St4 Annealing Sft is an open-source language model by SaketR1. Features: 0.8b LLM, VRAM: 1.5GB, Context: 256K, LLM Explorer Score: 0.32.
Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-0.8b Conversational Endpoints compatible Generated from trainer Qwen3 5 text Region:us Safetensors Sft Trl
Model Card on HF 🤗: https://huggingface.co/SaketR1/st4-annealing-sft
St4 Annealing Sft Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
St4 Annealing Sft Parameters and Internals
| LLM Name | St4 Annealing Sft |
| Repository 🤗 | https://huggingface.co/SaketR1/st4-annealing-sft |
| Model Name | st4-annealing-sft |
| Base Model(s) | |
| Model Size | 0.8b |
| Required VRAM | 1.5 GB |
| Updated | 2026-04-16 |
| Maintainer | SaketR1 |
| Model Type | qwen3_5_text |
| Model Files | |
| Model Architecture | Qwen3_5ForCausalLM |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 5.6.0.dev0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 248320 |
| Errors | replace |
Best Alternatives to St4 Annealing Sft
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...wen3.5 0.8B TW CivicAligned V1 | 256K / 1.5 GB | 113 | 0 |
| St4 Generic Sft | 256K / 1.5 GB | 24 | 0 |
| ...aling Sft Fixed Tokenization 2 | 256K / 1.5 GB | 38 | 0 |
| Qwen3.5 Text 0.8B Bnb 4bit | 256K / 0.8 GB | 347 | 0 |
Rank the St4 Annealing Sft Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52922 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a