Instructions to use dataslab/DSLM-LST-35B-A3B-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dataslab/DSLM-LST-35B-A3B-GPTQ-Int4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="dataslab/DSLM-LST-35B-A3B-GPTQ-Int4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("dataslab/DSLM-LST-35B-A3B-GPTQ-Int4")
model = AutoModelForMultimodalLM.from_pretrained("dataslab/DSLM-LST-35B-A3B-GPTQ-Int4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dataslab/DSLM-LST-35B-A3B-GPTQ-Int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dataslab/DSLM-LST-35B-A3B-GPTQ-Int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dataslab/DSLM-LST-35B-A3B-GPTQ-Int4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/dataslab/DSLM-LST-35B-A3B-GPTQ-Int4

SGLang

How to use dataslab/DSLM-LST-35B-A3B-GPTQ-Int4 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 "dataslab/DSLM-LST-35B-A3B-GPTQ-Int4" \
    --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": "dataslab/DSLM-LST-35B-A3B-GPTQ-Int4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "dataslab/DSLM-LST-35B-A3B-GPTQ-Int4" \
        --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": "dataslab/DSLM-LST-35B-A3B-GPTQ-Int4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use dataslab/DSLM-LST-35B-A3B-GPTQ-Int4 with Docker Model Runner:
```
docker model run hf.co/dataslab/DSLM-LST-35B-A3B-GPTQ-Int4
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

DSLM-LST-35B-A3B-GPTQ-Int4

DSLM-LST-35B-A3B-GPTQ-Int4 is a GPTQ INT4 quantization of a Qwen/Qwen3.5-35B-A3B model refined with our in-house Language Selection Tuning (LST) technique.

The pipeline is: Qwen/Qwen3.5-35B-A3B → LST tuning (output-head centric) → GPTQ INT4 quantization (gptqmodel). The LST adjustment is intentionally minimal in scope — most of the network, including the entire vision tower and all expert weights, is preserved — and the resulting model is then post-training quantized to 4-bit for memory- and throughput-efficient serving.

The architecture is Qwen3_5MoeForConditionalGeneration: a composite multimodal vision-language model with a MoE text backbone (256 experts, top-8 routing), a linear-attention + full-attention 4:1 hybrid layout, and a 27-block vision tower.

Why LST?

Multilingual LLMs trained on heavily skewed corpora (e.g., Qwen on Chinese-rich data) tend to leak the dominant training language regardless of prompt language — a phenomenon known as language confusion. For Korean users, Chinese characters sometimes appear in the middle of an otherwise-Korean answer, hurting readability and trust.

Language Selection Tuning (LST) addresses this in a learning-based manner. Unlike post-hoc decoding tricks (vocabulary masking, banned-token lists), LST adjusts the model's internal language-selection behavior. (The exact algorithm and training configuration are proprietary and not disclosed in this release.)

Key Properties

Minimal footprint. LST tuning modifies essentially only the output head; the tokenizer, chat template, vision tower, MoE experts, and attention weights are preserved from the base model.
Selectivity preserved. When the user explicitly asks for Chinese, the model still produces fluent Chinese — this is not blanket suppression.
4-bit efficient. GPTQ INT4 shrinks the ~70 GB bf16 model to ~22 GB while keeping reasoning performance close to DSLM-LST-35B-A3B (see Benchmarks).

Quantization

Quantizer: gptqmodel 7.0.0
Method: GPTQ, bits=4, group_size=32, sym=True, desc_act=False, pack=int32
Quantized (30,970 linear layers): MoE experts (gate/up/down) and attention / linear-attention projections
Kept in bf16 (not quantized): lm_head, embed_tokens, the entire vision tower, all norms, router gate (mlp.gate), shared_expert_gate, and the SSM parameters (A_log / dt_bias / conv1d)
Per-module GPTQ reconstruction error is small (median ≈ 2.5e-6, max ≈ 1.1e-3; 1.03 % of modules fell back to RTN per the configured outlier threshold).

