LLM EXPLORER 59,420 MODELS INDEXED

PARM V1.5 Base QwQ Qwen 2.5 O1 3B VLLM by Pinkstack

By Pinkstack · 84 downloads
HF Repo ↗ Copy URL

PARM V1.5 Base QwQ Qwen 2.5 O1 3B VLLM is an open-source language model by Pinkstack. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, LLM Explorer Score: 0.16.

  Autotrain compatible   Conversational   Endpoints compatible   O1   Pytorch   Qwen2   Region:us   Sft   Sharded   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Pinkstack/PARM-V1.5-base-QwQ-Qwen-2.5-o1-3B-VLLM 

PARM V1.5 Base QwQ Qwen 2.5 O1 3B VLLM Parameters and Internals

LLM NamePARM V1.5 Base QwQ Qwen 2.5 O1 3B VLLM
Repository 🤗https://huggingface.co/Pinkstack/PARM-V1.5-base-QwQ-Qwen-2.5-o1-3B-VLLM 
Model Size3b
Required VRAM6.2 GB
Updated2024-12-31
MaintainerPinkstack
Model Typeqwen2
Model Files  5.0 GB: 1-of-2   1.2 GB: 2-of-2
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.46.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to PARM V1.5 Base QwQ Qwen 2.5 O1 3B VLLM

Best Alternatives
Context / RAM
Downloads
Likes
VibeThinker 3B128K / 6.2 GB52745806
Ulam 1 Small128K / 6.2 GB2024
VibeThinker 3B128K / 6.2 GB3610
...ibeThinker 3B SFT Fable5 Glint128K / 6.2 GB650
Saba1.5 Pro 3B128K / 5.8 GB91
...b Sft Stage1.2 Ss1 Expert Math128K / 15.1 GB120
... Formattedtext Math Wiki Merge128K / 15.1 GB120
...2 Ss1 Expert Fictional Lyrical128K / 15.1 GB60
...tage1.1 Ss1 With Math.no Issue128K / 15.1 GB60
...ware Howto Formattedtext Merge128K / 15.1 GB50
Note: green Score (e.g. "73.2") means that the model is better than Pinkstack/PARM-V1.5-base-QwQ-Qwen-2.5-o1-3B-VLLM.