Merged Model 4-bit 4bit Autotrain compatible Base model:unsloth/qwen2-7b-bn... Bitsandbytes Conversational En Endpoints compatible License:apache-2.0 Quantized Qwen2 Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth
Qwen2 7B Alpacha Merged 4bit Parameters and Internals
| LLM Name | Qwen2 7B Alpacha Merged 4bit |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 7b |
| Required VRAM | 5.6 GB |
| Updated | 2024-07-04 |
| Maintainer | dbands |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|PAD_TOKEN|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen2 7B Alpacha Merged 4bit
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Qwen2 7B Bnb 4bit | 0.3 | 128K / 5.5 GB | 5822 | 2 |
| Tantrum 16bit | 0.3 | 128K / 15.2 GB | 168 | 0 |
| Qwen2 7B Matter 0.1 Slim A | 0.2 | 128K / 15.2 GB | 13 | 2 |
| ...lphin 2.9.2 Qwen2 7B Bpw6 EXL2 | 0.2 | 128K / 6.4 GB | 20 | 1 |
| PiSSA Qwen2 7B 4bit R128 5iter | 0.2 | 128K / 5.9 GB | 16 | 0 |
| Qwen2 7B 8bit | 0.2 | 128K / 8.1 GB | 17 | 1 |
| Qwen2 7B 4bit | 0.2 | 128K / 4.3 GB | 12 | 0 |
| Qwen2 7B Alpacha Merged 16bit | 0.2 | 128K / 15.2 GB | 7 | 0 |
| ...odeQwen1.5 7B Chat EXL2 8.0bpw | 0.2 | 64K / 7.5 GB | 7 | 4 |
| CodeQwen1.5 7B EXL2 8.0bpw | 0.2 | 64K / 7.5 GB | 10 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than dbands/Qwen2-7b-Alpacha-merged_4bit .
Rank the Qwen2 7B Alpacha Merged 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501