Requirements

transformers >= 5.9 — required for the qwen3_5_moe architecture, the modern tokenizer backend, the consolidated processor format, and GPTQ loading.
vLLM serving: the quantization is auto-detected and served via gptq_marlin. Do not pass --quantization moe_wna16 — with group_size=32 it conflicts with the vLLM moe_wna16 kernel's BLOCK_SIZE_K constraint and fails at startup. (Re-quantizing at group_size=128 would enable moe_wna16.)

Quickstart (vLLM, recommended)

vllm serve dataslab/DSLM-LST-35B-A3B-GPTQ-Int4 \
    --tensor-parallel-size 2 \
    --port 8000 \
    --gpu-memory-utilization 0.90 \
    --reasoning-parser qwen3        # exposes <think> trace via OpenAI API
    # --quantization is auto-detected (gptq_marlin); do NOT set moe_wna16
    # --max-model-len 16384         # cap context to shrink KV cache (default: 262,144)

Use with transformers

Non-Thinking mode (recommended for fast chat)

import torch
from transformers import AutoTokenizer, AutoModelForImageTextToText

REPO = "dataslab/DSLM-LST-35B-A3B-GPTQ-Int4"

tokenizer = AutoTokenizer.from_pretrained(REPO)
model = AutoModelForImageTextToText.from_pretrained(
    REPO,
    dtype=torch.bfloat16,   # non-quantized layers stay bf16; INT4 weights are dequantized on the fly
    device_map="auto",
)

messages = [
    {"role": "user", "content": "한반도 주변에 가장 흔한 점토광물은?"},
]

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

out = model.generate(**inputs, max_new_tokens=256)
text = tokenizer.decode(out[0][inputs.input_ids.shape[-1]:],
                       skip_special_tokens=True)
print(text)

Thinking mode (recommended for complex reasoning)

Either use thinking_budget (e.g., vLLM's --reasoning-parser qwen3) or give max_new_tokens enough headroom (e.g., 8,192 + 256 = 8,448). Caveat: without a thinking_budget cap, a too-small max_new_tokens can be fully consumed inside <think> and the answer never gets emitted.

# ... tokenizer / model loaded as above ...

THINKING_BUDGET = 8192   # max tokens inside <think>
ANSWER_TOKENS   = 256    # tokens after </think>

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

out = model.generate(**inputs, max_new_tokens=THINKING_BUDGET + ANSWER_TOKENS)
text = tokenizer.decode(out[0][inputs.input_ids.shape[-1]:],
                       skip_special_tokens=True)
print(text)

Why AutoModelForImageTextToText? The declared architecture Qwen3_5MoeForConditionalGeneration is a composite class wrapping both the text decoder and the vision tower. Loading via AutoModelForCausalLM works for text-only inference but strips the vision submodule and may produce a config that downstream tools (e.g., vLLM) reject. For a pure text causal-LM handle, use model.language_model after loading.

Benchmark Results

The DSLM-LST-35B-A3B-GPTQ-Int4 column refers to this model, while DSLM-LST-35B-A3B is the original LST model from which it was quantized.

Evaluation Metrics

(1) Selectivity

Refusal rate on explicit Chinese requests — the fraction of cases where the model fails to produce Chinese even though the user explicitly asked for it. Lower is better (respects user intent).

Lower better (~0): produces Chinese when asked (respects user intent).
Higher worse (~1): refuses Chinese even when asked (blanket suppression).

Metric	Benchmark Dataset
`chin_refusal` ↓	In-house 1,000-prompt Chinese elicitation set (e.g., `How do you say '사랑' in Chinese?` or the Python + Chinese-comment prompt)

(2) Chinese-leak suppression

Korean prompts → Korean answers expected; any Chinese token leaked into the answer is a failure. Metric is the clean-Korean response ratio.

