Model Card on HF 🤗: https://huggingface.co/TitanML/TinyLlama-1.1B-step-50K-105b-AWQ-4bit
TinyLlama 1.1B Step 50K 105B AWQ 4bit Benchmarks
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)
TinyLlama 1.1B Step 50K 105B AWQ 4bit Parameters and Internals
| LLM Name | TinyLlama 1.1B Step 50K 105B AWQ 4bit |
| Repository 🤗 | https://huggingface.co/TitanML/TinyLlama-1.1B-step-50K-105b-AWQ-4bit |
| Base Model(s) | |
| Model Size | 105b |
| Required VRAM | 0.8 GB |
| Updated | 2025-02-22 |
| Maintainer | TitanML |
| Model Type | llama |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq|4bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to TinyLlama 1.1B Step 50K 105B AWQ 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Anubis Pro 105B V1 | 128K / 210.7 GB | 280 | 16 |
| TinyLlama | 2K / 2.2 GB | 66 | 0 |
| TinyLlama 1.1B Step 50K 105B | 2K / 4.4 GB | 18991 | 132 |
| ...yLlama 1.1B Step 50K 105B ONNX | 2K / GB | 4 | 1 |
| Tiny Llama 1.1b Odia Ext | 2K / 2.2 GB | 13 | 0 |
| ...a 1.1B Step 50K 105B Gptq 4bit | 2K / 0.8 GB | 77 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than TitanML/TinyLlama-1.1B-step-50K-105b-AWQ-4bit .
Rank the TinyLlama 1.1B Step 50K 105B AWQ 4bit 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