ayushshah

Qwen3-1.7B-UltraChat-SFT

Deploy Dedicated

README

License: apache-2.0

Model Overview

Qwen3-1.7B-UltraChat-SFT has following features:

Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters 1.7B
Number of Paramaters (Non-Embedding): 1.4B
Number of Layers: 28
Number of Attention Heads (GQA): 16 for Q and 8 for KV
Context Length: 32,768

Training

Method: Supervised Fine-Tuning (SFT)
Framework: Unsloth
Fine-Tuning: LoRA
Precision: BF16
Environment: Windows Subsystem for Linux (WSL)
GPU: RTX 4090 24 GB, using FlashAttention 2, xFormers and Triton
Context Length: 2048 tokens
Dataset: UltraChat 200k. Conversations longer than the context window were trimmed before training.

Training Configuration

Table with columns: Parameter, Value
Parameter	Value
Epochs	1
Batch Size	4
Gradient Accumulation	8
Effective Batch Size	32
Optimizer	AdamW Fused
Learning rate	2.5e-4
Embedding Learning Rate	5e-5
LoRA Rank	32
LoRA Alpha	64

LoRA is applied tp q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj and down_proj.

Evaluation

The evaluation was performed using EleutherAI's Language Model Evaluation Harness.

Table with columns: Benchmark, Score
Benchmark	Score
MMLU-Pro	37.91
GSM8K	71.27
HellaSwag	62.28
TruthfulQA mc2	51.62
ARC Challenge	44.97
IFEval strict prompt	33.09

Usage

You can either use Unsloth or transformers.

Unsloth (Recommended)

Install Unsloth following these docs. Install Flash Attention if possible. Check if Triton and xFormers are installed.

python
from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "ayushshah/Qwen3-1.7B-UltraChat-SFT",
    max_seq_length = 2048,
    dtype = "bfloat16",
    load_in_4bit = False,
)

FastLanguageModel.for_inference(model)

prompt = "Explain gradient descent simply."
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize = True,
    add_generation_prompt = True,
    return_tensors = "pt",
).to(model.device)

outputs = model.generate(
    input_ids = inputs,
    max_new_tokens = 2048,
)

input_length = inputs.shape[1]
new_tokens = outputs[0][input_length:]

raw_text = tokenizer.decode(new_tokens, skip_special_tokens=True)
print(raw_text)

transformers

python
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("ayushshah/Qwen3-1.7B-UltraChat-SFT")
model = AutoModelForCausalLM.from_pretrained(
    "ayushshah/Qwen3-1.7B-UltraChat-SFT",
    torch_dtype="auto",
    device_map="auto"
)

prompt = "Explain gradient descent simply."
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize = True,
    add_generation_prompt = True,
    return_tensors = "pt",
).to(model.device)

outputs = model.generate(
    input_ids = inputs["input_ids"],
    max_new_tokens = 2048,
)

input_length = inputs["input_ids"].shape[1]
new_tokens = outputs[0][input_length:]

raw_text = tokenizer.decode(new_tokens, skip_special_tokens=True)
print(raw_text)

Limitations

This model provides the base model with conversational and instruction-following capabilities through supervised fine-tuning. Responses are generally concise and direct, making it a strong foundation for further preference alignment (e.g., DPO, RLHF, PPO) or domain-specific fine-tuning. While suitable for general instruction-following, responses may occasionally lack the depth, natural conversational flow, or helpfulness expected from preference-aligned chat models.

Citation

markdown
@misc{qwen3technicalreport,
      title={Qwen3 Technical Report}, 
      author={Qwen Team},
      year={2025},
      eprint={2505.09388},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.09388}, 
}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

ayushshah

Model Tree

Base

Qwen/Qwen3-1.7B-Base

Fine-tuned

this model

Input Modalities

Text

Output Modalities