Alignment-handbook Autotrain compatible Base model:finetune:tinyllama/... Base model:tinyllama/tinyllama... Conversational Dataset:jan-hq/bagel sft binar... Dataset:jan-hq/dolphin binariz... Dataset:jan-hq/openhermes bina... Endpoints compatible Generated from trainer Mistral Region:us Safetensors Sft Sharded Tensorflow Trl
Model Card on HF 🤗: https://huggingface.co/jan-hq/stealth-rag-v1.1
Stealth Rag V1.1 Benchmarks
ARC: 62.12 vs 96.7 (so35)-35.8%
HellaSwag: 83.83 vs 95.3 (gpt4)-12%
MMLU: 64.06 vs 88.3 (so35)-27.5%
TruthfulQA: 49.64 vs 59 (gpt4)-15.9%
WinoGrande: 79.32 vs 87.5 (gpt4)-9.3%
GSM8K: 67.78 vs 96.4 (so35)-29.7%
LLME Score: 0.14693
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)
Stealth Rag V1.1 Parameters and Internals
| LLM Name | Stealth Rag V1.1 |
| Repository 🤗 | https://huggingface.co/jan-hq/stealth-rag-v1.1 |
| Base Model(s) | |
| Model Size | 1.1b |
| Required VRAM | 14.4 GB |
| Updated | 2025-09-23 |
| Maintainer | jan-hq |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Stealth Rag V1.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Hare 1.1B Base 0.5v | 32K / 2.4 GB | 47 | 0 |
| TinyLlama Mistral | 32K / 4.4 GB | 11 | 2 |
| Hare 1.1B Base | 32K / 2.2 GB | 81 | 7 |
| Hare 1.1B Chat | 32K / 2.2 GB | 37 | 0 |
| Hare 1.1B Tool | 32K / 2.2 GB | 10 | 1 |
| Dipsmol | 32K / 2.2 GB | 5 | 0 |
| Mistral 1.1B Testing | 32K / 4.4 GB | 6 | 1 |
| Stealth Rag V1 E1 | 32K / 14.4 GB | 6 | 1 |
| Mallam 1.1B 4096 | 32K / 2.2 GB | 76 | 9 |
| ...Mistral En 1.1B Coder Wizardlm | 4K / 2.4 GB | 4 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than jan-hq/stealth-rag-v1.1 .
Rank the Stealth Rag V1.1 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124