ECE PRYMMAL 0.5B FT V5 MUSR Mathis is an open-source language model by matouLeLoup. Features: 0.5b LLM, VRAM: 0.6GB, LLM Explorer Score: 0.17.
Arxiv:1910.09700 Autotrain compatible Conversational Endpoints compatible Lora Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/MEscriva/ECE-PRYMMAL-0.5B-FT-V5-MUSR-Mathis
ECE PRYMMAL 0.5B FT V5 MUSR Mathis Benchmarks
MMLU Pro: 1.72
GPQA: 0.22
MUSR: 8.61
BBH: 3.24
IFEval: 8.66 vs 88 (so35)-90.2%
MATH Lvl 5: 1.06
LLME Score: 0.17428
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)
ECE PRYMMAL 0.5B FT V5 MUSR Mathis Parameters and Internals
| LLM Name | ECE PRYMMAL 0.5B FT V5 MUSR Mathis |
| Repository 🤗 | https://huggingface.co/MEscriva/ECE-PRYMMAL-0.5B-FT-V5-MUSR-Mathis |
| Model Size | 0.5b |
| Required VRAM | 0.6 GB |
| Updated | 2025-01-09 |
| Maintainer | matouLeLoup |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| Model Max Length | 32768 |
| Is Biased | none |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | up_proj|gate_proj|k_proj|v_proj|q_proj|o_proj|down_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
| Errors | replace |
Best Alternatives to ECE PRYMMAL 0.5B FT V5 MUSR Mathis
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2 0.5B Lora Ff Gd Steps 6 | 0K / 1 GB | 6 | 0 |
| ...n2 0.5B Lora Ff Gd Steps 6 Aws | 0K / 1 GB | 6 | 0 |
| Qwen2 0.5B Lora No Ff Aws | 0K / 1 GB | 5 | 0 |
| ... Lora Single Device Ff Testing | 0K / 1 GB | 6 | 0 |
| ...PRYMMAL 0.5B FT V5 MUSR Mathis | 0K / 0.6 GB | 14 | 0 |
| AutoMAD Small | 0K / 0 GB | 5 | 0 |
| Autotrain Uh1gg Kgp3o | 0K / 0.6 GB | 0 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than MEscriva/ECE-PRYMMAL-0.5B-FT-V5-MUSR-Mathis .
Rank the ECE PRYMMAL 0.5B FT V5 MUSR Mathis 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