Visual Question Answering
Transformers
Safetensors
English
llama
text-generation
multimodal
KBVQA
VQA
Finetuning
text-generation-inference
Instructions to use m7mdal7aj/fine_tuned_llama_2_7b_chat_OKVQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use m7mdal7aj/fine_tuned_llama_2_7b_chat_OKVQA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="m7mdal7aj/fine_tuned_llama_2_7b_chat_OKVQA")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("m7mdal7aj/fine_tuned_llama_2_7b_chat_OKVQA") model = AutoModelForCausalLM.from_pretrained("m7mdal7aj/fine_tuned_llama_2_7b_chat_OKVQA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "meta-llama/Llama-2-7b-chat-hf", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 32006, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.35.2", | |
| "use_cache": true, | |
| "vocab_size": 32007 | |
| } | |