Model Card on HF 🤗: https://huggingface.co/Nicolas-BZRD/pythia-410m-deduped_pubmed_qa_Mistral-7B-Instruct-v0.2_uld_loss
Pythia 410M Deduped Pubmed Qa Mistral 7B Instruct V0.2 Uld Loss Benchmarks
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)
Pythia 410M Deduped Pubmed Qa Mistral 7B Instruct V0.2 Uld Loss Parameters and Internals
| LLM Name | Pythia 410M Deduped Pubmed Qa Mistral 7B Instruct V0.2 Uld Loss |
| Repository 🤗 | https://huggingface.co/Nicolas-BZRD/pythia-410m-deduped_pubmed_qa_Mistral-7B-Instruct-v0.2_uld_loss |
| Model Size | 7b |
| Required VRAM | 1.6 GB |
| Updated | 2025-09-23 |
| Maintainer | Nicolas-BZRD |
| Model Type | gpt_neox |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | GPTNeoXForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.36.2 |
| Vocabulary Size | 50304 |
| Torch Data Type | float32 |
Best Alternatives to Pythia 410M Deduped Pubmed Qa Mistral 7B Instruct V0.2 Uld Loss
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| RedPajama INCITE 7B Instruct | 2K / 13.8 GB | 1933 | 106 |
| ... 7B Instruct V0.2 Text Teacher | 2K / 1.6 GB | 5 | 0 |
| RedPajama 7B Chat Curated | 2K / 13.8 GB | 40 | 2 |
| ...a INCITE Instruct 7B V0.1 GGML | 2K / 4.3 GB | 2 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than Nicolas-BZRD/pythia-410m-deduped_pubmed_qa_Mistral-7B-Instruct-v0.2_uld_loss .
Rank the Pythia 410M Deduped Pubmed Qa Mistral 7B Instruct V0.2 Uld Loss 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? 51611 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124