Model Card on HF 🤗: https://huggingface.co/mohan11111/tinyllama56k-2bit-HQQ
Tinyllama56k 2bit HQQ 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)
Tinyllama56k 2bit HQQ Parameters and Internals
| LLM Name | Tinyllama56k 2bit HQQ |
| Repository 🤗 | https://huggingface.co/mohan11111/tinyllama56k-2bit-HQQ |
| Required VRAM | 0.5 GB |
| Updated | 2025-02-17 |
| Maintainer | mohan11111 |
| Model Type | llama |
| Model Files | |
| Quantization Type | 2bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Tinyllama56k 2bit HQQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... Text Chat 512K 5.0bpw H6 EXL2 | 512K / 4.4 GB | 4 | 1 |
| ... Text Chat 512K 6.0bpw H6 EXL2 | 512K / 5.2 GB | 4 | 1 |
| Phi 3.5 Instruct Vul | 128K / 7.6 GB | 78 | 0 |
| ... Text Chat 128K 6.0bpw H6 EXL2 | 128K / 5.2 GB | 3 | 1 |
| ...ocalAI Functioncall Phi 4 V0.3 | 16K / 29.4 GB | 139 | 5 |
| PARM V2 Phi 4 4K CoT PyTorch | 16K / 29.4 GB | 0 | 1 |
| QuantumQuill | 16K / 2.2 GB | 163 | 0 |
| CodeMate V0.1 6.0bpw H6 EXL2 | 16K / 25.7 GB | 5 | 1 |
| ...oros C34b 3.1.2 8.0bpw H6 EXL2 | 16K / 34 GB | 8 | 1 |
| TinyLlama QuantumQuill Chat | 15K / 2.2 GB | 71 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mohan11111/tinyllama56k-2bit-HQQ .
Rank the Tinyllama56k 2bit HQQ 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