Higher better (~1): Korean answers stay fully Korean (no Chinese tokens leaked).
Lower worse (~0): Chinese tokens leak into otherwise-Korean answers.

Metric	Benchmark Dataset
`chin_cs` ↑	KMMLU Computer Science subjects (free-form Korean generation)
`chin_ie` ↑	KMMLU Industrial Engineering subjects (free-form Korean generation)
`chin_total` ↑	KMMLU (free-form Korean generation)

(3) Reasoning / task performance

Metric	Benchmark Dataset
`acc_cs` ↑	KMMLU Computer Science subjects (multiple-choice log-likelihood comparison)
`acc_ie` ↑	KMMLU Industrial Engineering subjects (multiple-choice log-likelihood comparison)
`acc_total` ↑	KMMLU (multiple-choice log-likelihood comparison)
`HumanEval` ↑	HumanEval (pass@1)
`GSM8K` ↑	GSM8K (exact-match accuracy)

Chinese Suppression (Thinking mode)

Evaluated with enable_thinking=True. The DSLM-LST-35B-A3B-GPTQ-Int4 column is calibrated with thinking enabled.

Metric	Qwen3.5-35B-A3B (base)	DSLM-LST-35B-A3B	DSLM-LST-35B-A3B-GPTQ-Int4
(1) Selectivity
chin_refusal ↓	0.005	0.030	0.039
(2) Chinese-leak suppression
chin_cs ↑	0.989	0.998	0.999
chin_ie ↑	0.983	0.994	0.993
chin_total ↑	0.9754	0.9901	0.9895
(3) Reasoning / Task performance
acc_cs ↑	0.869	0.869	0.865
acc_ie ↑	0.622	0.622	0.602
acc_total ↑	0.6411	0.6411	0.6340
HumanEval ↑	0.7683	0.7378	0.7561
GSM8K ↑	0.8347	0.8347	0.8810 🌟

INT4 quantization keeps Chinese-leak suppression (chin_total 0.9895, vs DSLM-LST-35B-A3B's 0.9901) and selectivity (chin_refusal 0.039) on par with DSLM-LST-35B-A3B, with KMMLU accuracy within ~0.7 pt and HumanEval/GSM8K comparable to — or above — DSLM-LST-35B-A3B. (KMMLU acc_* for the INT4 model were measured via the vLLM backend; on identical weights the HF↔vLLM backend difference is ≤0.05 pt, so the ~0.7 pt acc gap is essentially the quantization effect.)

Example Outputs

Asked in Korean which method counts living microorganisms, Qwen3.5-35B-A3B leaks 24 Chinese tokens (平板計數法, 集落形成) across its chain-of-thought and answer. DSLM-LST-35B-A3B-GPTQ-Int4 answers the same prompt entirely in Korean (0 Chinese tokens) — the leak suppression survives INT4 quantization.

Domain-wise Leakage Comparisons

Computer Science

Prompt: BIOS Setup의 기본기능으로 잘못된 것은?

Qwen3.5-35B-A3B (leaks 出荷) DSLM-LST-35B-A3B-GPTQ-Int4 (clean Korean)

Qwen3.5-35B-A3B (leaks `出荷`)	DSLM-LST-35B-A3B-GPTQ-Int4 (clean Korean)
보통 컴퓨터 자격증 시험 (정보처리기사, 컴퓨터활용능력 등) 에서 출제되는 BIOS Setup 의 기본기능으로 잘못된 것에 대한 정답은 일반적으로 다음과 같습니다. 정답: 운영체제 설치 (OS Installation) BIOS Setup 의 올바른 기능: • 시스템 시간 및 날짜 설정 • 부팅 장치 순서 설정 (Boot Order) • 보안 설정 / 전원 관리 설정 • CMOS 초기화: 설정을 공장出荷 상태로 되돌립니다.	일반적인 컴퓨터 자격증 시험 (컴퓨터활용능력, 정보처리기사 등) 에서 자주 출제되는 BIOS Setup 의 기본 기능과 오답을 정리해 드립니다. BIOS Setup 의 실제 기본 기능 (올바른 것) 1. 시스템 시간 및 날짜 설정 2. 부팅 장치 순서 변경 (Boot Order) 3. 하드웨어 정보 확인 5. 시스템 보안 설정: BIOS 비밀번호, 부팅 비밀번호 설정. …

보통 컴퓨터 자격증 시험 (정보처리기사, 컴퓨터활용능력 등) 에서 출제되는 BIOS Setup 의 기본기능으로 잘못된 것에 대한 정답은 일반적으로 다음과 같습니다.

