LLaVA-Reward is a model from Shijie Zhou, released under MIT License (access requested at publisher). Its published files total 4.7 GB.
Parameters—
Context—
Weights4.7 GB
Licensemit
AccessAccess requested at publisher
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- smz8599/LLaVA-Reward
- Publisher
- Shijie Zhou
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- f5a3519576a49130ec00b7586c95f6699e0eca68
- First published
- 2025-06-15
- Last updated
- 2026-10-01
Files and Weights
97 files, 4.7 GB in total. The weights are 16 files totalling 4.7 GB in bin.
Weights16 files · 4.7 GB
Configuration56 files · 657.4 KB
Tokenizer22 files · 56.9 MB
Documentation1 file · 24 B
Repository2 files · 7.9 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| alignment/llavareward_phi_alignment/lora/adapter_model.bin | Weights | 402.7 MB | — |
| alignment/llavareward_phi_alignment/pytorch_model.bin | Weights | 44.1 MB | — |
| fidelity/llavareward_phi_fidelity/lora/adapter_model.bin | Weights | 402.7 MB | — |
| fidelity/llavareward_phi_fidelity/pytorch_model.bin | Weights | 100.7 MB | — |
| fidelity/llavareward_qwen_fidelity/lora/adapter_model.bin | Weights | 646.1 MB | — |
| fidelity/llavareward_qwen_fidelity/pytorch_model.bin | Weights | 89.2 MB | — |
| general_reward/llavareward_reward_phi_0/lora/adapter_model.bin | Weights | 402.7 MB | — |
| general_reward/llavareward_reward_phi_0/pytorch_model.bin | Weights | 44.1 MB | — |
| general_reward/llavareward_reward_phi_1/lora/adapter_model.bin | Weights | 402.7 MB | — |
| general_reward/llavareward_reward_phi_1/pytorch_model.bin | Weights | 100.7 MB | — |
| general_reward/llavareward_reward_qwen/lora/adapter_model.bin | Weights | 646.1 MB | — |
| general_reward/llavareward_reward_qwen/pytorch_model.bin | Weights | 89.2 MB | — |
| safety/llavareward_phi_safety/lora/adapter_model.bin | Weights | 402.7 MB | — |
| safety/llavareward_phi_safety/pytorch_model.bin | Weights | 100.7 MB | — |
| safety/llavareward_qwen_safety/lora/adapter_model.bin | Weights | 646.1 MB | — |
| safety/llavareward_qwen_safety/pytorch_model.bin | Weights | 166.2 MB | — |
| alignment/llavareward_phi_alignment/config.json | Configuration | 3.8 KB | — |
| alignment/llavareward_phi_alignment/configuration_phi3_v.py | Configuration | 10.7 KB | — |
| alignment/llavareward_phi_alignment/lora/adapter_config.json | Configuration | 700 B | — |
| alignment/llavareward_phi_alignment/modeling_phi3_v.py | Configuration | 89.3 KB | — |
| alignment/llavareward_phi_alignment/preprocessor_config.json | Configuration | 464 B | — |
| alignment/llavareward_phi_alignment/processing_phi3_v.py | Configuration | 22.0 KB | — |
| alignment/llavareward_phi_alignment/reward_config.yaml | Configuration | 101 B | — |
| alignment/llavareward_phi_alignment/special_tokens_map.json | Configuration | 670 B | — |
| config.json | Configuration | 730 B | — |
| fidelity/llavareward_phi_fidelity/config.json | Configuration | 3.8 KB | — |
| fidelity/llavareward_phi_fidelity/configuration_phi3_v.py | Configuration | 10.7 KB | — |
| fidelity/llavareward_phi_fidelity/lora/adapter_config.json | Configuration | 700 B | — |
| fidelity/llavareward_phi_fidelity/modeling_phi3_v.py | Configuration | 89.3 KB | — |
| fidelity/llavareward_phi_fidelity/preprocessor_config.json | Configuration | 464 B | — |
| fidelity/llavareward_phi_fidelity/processing_phi3_v.py | Configuration | 22.0 KB | — |
| fidelity/llavareward_phi_fidelity/reward_config.yaml | Configuration | 100 B | — |
| fidelity/llavareward_phi_fidelity/special_tokens_map.json | Configuration | 670 B | — |
| fidelity/llavareward_qwen_fidelity/added_tokens.json | Configuration | 605 B | — |
| fidelity/llavareward_qwen_fidelity/config.json | Configuration | 1.3 KB | — |
| fidelity/llavareward_qwen_fidelity/lora/adapter_config.json | Configuration | 3.2 KB | — |
| fidelity/llavareward_qwen_fidelity/reward_config.yaml | Configuration | 101 B | — |
| fidelity/llavareward_qwen_fidelity/special_tokens_map.json | Configuration | 613 B | — |
| general_reward/llavareward_reward_phi_0/config.json | Configuration | 3.8 KB | — |
| general_reward/llavareward_reward_phi_0/configuration_phi3_v.py | Configuration | 10.7 KB | — |
| general_reward/llavareward_reward_phi_0/lora/adapter_config.json | Configuration | 700 B | — |
| general_reward/llavareward_reward_phi_0/modeling_phi3_v.py | Configuration | 89.3 KB | — |
| general_reward/llavareward_reward_phi_0/preprocessor_config.json | Configuration | 464 B | — |
| general_reward/llavareward_reward_phi_0/processing_phi3_v.py | Configuration | 22.0 KB | — |
| general_reward/llavareward_reward_phi_0/reward_config.yaml | Configuration | 102 B | — |
