Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-72b-in... Chat Conversational En Endpoints compatible Instruct Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/JungZoona/T3Q-Qwen2.5-7B-Instruct-it-8-4-0.0001-cosine-16-16-2epoch
T3Q Qwen2.5 7B Instruct It 8 4 0.0001 Cosine 16 16 2epoch Benchmarks
MMLU Pro: 44.16
GPQA: 8.05
MUSR: 23.7
BBH: 35.42
IFEval: 70.25 vs 88 (so35)-20.2%
MATH Lvl 5: 30.44
LLME Score: 0.32436
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)
T3Q Qwen2.5 7B Instruct It 8 4 0.0001 Cosine 16 16 2epoch Parameters and Internals
| LLM Name | T3Q Qwen2.5 7B Instruct It 8 4 0.0001 Cosine 16 16 2epoch |
| Repository 🤗 | https://huggingface.co/JungZoona/T3Q-Qwen2.5-7B-Instruct-it-8-4-0.0001-cosine-16-16-2epoch |
| Base Model(s) | |
| Model Size | 72b |
| Required VRAM | 15.2 GB |
| Updated | 2025-03-06 |
| Maintainer | JungZoona |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to T3Q Qwen2.5 7B Instruct It 8 4 0.0001 Cosine 16 16 2epoch
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| AceInstruct 72B | 128K / 146 GB | 853 | 18 |
| EVA Qwen2.5 72B V0.2 | 128K / 146 GB | 133 | 21 |
| ...n2.5 72B 2x Instruct TIES V1.0 | 128K / 146.1 GB | 6 | 1 |
| ...2B PT BR Instruct Experimental | 128K / 146 GB | 18 | 0 |
| ... BI Qwen2.5 72B PT BR Instruct | 128K / 146 GB | 5 | 0 |
| ...A Abliterated TIES Qwen2.5 72B | 128K / 146.1 GB | 7 | 1 |
| 72B Qwen2.5 Kunou V1 | 128K / 146 GB | 46 | 22 |
| EVA Qwen2.5 72B V0.1 | 128K / 146 GB | 103 | 17 |
| EVA Qwen2.5 72B V0.0 | 128K / 146 GB | 121 | 5 |
| Qwen2.5 72B Instruct | 32K / 145.5 GB | 99150 | 842 |
Note: green Score (e.g. "73.2") means that the model is better than JungZoona/T3Q-Qwen2.5-7B-Instruct-it-8-4-0.0001-cosine-16-16-2epoch .
Rank the T3Q Qwen2.5 7B Instruct It 8 4 0.0001 Cosine 16 16 2epoch 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? 49901 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124