정답: 운영체제 설치 (OS Installation)

BIOS Setup 의 올바른 기능:
• 시스템 시간 및 날짜 설정
• 부팅 장치 순서 설정 (Boot Order)
• 보안 설정 / 전원 관리 설정
• CMOS 초기화: 설정을 공장出荷 상태로 되돌립니다.

일반적인 컴퓨터 자격증 시험 (컴퓨터활용능력, 정보처리기사 등) 에서 자주 출제되는 BIOS Setup 의 기본 기능과 오답을 정리해 드립니다.

BIOS Setup 의 실제 기본 기능 (올바른 것)
1. 시스템 시간 및 날짜 설정
2. 부팅 장치 순서 변경 (Boot Order)
3. 하드웨어 정보 확인
5. 시스템 보안 설정: BIOS 비밀번호, 부팅 비밀번호 설정. …

Industrial Engineering

Prompt: 머시닝센터에서 공작물 가공시 주의해야 할 사항으로 올바른 것은?

Qwen3.5-35B-A3B (leaks 卷入) DSLM-LST-35B-A3B-GPTQ-Int4 (clean Korean)

Qwen3.5-35B-A3B (leaks `卷入`)	DSLM-LST-35B-A3B-GPTQ-Int4 (clean Korean)
… 머시닝센터 (CNC) 가공 시 가장 중요하게 고려해야 할 올바른 주의사항들을 정리해 드립니다. 2. 안전 수칙 (보호구) • 올바른 사항: 안전 고글을 착용하고, 회전하는 스플라인 (스핀들) 근처에서는 장갑을 착용하지 않아야 합니다. • 이유: 장갑을 끼고 회전체 근처에서 작업할 경우 장갑이 걸려 손이卷入 (감김) 될 위험이 매우 큽니다.	… 머시닝센터 (CNC) 에서 공작물 가공 시 가장 중요하게 지켜야 할 올바른 주의사항들을 정리해 드립니다. 1. 안전 수칙 (가장 중요) • 장갑 착용 금지: 회전하는 척 (Chucks) 이나 공구 (Tool) 에 접근할 때는 절대 장갑을 착용하지 않아야 합니다. (장갑이 걸려서 손이 끼일 수 있음) • 안전장구 착용: 안전고글, 안전화, 귀마개 등을 반드시 착용해야 합니다. …

… 머시닝센터 (CNC) 가공 시 가장 중요하게 고려해야 할 올바른 주의사항들을 정리해 드립니다.

2. 안전 수칙 (보호구)
• 올바른 사항: 안전 고글을 착용하고, 회전하는 스플라인 (스핀들) 근처에서는 장갑을 착용하지 않아야 합니다.
• 이유: 장갑을 끼고 회전체 근처에서 작업할 경우 장갑이 걸려 손이卷入 (감김) 될 위험이 매우 큽니다.

… 머시닝센터 (CNC) 에서 공작물 가공 시 가장 중요하게 지켜야 할 올바른 주의사항들을 정리해 드립니다.

