8-bit Autotrain compatible Compressed-tensors Conversational Endpoints compatible Llama Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/nm-testing/tinyllama-oneshot-w8-channel-a8-tensor
Tinyllama Oneshot W8 Channel A8 Tensor 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 Oneshot W8 Channel A8 Tensor Parameters and Internals
| LLM Name | Tinyllama Oneshot W8 Channel A8 Tensor |
| Repository 🤗 | https://huggingface.co/nm-testing/tinyllama-oneshot-w8-channel-a8-tensor |
| Model Size | 1.1b |
| Required VRAM | 1.2 GB |
| Updated | 2025-02-08 |
| Maintainer | nm-testing |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Tinyllama Oneshot W8 Channel A8 Tensor
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Coven Tiny 1.1b 32k Orpo Alpha | 32K / 2.2 GB | 131 | 2 |
| Test Mix 01 | 32K / 2.2 GB | 135 | 0 |
| Palmer Merge Test 5 | 32K / 2.2 GB | 126 | 0 |
| ...llama 1.1B 16K Instructions V4 | 32K / 2.2 GB | 9 | 0 |
| TinyLlama 1.1B 32K Instruct | 32K / 2.2 GB | 286 | 12 |
| Palmer 002 32K | 32K / 2.2 GB | 136 | 0 |
| TinyLlama 1.1B 32K | 32K / 2.2 GB | 116 | 28 |
| Tinyllama History Chat V1.1 | 32K / 2.2 GB | 98 | 0 |
| TinyJ.O.S.I.E. 1.1B 32K Base | 32K / 2.2 GB | 30 | 1 |
| Tinyllama 32k | 32K / 2.2 GB | 82 | 0 |
Rank the Tinyllama Oneshot W8 Channel A8 Tensor 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? 42807 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227