Frostwind V2.1 M7 is an open-source language model by Sao10K. Features: LLM, VRAM: 14.4GB, Context: 32K, License: cc-by-nc-4.0, HF Score: 62.2, LLM Explorer Score: 0.27, Arc: 61.8, HellaSwag: 83.8, MMLU: 63.8, TruthfulQA: 46.9, WinoGrande: 78.7, GSM8K: 38.4.
Model Card on HF 🤗: https://huggingface.co/Sao10K/Frostwind-v2.1-m7
Frostwind V2.1 M7 Benchmarks
ARC: 61.77 vs 96.7 (so35)-36.1%
HellaSwag: 83.77 vs 95.3 (gpt4)-12.1%
MMLU: 63.83 vs 88.3 (so35)-27.7%
TruthfulQA: 46.94 vs 59 (gpt4)-20.4%
WinoGrande: 78.69 vs 87.5 (gpt4)-10.1%
GSM8K: 38.36 vs 96.4 (so35)-60.2%
LLME Score: 0.26803
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)
Frostwind V2.1 M7 Parameters and Internals
| LLM Name | Frostwind V2.1 M7 |
| Repository 🤗 | https://huggingface.co/Sao10K/Frostwind-v2.1-m7 |
| Required VRAM | 14.4 GB |
| Updated | 2024-07-04 |
| Maintainer | Sao10K |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MistralForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Frostwind V2.1 M7
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Krutrim 2 Instruct | 1000K / 49.3 GB | 147 | 36 |
| Ft V1 Violet | 1000K / 24.5 GB | 5 | 0 |
| Mistral Large Instruct 2407 | 128K / 226.7 GB | 7491 | 859 |
| Tiny Random MistralForCausalLM | 128K / 0 GB | 3252 | 1 |
| Winterreise M7 | 32K / 14.4 GB | 0 | 0 |
| MistralLite | 32K / 14.4 GB | 11345 | 435 |
| K2S3 V0.1 | 32K / 28.7 GB | 6 | 0 |
| MistralLite | 32K / 14.4 GB | 61777 | 430 |
| ...ydaz Web AI Reasoner BaseModel | 32K / 14.4 GB | 0 | 1 |
| Tess XS V1.3 Yarn 128K | 32K / 14.5 GB | 3320 | 13 |
Note: green Score (e.g. "73.2") means that the model is better than Sao10K/Frostwind-v2.1-m7 .
Rank the Frostwind V2.1 M7 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? 52721 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