pathlang-1p7b-runB-en-first with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Raghav-Singhal/pathlang-1p7b-runB-en-first"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Raghav-Singhal/pathlang-1p7b-runB-en-first",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Raghav-Singhal/pathlang-1p7b-runB-en-first

SGLang

How to use Raghav-Singhal/pathlang-1p7b-runB-en-first 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 "Raghav-Singhal/pathlang-1p7b-runB-en-first" \
    --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": "Raghav-Singhal/pathlang-1p7b-runB-en-first",
		"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 "Raghav-Singhal/pathlang-1p7b-runB-en-first" \
        --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": "Raghav-Singhal/pathlang-1p7b-runB-en-first",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Raghav-Singhal/pathlang-1p7b-runB-en-first with Docker Model Runner:
```
docker model run hf.co/Raghav-Singhal/pathlang-1p7b-runB-en-first
```

pathlang-1p7b-runB-en-first

A 1.7B-parameter bilingual (English + Chinese) language model, part of a controlled language-ordering study. Three models share the same architecture, initialization, total data diet (50B English + 50B Chinese = 100B tokens), and LR schedule; they differ only in the order in which the two languages are presented during pretraining. This is the English-first run.

Curriculum (this run)

Phase 1 (0-30B): 100% English
Phase 2 (30-90B): 75% Chinese / 25% English
Phase 3 (90-100B): 50/50

The other runs in the study: Raghav-Singhal/pathlang-1p7b-runA-zh-first, Raghav-Singhal/pathlang-1p7b-runB-en-first, Raghav-Singhal/pathlang-1p7b-runC-5050.

Architecture

SmolLM2-1.7B backbone: 24 layers, hidden size 2048, FFN 8192, 32 attention heads
RoPE (base 10000), RMSNorm, SwiGLU, no biases, sequence length 2048
Tokenizer: Qwen3 (multilingual, vocab 151,936)
~2.1B total parameters (with the Qwen3 embedding)

Training

100B tokens: 50B English (DCLM-edu) + 50B Chinese (FineWeb-2 cmn_Hani)
Global batch size 960, sequence length 2048, 50,860 steps
WSD LR schedule (peak 2e-4, 2000 warmup, linear decay over the final 10B tokens), bf16, Adam
Converted from Megatron-LM to HF LlamaForCausalLM format

Held-out validation loss (final checkpoint, 100B tokens)

	English val	Chinese val
this run (English-first)	2.657	2.429

Cross-entropy in nats/token on held-out blocks of the training corpora. The headline finding of the study: each run ends best at the language that dominated its middle (bulk) phase — a recency effect that also holds on an out-of-distribution corpus (HPLT4.0).

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("Raghav-Singhal/pathlang-1p7b-runB-en-first")
tok = AutoTokenizer.from_pretrained("Raghav-Singhal/pathlang-1p7b-runB-en-first")

Note

License is set to other pending confirmation; the training data (DCLM-edu, FineWeb-2) and their respective terms apply. This is a base (non-instruction-tuned) research checkpoint.

Downloads last month: 109

Safetensors

Model size

2B params

Tensor type

BF16