🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning. 🦥 Unsloth Zoo will now patch everything to make training faster! Traceback (most recent call last): File "/home/priya/qwen_unsloth/train_qwen38-3S.py", line 53, in model, tokenizer = FastModel.from_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/priya/miniconda3/envs/geocoding/lib/python3.11/site-packages/unsloth/models/loader_utils.py", line 1278, in _wrapper return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/home/priya/miniconda3/envs/geocoding/lib/python3.11/site-packages/unsloth/models/loader.py", line 1360, in from_pretrained new_model_name = get_model_name( ^^^^^^^^^^^^^^^ File "/home/priya/miniconda3/envs/geocoding/lib/python3.11/site-packages/unsloth/models/loader_utils.py", line 301, in get_model_name raise NotImplementedError( NotImplementedError: Unsloth: unsloth/Qwen3.8-27B-unsloth-bnb-4bit is not supported in your current Unsloth version! Please update Unsloth via: pip uninstall unsloth unsloth_zoo -y pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git" pip install --upgrade --no-cache-dir "git+https://github.com/unslothai/unsloth-zoo.git" Starting with the exact official 4-bit model repository. 🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning. 🦥 Unsloth Zoo will now patch everything to make training faster! [unsloth_zoo.log|WARNING]Loading unsloth/Qwen3.8-27B-unsloth-bnb-4bit as text-only; vision/audio towers skipped. Use FastVisionModel for multimodal inputs. ==((====))== Unsloth 2026.8.18: Fast Qwen3_5 patching. Transformers: 5.5.0. \\ /| NVIDIA RTX A6000. Num GPUs = 1. Max memory: 47.527 GB. Platform: Linux. O^O/ \_/ \ Torch: 2.7.1+cu118. CUDA: 8.6. CUDA Toolkit: 11.8. Triton: 3.3.1 \ / Bfloat16 = TRUE. FA [Xformers = 0.0.31. FA2 = False] "-____-" Free license: http://github.com/unslothai/unsloth Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored! The fast path is not available because one of the required library is not installed. Falling back to torch implementation. To install follow https://github.com/fla-org/flash-linear-attention#installation and https://github.com/Dao-AILab/causal-conv1d Loading weights: 0%| | 0/851 [00:00system Objective: Generate a sanskrit verse in Anuṣṭubh meter based on a given meaning or theme while strictly following the metrical (?and rhyme) rules. Rules of Chandas: Syllable Rules: LAGHU vowels: अ, इ, उ, ऋ, ऌ GURU vowels: आ, ई, ऊ, ॠ, ॡ, ए, ऐ, ओ, औ HRASVA vowels: अ, इ, उ, ऋ, ऌ DEERGHA vowels: आ, ई, ऊ, ॠ, ॡ, ए, ऐ, ओ, औ Syllable is marked laghu, guru and hrasva, deergha based on the vowel it contains. Syllable containing anusvāra("ं") or visarga("ः") is always marked as guru. Syllable that is followed by a conjunct consonant (saṁyuktākṣara) is always marked guru. The goal is to generate Sanskrit verse that follows the anushtup meter rules for the given input translation. RULES: Verse Rules: The verse contains 32 syllables/akshara and 4 padas in total. The verse is divided in 2 lines, each containing 16 syllables. Each line is divided into 2 padas (quartets),each containing exactly 8 syllables. The fifth syllable of every pada must be LAGHU or short. The sixth syllable of every pada must be GURU or long. The seventh syllable of the second and the fourth pada must be HRASVA The seventh syllable of the first and third paada must be DEERGHA Language: The generated verse must be in sanskrit in Devanagri script. The Input given is in the hindi. Do NOT include English words, transliteration, labels, or explanations. Output Format: (Output exactly 4 lines, one pada per line. Nothing else.) Example 1: Meaning: इसलिये कामनाओं या भोगोंकी वृद्धिके लिये आग्रह नहीं रखना चाहिये भोगों में जो आसक्ति होती है, वह दुःखरूप ही है धन पाकर भी उसे धर्ममें ही लगा देना चाहिये काम भोगोंको तो सर्वथा त्याग ही देना चाहिये Sanskrit Verse: न कामाननुरुद्ध्येत दुःखं कामेषु वै रतिः प्राप्यार्थमुपयुञ्जीत धर्मं कामान् विसर्जयेत् ॥ Example 2: Meaning: कारण कि यज्ञसे शेष बचे हुए अन्नको खानेवाले श्रेष्ठ पुरुष सब पापोंसे छूटते हैं और जो पापीलोग अपने शरीरपोषणके लिये ही पकाते हैं, वे तो पापको ही खाते हैं ॥ Sanskrit Verse: यज्ञशिष्टाशिनः सन्तो मुच्यन्ते सर्वकिल्बिषैः भुञ्जते ते त्वयं पापा ये पचन्त्यात्मकारणात् ॥ Example 3: Meaning: वहाँसे सेनाविन्दुकी राजधानी देवप्रश्वमें आकर चतु रंगिणी सेनाके साथ शक्तिशाली अर्जुनने यहीं पड़ाव डाला ॥ Sanskrit Verse: स देवप्रस्थमासाद्य सेनाविन्दोः पुरं प्रति बलेन चतुरङ्गेण निवेशमकरोत् प्रभुः ॥<|im_end|> <|im_start|>user Meaning: दिन और रात्रि उनके नेत्र हैं, वे दिव्यस्वरूप हैं वेद उनका अड्ग और श्रुतियाँ आभूषण हैं हविष्य नासिका, खुवा थूथन और सामवेदका गम्भीर घोष ही उनका स्वर है वे महान्‌ हैं ॥ Generate the Sanskrit verse.<|im_end|> <|im_start|>assistant अहोरात्रेक्षणो दिव्यो वेदाड़ः श्रुतिभूषण: आज्यनास: स्त्रुवातुण्डः सामघोषस्वनो महान्‌॥<|im_end|> -------------------------------------------------------------------------------------- -------------------------------------------------------------------------------------- warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead. `logging_dir` is deprecated and will be removed in v5.2. Please set `TENSORBOARD_LOGGING_DIR` instead. [unsloth.trainer|WARNING]Unsloth: packing=True ignored (hybrid linear-attention model). Unsloth: Tokenizing ["text"]: 0%| | 0/23316 [00:00