Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b Chat Conversational Dataset:arcee-ai/evolkit-20k Dataset:maziyarpanahi/french i... En English Finetuned Fr French Instruct Qwen Qwen2 Qwen2.5 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/MaziyarPanahi/calme-3.1-instruct-3b
Calme 3.1 Instruct 3B Benchmarks
MMLU Pro: 28.41
GPQA: 4.81
MUSR: 7.4
BBH: 27.31
IFEval: 43.36 vs 88 (so35)-50.7%
MATH Lvl 5: 17.75
LLME Score: 0.3291
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)
Calme 3.1 Instruct 3B Parameters and Internals
| LLM Name | Calme 3.1 Instruct 3B |
| Repository 🤗 | https://huggingface.co/MaziyarPanahi/calme-3.1-instruct-3b |
| Model Name | calme-3.1-instruct-3b |
| Model Creator | MaziyarPanahi |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 11 GB |
| Updated | 2025-03-12 |
| Maintainer | MaziyarPanahi |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | fr en |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.45.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Calme 3.1 Instruct 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Saba2 3B | 128K / 6.2 GB | 25 | 0 |
| SmallThinker 3B Preview | 32K / 6.8 GB | 116051 | 389 |
| Qwen2.5 3B Instruct | 32K / 6.2 GB | 687541 | 212 |
| Chirp 01 | 32K / 6.2 GB | 845 | 11 |
| Qwen2.5 3B Model Stock V3.1 | 32K / 6.8 GB | 93 | 3 |
| Qwen2.5 3B Model Stock V3.2 | 32K / 6.8 GB | 61 | 2 |
| Qwen2.5 3B Model Stock V4.1 | 32K / 6.8 GB | 30 | 2 |
| Calme 3.2 Baguette 3B | 32K / 11 GB | 2982 | 1 |
| Q2.5 CodeR1 3B | 32K / 6.2 GB | 226 | 1 |
| Calme 3.1 Baguette 3B | 32K / 6.2 GB | 3089 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than MaziyarPanahi/calme-3.1-instruct-3b .
Rank the Calme 3.1 Instruct 3B 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? 44949 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227