4bit Autotrain compatible Conversational Endpoints compatible Instruct Llama Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/dreamgen/llama3-8b-instruct-align-test2-kto
Llama3 8B Instruct Align Test2 Kto Benchmarks
ARC: 60.58 vs 96.7 (so35)-37.4%
HellaSwag: 78 vs 95.3 (gpt4)-18.2%
MMLU: 66.38 vs 88.3 (so35)-24.8%
TruthfulQA: 52.41 vs 59 (gpt4)-11.2%
WinoGrande: 75.06 vs 87.5 (gpt4)-14.2%
GSM8K: 68.16 vs 96.4 (so35)-29.3%
LLME Score: 0.2018
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 Instruct Align Test2 Kto Parameters and Internals
| LLM Name | Llama3 8B Instruct Align Test2 Kto |
| Repository 🤗 | https://huggingface.co/dreamgen/llama3-8b-instruct-align-test2-kto |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2025-02-22 |
| Maintainer | dreamgen |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | cc |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_250|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama3 8B Instruct Align Test2 Kto
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...B Instruct Gradient 1048K 4bit | 1024K / 4.5 GB | 21 | 2 |
| ...B Instruct Gradient 1048K 8bit | 1024K / 8.6 GB | 7 | 1 |
| ...truct Gradient 1048K Bpw6 EXL2 | 1024K / 6.7 GB | 10 | 2 |
| ...truct Gradient 1048K Bpw5 EXL2 | 1024K / 5.8 GB | 7 | 0 |
| Llama 3 8B Instruct 1048K 4bit | 1024K / 4.5 GB | 12 | 25 |
| Llama 3 8B Instruct 1048K 8bit | 1024K / 8.6 GB | 28 | 17 |
| ... Gradient 1048K 8.0bpw H8 EXL2 | 1024K / 8.6 GB | 8 | 3 |
| ...ct Gradient 1048K Bpw2.25 EXL2 | 1024K / 3.4 GB | 5 | 1 |
| Llama 3 8B Instruct 262K 2bit | 256K / 2.5 GB | 7 | 1 |
| ...B Instruct 262k V2 EXL2 6.0bpw | 256K / 6.7 GB | 11 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than dreamgen/llama3-8b-instruct-align-test2-kto .
Rank the Llama3 8B Instruct Align Test2 Kto 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227