Merged Model Autotrain compatible Base model:gradientai/llama-3-... Base model:johnsnowlabs/jsl-me... Conversational Endpoints compatible Gradientai/llama-3-8b-instruct... Instruct Johnsnowlabs/jsl-medllama-3-8b... Llama Region:us Safetensors Sharded Tensorflow Zh
Llama3 8B Slerp Med 262K Benchmarks
ARC: 51.54 vs 96.7 (so35)-46.7%
HellaSwag: 75.15 vs 95.3 (gpt4)-21.1%
MMLU: 56 vs 88.3 (so35)-36.6%
TruthfulQA: 43.53 vs 59 (gpt4)-26.2%
WinoGrande: 68.51 vs 87.5 (gpt4)-21.7%
GSM8K: 27.14 vs 96.4 (so35)-71.8%
LLME Score: 0.26102
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)
Llama3 8B Slerp Med 262K Parameters and Internals
| LLM Name | Llama3 8B Slerp Med 262K |
| Repository 🤗 | https://huggingface.co/shanchen/llama3-8B-slerp-med-262k |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 8b |
| Required VRAM | 16 GB |
| Updated | 2024-10-18 |
| Maintainer | shanchen |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | zh |
| Model Architecture | LlamaForCausalLM |
| License | llama3 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama3 8B Slerp Med 262K
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...a 3 8B Instruct Gradient 1048K | 1024K / 16.1 GB | 7474 | 667 |
| L3.1 Gradient | 1024K / 16.1 GB | 5 | 0 |
| ...SLERP Gradient1048k OpenBioLLM | 1024K / 16.1 GB | 21 | 0 |
| Llama3 8B Special Dark V3.1.2B | 1024K / 16.1 GB | 6 | 0 |
| Loki | 1024K / 16.1 GB | 5 | 0 |
| ...lama3 8B Special Dark V3.1.2aa | 1024K / 16.1 GB | 5 | 0 |
| ...lama3 8B Special Dark V3.1.1yy | 1024K / 16.1 GB | 5 | 0 |
| Unholy Thoth 8B V2 | 1024K / 16.1 GB | 5 | 0 |
| ...struct Gradient 1048K MAC Lora | 1024K / 5.9 GB | 4 | 2 |
| ... Instruct Gradient 1048K Agent | 1024K / 16.1 GB | 124 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than shanchen/llama3-8B-slerp-med-262k .
Rank the Llama3 8B Slerp Med 262K 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803