1. 안전 수칙 (가장 중요)
• 장갑 착용 금지: 회전하는 척 (Chucks) 이나 공구 (Tool) 에 접근할 때는 절대 장갑을 착용하지 않아야 합니다. (장갑이 걸려서 손이 끼일 수 있음)
• 안전장구 착용: 안전고글, 안전화, 귀마개 등을 반드시 착용해야 합니다. …

Law

Prompt: 경비조사업무의 과정으로 옳지 않은 것은?

Qwen3.5-35B-A3B (leaks 它们是) DSLM-LST-35B-A3B-GPTQ-Int4 (clean Korean)

Qwen3.5-35B-A3B (leaks `它们是`)	DSLM-LST-35B-A3B-GPTQ-Int4 (clean Korean)
… 일반적으로 '경비조사업무의 과정'과 관련하여 옳지 않은 것 (오답)으로 가장 많이 나오는 내용은 경비원의 법적 권한 (체포권, 수사권, 제재권 등)과 관련된 내용입니다. 경비조사업무의 올바른 과정 (정답에 해당하는 내용) … 만약 선택지에 이 내용들이 있다면它们是 옳은 것입니다. 1. 사전 준비 (계약 및 현장 조사) 2. 인력 배치 및 교육 3. 경비 수행 (순찰 및 출입 통제) …	… 경비업법 및 경비조사업무의 표준 프로세스에 기반하여, 시험 문제에서 자주 출제되는 '옳지 않은 것'의 유형을 정리해 드릴 수 있습니다. 경비조사업무의 올바른 과정 (표준) 1. 계약 체결: 의뢰인 (고객) 과 경비업체 간 계약 2. 인원 선정 및 교육: 경비원 선발 및 직무/법률 교육 (필수) 3. 배치 (배정): 현장에 경비원 배치 …

… 일반적으로 '경비조사업무의 과정'과 관련하여 옳지 않은 것 (오답)으로 가장 많이 나오는 내용은 경비원의 법적 권한 (체포권, 수사권, 제재권 등)과 관련된 내용입니다.

경비조사업무의 올바른 과정 (정답에 해당하는 내용)
… 만약 선택지에 이 내용들이 있다면它们是 옳은 것입니다.
1. 사전 준비 (계약 및 현장 조사)
2. 인력 배치 및 교육
3. 경비 수행 (순찰 및 출입 통제) …

… 경비업법 및 경비조사업무의 표준 프로세스에 기반하여, 시험 문제에서 자주 출제되는 '옳지 않은 것'의 유형을 정리해 드릴 수 있습니다.

경비조사업무의 올바른 과정 (표준)
1. 계약 체결: 의뢰인 (고객) 과 경비업체 간 계약
2. 인원 선정 및 교육: 경비원 선발 및 직무/법률 교육 (필수)
3. 배치 (배정): 현장에 경비원 배치 …

Cross-lingual Selectivity

When the user explicitly asks for Chinese, DSLM-LST-35B-A3B-GPTQ-Int4 readily produces it. The previous examples showed the model avoiding unwanted Chinese inside an otherwise-Korean answer; the example below shows it emitting Chinese fluently — in both code comments and prose — when the user's instruction calls for it. Selectivity survives INT4 quantization.

Prompt: 이진 트리를 중위 순회하는 파이썬 함수를 작성해주세요. 설명은 중국어로 해주세요.

