Experiment26 Truthy Iter 0 is an open-source language model by rwitz. Features: 7.2b LLM, VRAM: 14.4GB, Context: 32K, License: mit, HF Score: 76.7, LLM Explorer Score: 0.13, Arc: 73.3, HellaSwag: 89.1, MMLU: 64.4, TruthfulQA: 77.9, WinoGrande: 84.9, GSM8K: 70.4.
Arxiv:1910.09700 Autotrain compatible Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/rwitz/experiment26-truthy-iter-0
Experiment26 Truthy Iter 0 Benchmarks
ARC: 73.29 vs 96.7 (so35)-24.2%
HellaSwag: 89.11 vs 95.3 (gpt4)-6.5%
MMLU: 64.35 vs 88.3 (so35)-27.1%
TruthfulQA: 77.86 vs 59 (gpt4)32%
WinoGrande: 84.93 vs 87.5 (gpt4)-2.9%
GSM8K: 70.36 vs 96.4 (so35)-27%
LLME Score: 0.12786
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)
Experiment26 Truthy Iter 0 Parameters and Internals
| LLM Name | Experiment26 Truthy Iter 0 |
| Repository 🤗 | https://huggingface.co/rwitz/experiment26-truthy-iter-0 |
| Model Size | 7.2b |
| Required VRAM | 14.4 GB |
| Updated | 2024-10-02 |
| Maintainer | rwitz |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Experiment26 Truthy Iter 0
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Web AI HumanAI 012 INSTRUCT XA | 512K / 14.4 GB | 9 | 0 |
| ...Web AI HumanAI 012 INSTRUCT IA | 512K / 14.4 GB | 8 | 0 |
| ...Web AI HumanAI 011 INSTRUCT ML | 512K / 14.4 GB | 7 | 0 |
| 14 | 512K / 14.5 GB | 319 | 0 |
| SpydazWeb HumanAI M2 | 512K / GB | 38 | 0 |
| ...dazWeb AI HumanAI 011 INSTRUCT | 512K / 14.4 GB | 14 | 1 |
| SpydazWeb AI HumanAI 009 CHAT | 512K / 14.4 GB | 6 | 0 |
| SpydazWeb AI HumanAI 007 | 512K / 14.4 GB | 5 | 0 |
| ...Web AI HumanAI 012 INSTRUCT MX | 512K / 14.4 GB | 8 | 0 |
| SpydazWeb AI HumanAI 010 CHAT | 512K / 14.4 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than rwitz/experiment26-truthy-iter-0 .
Rank the Experiment26 Truthy Iter 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? 53185 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a