Autotrain compatible Endpoints compatible Llama Merge Model-index Not-for-all-audiences Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/TeeZee/DarkForest-20B-v2.0
DarkForest 20B V2.0 Benchmarks
ARC: 63.74 vs 96.7 (so35)-34.1%
HellaSwag: 86.32 vs 95.3 (gpt4)-9.4%
MMLU: 59.79 vs 88.3 (so35)-32.3%
TruthfulQA: 56.14 vs 59 (gpt4)-4.8%
WinoGrande: 77.9 vs 87.5 (gpt4)-11%
GSM8K: 23.28 vs 96.4 (so35)-75.9%
LLME Score: 0.19383
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)
DarkForest 20B V2.0 Parameters and Internals
| LLM Name | DarkForest 20B V2.0 |
| Repository 🤗 | https://huggingface.co/TeeZee/DarkForest-20B-v2.0 |
| Model Size | 20b |
| Required VRAM | 40.1 GB |
| Updated | 2025-01-29 |
| Maintainer | TeeZee |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to DarkForest 20B V2.0
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Internlm2 5 20B Llamafied | 256K / 39.9 GB | 130 | 3 |
| Internlm2 20B Llama | 32K / 39.6 GB | 1748 | 20 |
| Stellaris Internlm2 20B R512 | 32K / 39.8 GB | 13 | 3 |
| Internlm2 Base 20B Llama | 32K / 39.6 GB | 23 | 3 |
| Internlm2 Chat 20B Llama Old | 32K / 39.6 GB | 18 | 3 |
| Internlm2 Base 20B Llama | 32K / 39.6 GB | 14 | 0 |
| Deita 20B | 32K / 39.8 GB | 49 | 1 |
| Bagel 20B V04 Llama | 32K / 39.6 GB | 14 | 7 |
| Bagel DPO 20B V04 Llama | 32K / 39.6 GB | 17 | 3 |
| Internlm2 Limarp Chat 20B | 32K / 39.6 GB | 12 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than TeeZee/DarkForest-20B-v2.0 .
Rank the DarkForest 20B V2.0 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