| general_reward/llavareward_reward_phi_0/special_tokens_map.json | Configuration | 670 B | — |
| general_reward/llavareward_reward_phi_1/config.json | Configuration | 3.8 KB | — |
| general_reward/llavareward_reward_phi_1/configuration_phi3_v.py | Configuration | 10.7 KB | — |
| general_reward/llavareward_reward_phi_1/lora/adapter_config.json | Configuration | 700 B | — |
| general_reward/llavareward_reward_phi_1/modeling_phi3_v.py | Configuration | 89.3 KB | — |
| general_reward/llavareward_reward_phi_1/preprocessor_config.json | Configuration | 464 B | — |
| general_reward/llavareward_reward_phi_1/processing_phi3_v.py | Configuration | 22.0 KB | — |
| general_reward/llavareward_reward_phi_1/reward_config.yaml | Configuration | 101 B | — |
| general_reward/llavareward_reward_phi_1/special_tokens_map.json | Configuration | 670 B | — |
| general_reward/llavareward_reward_qwen/added_tokens.json | Configuration | 605 B | — |
| general_reward/llavareward_reward_qwen/config.json | Configuration | 1.3 KB | — |
| general_reward/llavareward_reward_qwen/lora/adapter_config.json | Configuration | 3.2 KB | — |
| general_reward/llavareward_reward_qwen/reward_config.yaml | Configuration | 102 B | — |
| general_reward/llavareward_reward_qwen/special_tokens_map.json | Configuration | 613 B | — |
| safety/llavareward_phi_safety/config.json | Configuration | 3.8 KB | — |
| safety/llavareward_phi_safety/configuration_phi3_v.py | Configuration | 10.7 KB | — |
| safety/llavareward_phi_safety/lora/adapter_config.json | Configuration | 700 B | — |
| safety/llavareward_phi_safety/modeling_phi3_v.py | Configuration | 89.3 KB | — |
| safety/llavareward_phi_safety/preprocessor_config.json | Configuration | 464 B | — |
| safety/llavareward_phi_safety/processing_phi3_v.py | Configuration | 22.0 KB | — |
| safety/llavareward_phi_safety/reward_config.yaml | Configuration | 101 B | — |
| safety/llavareward_phi_safety/special_tokens_map.json | Configuration | 670 B | — |
| safety/llavareward_qwen_safety/added_tokens.json | Configuration | 605 B | — |
| safety/llavareward_qwen_safety/config.json | Configuration | 1.5 KB | — |
| safety/llavareward_qwen_safety/lora/adapter_config.json | Configuration | 3.2 KB | — |
| safety/llavareward_qwen_safety/reward_config.yaml | Configuration | 101 B | — |
| safety/llavareward_qwen_safety/special_tokens_map.json | Configuration | 613 B | — |
| README.md | Documentation | 24 B | — |
| .gitattributes | Repository | 1.8 KB | — |
| safety/llavareward_qwen_safety/.DS_Store | Repository | 6.1 KB | — |
| alignment/llavareward_phi_alignment/tokenizer.json | Tokenizer | 1.9 MB | — |
| alignment/llavareward_phi_alignment/tokenizer_config.json | Tokenizer | 9.6 KB | — |
| fidelity/llavareward_phi_fidelity/tokenizer.json | Tokenizer | 1.9 MB | — |
| fidelity/llavareward_phi_fidelity/tokenizer_config.json | Tokenizer | 9.6 KB | — |
| fidelity/llavareward_qwen_fidelity/merges.txt | Tokenizer | 1.7 MB | — |
| fidelity/llavareward_qwen_fidelity/tokenizer.json | Tokenizer | 11.4 MB | — |
| fidelity/llavareward_qwen_fidelity/tokenizer_config.json | Tokenizer | 7.3 KB | — |
| fidelity/llavareward_qwen_fidelity/vocab.json | Tokenizer | 2.8 MB | — |
| general_reward/llavareward_reward_phi_0/tokenizer.json | Tokenizer | 1.9 MB | — |
| general_reward/llavareward_reward_phi_0/tokenizer_config.json | Tokenizer | 9.6 KB | — |
| general_reward/llavareward_reward_phi_1/tokenizer.json | Tokenizer | 1.9 MB | — |
| general_reward/llavareward_reward_phi_1/tokenizer_config.json | Tokenizer | 9.6 KB | — |
| general_reward/llavareward_reward_qwen/merges.txt | Tokenizer | 1.7 MB | — |
| general_reward/llavareward_reward_qwen/tokenizer.json | Tokenizer | 11.4 MB | — |
| general_reward/llavareward_reward_qwen/tokenizer_config.json | Tokenizer | 7.3 KB | — |
| general_reward/llavareward_reward_qwen/vocab.json | Tokenizer | 2.8 MB | — |
| safety/llavareward_phi_safety/tokenizer.json | Tokenizer | 1.9 MB | — |
| safety/llavareward_phi_safety/tokenizer_config.json | Tokenizer | 9.6 KB | — |
| safety/llavareward_qwen_safety/merges.txt | Tokenizer | 1.7 MB | — |
| safety/llavareward_qwen_safety/tokenizer.json | Tokenizer | 11.4 MB | — |
| safety/llavareward_qwen_safety/tokenizer_config.json | Tokenizer | 5.8 KB | — |
| safety/llavareward_qwen_safety/vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- mit
- Access
- Access requested at publisher
- Download size
- 4.7 GB
Request access from Shijie Zhou
Shijie Zhou grants access through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 4.7 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About LLaVA-Reward
Can I use LLaVA-Reward commercially?
Yes. LLaVA-Reward is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.