Model Type |
| |||
Use Cases |
|
LLM Name | IcaroLM |
Repository ๐ค | https://huggingface.co/alexsobolev/IcaroLM |
Model Size | 1.5b |
Required VRAM | 3.1 GB |
Updated | 2025-03-15 |
Maintainer | alexsobolev |
Model Type | qwen2 |
Model Files | |
Quantization Type | 4bit |
Model Architecture | Qwen2ForCausalLM |
License | apache-2.0 |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.41.2 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|PAD_TOKEN|> |
Vocabulary Size | 151936 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...ill Qwen 1.5B Unsloth Bnb 4bit | 128K / 1.8 GB | 129398 | 13 |
... R1 Distill Qwen 1.5B Bnb 4bit | 128K / 1.6 GB | 135915 | 8 |
Research PathfinderAI | 128K / 3.5 GB | 19 | 0 |
Deep Ft4 Grp 16bit | 128K / 3.5 GB | 308 | 0 |
DeepSeek R1 ForumNXT | 128K / 3.5 GB | 7 | 0 |
Deep Ft8 Grp 16bit | 128K / 3.5 GB | 97 | 0 |
...pSeek R1 Distill Qwen 1.5B 500 | 128K / 1.7 GB | 29 | 0 |
Atlas Flash 1.5B Preview | 128K / 3.5 GB | 238 | 2 |
Deep Ft5 Grp 16bit | 128K / 3.5 GB | 82 | 0 |
Model | 128K / 3.5 GB | 19 | 0 |
๐ 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! ๐