Tigerbot 7B Sft V1 4bit is an open-source language model by TigerResearch. Features: 7b LLM, VRAM: 5.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.08, Arc: 58.4, HellaSwag: 59.8, MMLU: 31.4, GSM8K: 12.4.
Model Card on HF 🤗: https://huggingface.co/TigerResearch/tigerbot-7b-sft-v1-4bit
Tigerbot 7B Sft V1 4bit Benchmarks
ARC: 58.4 vs 96.7 (so35)-39.6%
HellaSwag: 59.8 vs 95.3 (gpt4)-37.3%
MMLU: 31.4 vs 88.3 (so35)-64.4%
GSM8K: 12.4 vs 96.4 (so35)-87.1%
OpenCompas: 39 vs 73.3 (gpt4)-46.8%
Exam: 38.5 vs 77.2 (gpt4)-50.1%
Language: 39.6 vs 62 (gpt4)-36.1%
Knowledge: 41.4 vs 73.5 (gpt4)-43.7%
Understand: 42.1 vs 70 (gpt4)-39.9%
Reasoning: 37.1 vs 74.4 (gpt4)-50.1%
LLME Score: 0.07593
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)
Tigerbot 7B Sft V1 4bit Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | Tigerbot 7B Sft V1 4bit |
| Repository 🤗 | https://huggingface.co/TigerResearch/tigerbot-7b-sft-v1-4bit |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 5.2 GB |
| Updated | 2026-04-02 |
| Maintainer | TigerResearch |
| Model Type | bloom |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | BloomForCausalLM |
| License | apache-2.0 |
| Model Max Length | 1024 |
| Transformers Version | 4.27.0.dev0 |
| Tokenizer Class | BloomTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 250682 |
| Torch Data Type | bfloat16 |
Best Alternatives to Tigerbot 7B Sft V1 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phoenix Inst Chat 7B Int4 | 2K / 5.2 GB | 10 | 6 |
| Vietcuna 7B V3 AWQ | 0K / 7.2 GB | 6 | 0 |
| Yayi 7B | 0K / 28.2 GB | 883 | 30 |
| Gogpt 7B Bloom | 0K / 32.3 GB | 811 | 3 |
| ...Qa Llama 2 7B Chat Hf Uld Loss | 0K / 2.2 GB | 5 | 0 |
| ...lama 2 7B Chat Hf Text Teacher | 0K / 2.2 GB | 5 | 0 |
| ...tral 7B Instruct V0.2 Uld Loss | 0K / 2.2 GB | 5 | 0 |
| ... 7B Instruct V0.2 Text Teacher | 0K / 2.2 GB | 5 | 0 |
| Phoenix Inst Chat 7B | 0K / 16.2 GB | 850 | 43 |
| Vietcuna 7B V3 AWQ | 0K / 7.2 GB | 15 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than TigerResearch/tigerbot-7b-sft-v1-4bit .
Rank the Tigerbot 7B Sft V1 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? 53053 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a