Model Card on HF 🤗: https://huggingface.co/HuggingFaceTB/cosmo2-test-classic
Cosmo2 Test Classic Parameters and Internals
| LLM Name | Cosmo2 Test Classic |
| Repository 🤗 | https://huggingface.co/HuggingFaceTB/cosmo2-test-classic |
| Model Size | 1.7b |
| Required VRAM | 3.4 GB |
| Updated | 2024-07-04 |
| Maintainer | HuggingFaceTB |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.39.3 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
Best Alternatives to Cosmo2 Test Classic
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmolLM2 1.7B Instruct 16K | 16K / 3.4 GB | 16 | 9 |
| SmolLM2 1.7B Instruct | 8K / 3.4 GB | 58880 | 644 |
| Penny 1.7B | 8K / 6.9 GB | 262 | 23 |
| SmolLM2 1.7B | 8K / 3.4 GB | 26005 | 118 |
| SmolTulu 1.7B Reinforced | 8K / 3.4 GB | 591 | 5 |
| Smollm2 1.7B Smoltalk | 8K / 3.4 GB | 16 | 0 |
| ... 1.7B Smoltalk Stratified 100k | 8K / 3.4 GB | 13 | 0 |
| Smollm2 1.7B Tulu | 8K / 3.4 GB | 13 | 0 |
| SmolLM2 1.7 Persona | 8K / 3.5 GB | 32 | 0 |
| Superthoughts Lite V1 | 8K / 3.4 GB | 21 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/cosmo2-test-classic .
Rank the Cosmo2 Test Classic 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? 48075 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124