DSLM-LST-35B-A3B-GPTQ-Int4 (code with Chinese comments + Chinese explanation):

from typing import List, Optional

# 二叉树节点定义
class TreeNode:
    def __init__(self, val=0, left=None, right=None):
        self.val = val
        self.left = left
        self.right = right

def inorder_traversal(root: Optional[TreeNode]) -> List[int]:
    """
    二叉树的中序遍历 (Inorder Traversal)
    遍历顺序：左子树 -> 根节点 -> 右子树
    """
    result = []

    def traverse(node: Optional[TreeNode]):
        if node is None:
            return
        traverse(node.left)     # 1. 递归遍历左子树
        result.append(node.val) # 2. 访问根节点
        traverse(node.right)    # 3. 递归遍历右子树

    traverse(root)
    return result

**代码说明 (Chinese explanation):**
1. 算法原理：中序遍历（Inorder Traversal）遵循「左 (Left) -> 根 (Root) -> 右 (Right)」的访问顺序。
2. 复杂度分析：时间复杂度 O(n)，空间复杂度 O(h)（h 为树高，由递归调用栈深度决定）。
3. 适用场景：对二叉搜索树 (BST) 进行中序遍历，得到的结果是有序的（从小到大）。

Thinking-trace Suppression

The base model's <think> block leaks Chinese even more severely than its final answer: once the reasoning gets stuck, it slips into Chinese and loops on its own hypotheses. DSLM-LST-35B-A3B-GPTQ-Int4 suppresses that leakage inside the thinking block too — and here it also stays on topic where the base model drifts off it.

The prompt below is a fire-safety / chemistry question comparing white phosphorus (황린) and red phosphorus (적린). The base model fails to recognize the topic, convinces itself the terms are Chinese herbal-medicine names (황련 黃連, 적련 赤蓮), and spirals through a Chinese-leaking self-doubt loop — ending in a confident but wrong answer about traditional medicine. DSLM-LST-35B-A3B-GPTQ-Int4 identifies the phosphorus allotropes correctly, reasons in clean English/Korean, and returns an accurate comparison.

Prompt: 황린과 적린을 비교 설명한 것이다. 옳은 것은?

Chinese-character counts (thinking budget = 8,192):

Metric	Qwen3.5-35B-A3B	DSLM-LST-35B-A3B-GPTQ-Int4
`<think>` block, Chinese characters	672	0
`<answer>` block, Chinese characters	leaks `黃連` / `赤蓮` (14 chars)	0 (clean Korean)
`<think>` length / "Wait…" self-doubt events	26,068 chars / 165 (loops in Chinese)	5,489 chars / 2 (English/Korean)
Topic identified	❌ misread as herbal medicine	✅ phosphorus allotropes (correct)

Qwen3.5-35B-A3B <think> block (loops through Chinese herb hypotheses):

Here's a thinking process that leads to the suggested answer:

1.  **Analyze the Request:**
    *   **Topic:** Comparison between "Hwangrin" (황린) and "Jeokrin" (적린).
    *   **Context:** These terms are likely related to Korean traditional medicine
        (Hanbang) ...
    *   **Hypothesis 3 (Most Likely):** It refers to "Hwangryeon" (黃連 - Coptis
        chinensis) and "Jeokryeon" (赤蓮)? No.
        ...
        *   *Wait, could it be "Hwangryeon" (黃連) and "Jeokryeon" (赤蓮)?*
        *   *Wait, could it be "Hwangjin" (黃精) and "Jeokjin"?*
        *   *Wait, is it possible the user means "Hwangryeon" (黃連) and "Jeokryeon" (赤蓮) ...?*
        *   *Wait, is it possible the user means "Hwanggi" (黃耆) and "Jeokgi" (赤耆)?*
        ... (165 such "Wait…" hypotheses, leaking 672 Chinese characters) ...

The base model never recovers the actual topic. Each Wait, could it be …? re-emits another Chinese herb name (黃連, 赤蓮, 黃精, 黃耆), and that Chinese leak carries straight into the user-facing answer.

Qwen3.5-35B-A3B Final answer (wrong topic + Chinese leak):

질문하신 **'황린 (黃林)'과 '적린 (赤林)'**은 한의학이나 약재학에서 일반적으로 통용되는
표준 명칭이 아닙니다.

대부분의 경우, 이는 **'황련 (黃連, Coptis chinensis)'**과 **'적련 (赤蓮, Nelumbo
nucifera 등)'**의 오타이거나 ...

