Arxiv:1910.07467 Arxiv:2002.05202 Arxiv:2104.09864 Arxiv:2401.03804 4bit Autotrain compatible Custom code Gptq Quantized Region:us Telechat
Model Card on HF 🤗: https://huggingface.co/Tele-AI/telechat-7B-int4
Telechat 7B Int4 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)
Telechat 7B Int4 Parameters and Internals
| Model Type |
| |||||||||||||||||||
| Use Cases |
| |||||||||||||||||||
| Additional Notes |
| |||||||||||||||||||
| Supported Languages |
| |||||||||||||||||||
| Training Details |
| |||||||||||||||||||
| Release Notes |
|
| LLM Name | Telechat 7B Int4 |
| Repository 🤗 | https://huggingface.co/Tele-AI/telechat-7B-int4 |
| Model Size | 7b |
| Required VRAM | 4.7 GB |
| Updated | 2025-02-05 |
| Maintainer | Tele-AI |
| Model Type | telechat |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | TelechatForCausalLM |
| License | apache-2.0 |
| Transformers Version | 4.30.0 |
| Tokenizer Class | BloomTokenizerFast |
| Padding Token | <pad> |
| Vocabulary Size | 160256 |
| Torch Data Type | float16 |
Best Alternatives to Telechat 7B Int4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Telechat 7B Int8 | 0K / 8 GB | 14 | 81 |
| Telechat 7B | 0K / 0.4 GB | 19 | 107 |
Note: green Score (e.g. "73.2") means that the model is better than Tele-AI/telechat-7B-int4 .
Rank the Telechat 7B Int4 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227