Vikhr 7B Instruct Merged 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)
Vikhr 7B Instruct Merged Parameters and Internals
| LLM Name | Vikhr 7B Instruct Merged |
| Repository 🤗 | https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_merged |
| Model Size | 7b |
| Required VRAM | 14.6 GB |
| Updated | 2024-09-07 |
| Maintainer | Vikhrmodels |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.34.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 40000 |
| Torch Data Type | float16 |
Best Alternatives to Vikhr 7B Instruct Merged
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 2 7B 32K Instruct | 32K / 13.5 GB | 12856 | 160 |
| Qwen2 7B Instruct Llama | 32K / 15.2 GB | 4 | 2 |
| Qwen2 7B Instruct Mistral | 32K / 15.2 GB | 5 | 1 |
| AIRIC The Mistral | 32K / 14.4 GB | 675 | 7 |
| ...ls Vikhr 7B Instruct 0.4 4bits | 32K / 5.2 GB | 5 | 0 |
| Vikhr 7B Instruct 0.3 | 32K / 14.6 GB | 39 | 4 |
| ... Samantha Philosopher 7B Slerp | 32K / 13.4 GB | 4 | 2 |
| Clinical Ehr Prototype 0.1 | 32K / 14.4 GB | 14 | 2 |
| ...stral 7B Instruct V0.1 Sharded | 32K / 14.4 GB | 1544 | 13 |
| ... Llama2 7B 32K Instructions V2 | 32K / 13.5 GB | 14 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Vikhrmodels/Vikhr-7B-instruct_merged .
Rank the Vikhr 7B Instruct Merged 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803