### 1. 한약재 '황련 (黃連)'과 '적련 (赤蓮)'의 비교 (가장 유력)
*   **황련 (黃連):** 성질: 한약재 (계통: 청열약). ...

DSLM-LST-35B-A3B-GPTQ-Int4 <think> block (correct topic, clean English/Korean — 0 Chinese):

Here's a thinking process that leads to the suggested answer:

1.  **Analyze the Request:**
    *   **Topic:** Comparison between "Hwang-in" (Yellow Phosphorus, 황린) and
        "Red Phosphorus" (적린).
    *   **Context:** This sounds like a chemistry question, likely from a high school
        or college entrance exam context in Korea.

2.  **Recall Key Facts about Phosphorus Allotropes:**
    *   **Yellow Phosphorus (White Phosphorus):** Formula $P_4$; highly toxic;
        spontaneously ignites in air; soluble in $CS_2$; stored under water.
    *   **Red Phosphorus:** Polymerized structure; much less toxic; less reactive;
        insoluble in water and $CS_2$; more stable.

    *   *Self-Correction:* Wait, "Hwang-in" (Yellow Phosphorus) is often referred to
        as "White Phosphorus" (백린) in strict chemical terms ...
    *Let's write the response.*

DSLM-LST-35B-A3B-GPTQ-Int4 still second-guesses itself ("Wait, …"), but it correctly anchors on phosphorus chemistry from the first line, reasons entirely in English/Korean, and the trace terminates naturally after ~5,500 characters (0 Chinese) instead of looping to the budget limit.

DSLM-LST-35B-A3B-GPTQ-Int4 Final answer (correct, useful, clean Korean):

황린 (백린) 과 적린의 일반적인 비교 특징 중
**화학 시험에서 자주 정답으로 나오는 내용**을 정리해 드립니다.

### 황린 (백린) vs 적린 비교 요약
| 특징     | 황린 (White Phosphorus)        | 적린 (Red Phosphorus)        |
| :------- | :----------------------------- | :--------------------------- |
| 분자 구조 | P₄ (정사면체 구조)              | 고분자 구조 (연쇄형)          |
| 안정성   | 불안정함                        | 안정함 (황린보다 안정)        |
| 반응성   | 매우 활발함 (공기 중 자연발화)   | 상대적으로 덜 활발함          |
| 용해도   | 이황화탄소(CS₂)에 녹음           | 이황화탄소(CS₂)에 녹지 않음   |
| 독성     | 강한 독성                       | 독성이 적음                  |
| 저장법   | 물 속에 저장 (공기 차단)         | 밀폐 용기에 저장             |

On the same prompt, the base model leaks Chinese into both its reasoning trace and its final answer and answers the wrong question (Chinese herbal medicine). DSLM-LST-35B-A3B-GPTQ-Int4 keeps the entire trace in clean English/Korean, correctly identifies the phosphorus topic, and returns an accurate, useful Korean answer (0 Chinese characters) — even after INT4 quantization.

Limitations

Not an instruction-tuned chat model. The LST adjustment scope is minimal, so conversational behavior, instruction-following, and reasoning patterns are inherited from the base model — only unintended Chinese-token leakage is mitigated.
Degraded Chinese generation. Tasks that require Chinese output (Chinese translation, Chinese code comments, bilingual Q&A) will see lower quality; use the base Qwen3.5-35B-A3B for those.
INT4 quantization loss. A small accuracy reduction (~0.7 pt on KMMLU) is expected relative to DSLM-LST-35B-A3B; quality-sensitive workloads may prefer the unquantized DSLM-LST-35B-A3B.
Multimodal not re-benchmarked. The vision tower is kept in bf16 (unquantized) and unchanged, so multimodal behavior should be unaffected, but the vision pipeline was not separately re-benchmarked for this release.

License

This model is not available for public download. For a publicly available alternative, see DSLM-LST-9B. For commercial or research access to this model, please contact us.