Qwen Sft La V0.1 is an open-source language model by langgptai. Features: 4b LLM, License: other, HF Score: 47.7, LLM Explorer Score: 0.17, Arc: 46.7, HellaSwag: 69.2, MMLU: 55.6, TruthfulQA: 45.9, WinoGrande: 64.3, GSM8K: 4.6.
Adapter Base model:qwen/qwen1.5-4b-cha... Finetuned Generated from trainer License:other Llama-factory Lora Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/langgptai/Qwen-sft-la-v0.1
Qwen Sft La V0.1 Benchmarks
ARC: 46.67 vs 96.7 (so35)-51.7%
HellaSwag: 69.17 vs 95.3 (gpt4)-27.4%
MMLU: 55.61 vs 88.3 (so35)-37%
TruthfulQA: 45.94 vs 59 (gpt4)-22.1%
WinoGrande: 64.25 vs 87.5 (gpt4)-26.6%
GSM8K: 4.62 vs 96.4 (so35)-95.2%
LLME Score: 0.16623
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)
Qwen Sft La V0.1 Parameters and Internals
| LLM Name | Qwen Sft La V0.1 |
| Repository 🤗 | https://huggingface.co/langgptai/Qwen-sft-la-v0.1 |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 0 GB |
| Updated | 2024-07-16 |
| Maintainer | langgptai |
| Model Files | |
| Model Architecture | Adapter |
| License | other |
| Model Max Length | 32768 |
| Is Biased | none |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|q_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 8 |
| Errors | replace |
Best Alternatives to Qwen Sft La V0.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen Las V0.1 | 0K / 0 GB | 5 | 0 |
| Qwen Sft Ls V0.1 | 0K / 0 GB | 5 | 0 |
| Qwen Qwen1.5 4B 1719895310 | 0K / 0 GB | 5 | 0 |
| Qwen Qwen1.5 4B 1719895024 | 0K / 0 GB | 5 | 0 |
| Qwen Qwen1.5 4B 1719767792 | 0K / 0.1 GB | 4 | 1 |
| Qwen Qwen1.5 4B 1719767451 | 0K / 0 GB | 5 | 0 |
| Qwen Qwen1.5 4B 1719767879 | 0K / 0 GB | 5 | 0 |
| Qwen Qwen1.5 4B 1719767111 | 0K / 0 GB | 5 | 0 |
| Qwen Qwen1.5 4B 1719766837 | 0K / 0 GB | 5 | 0 |
| Qwen Qwen1.5 4B 1719768138 | 0K / 0.1 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than langgptai/Qwen-sft-la-v0.1 .
Rank the Qwen Sft La V0.1 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? 52721 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