|
--- |
|
license: mit |
|
library_name: peft |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
tags: |
|
- facebook |
|
- meta |
|
- pytorch |
|
- llama |
|
- llama-2 |
|
--- |
|
|
|
**Website**: [FireAct Agent](https://fireact-agent.github.io) |
|
|
|
# **FireAct Llama-2/CodeLlama** |
|
FireAct Llama/CodeLlama is a collection of fine-tuned generative text models for performaning ReAct with external search tools. Links to other models can be found in the Index section. |
|
|
|
## Foundation Model Details |
|
*Note: As the foundation models, Llama-2 and CodeLlama, are developed by Meta, please also read the guidence and license on their website, [Llama-2](https://huggingface.co./meta-llama) and [CodeLlama](https://huggingface.co./codellama), before using FireAct models.* |
|
|
|
**Model Developers** Sysmtem 2 Research, Cambridge LTL, Monash University, Princeton PLI. |
|
|
|
**Variations** FireAct models including Llama-2-7B full fine-tuned models, and Llama-2-[7B,13B], CodeLlama-[7B,13B,34B] LoRA fine-tuned models. All released models are fine-tuned on multi-task (HotpotQA/StrategyQA/MMLU) and multi-types (ReAct/CoT/Reflexion) data. |
|
|
|
**Input** Models input text only. |
|
|
|
**Output** Models generate text only. |
|
|
|
## Index |
|
**Full Fine-tuned Model** |
|
|
|
FireAct Llama-2: |
|
- [fireact_llama_2_7b](https://huggingface.co./forestai/fireact_llama_2_7b) |
|
|
|
**LoRA Fine-tuned Model** |
|
|
|
FireAct Llama-2: |
|
- [fireact_llama_2_7b_lora](https://huggingface.co./forestai/fireact_llama_2_7b_lora) |
|
- [fireact_llama_2_13b_lora](https://huggingface.co./forestai/fireact_llama_2_13b_lora) |
|
|
|
FireAct CodeLlama: |
|
- [fireact_codellama_7b_lora](https://huggingface.co./forestai/fireact_codellama_7b_lora) |
|
- [fireact_codellama_13b_lora](https://huggingface.co./forestai/fireact_codellama_13b_lora) |
|
- [fireact_codellama_34b_lora](https://huggingface.co./forestai/fireact_codellama_34b_lora) |
|
|
|
|
|
## LoRA Training procedure |
|
|
|
|
|
The following `bitsandbytes` quantization config was used during training: |
|
- load_in_8bit: True |
|
- load_in_4bit: False |
|
- llm_int8_threshold: 6.0 |
|
- llm_int8_skip_modules: None |
|
- llm_int8_enable_fp32_cpu_offload: False |
|
- llm_int8_has_fp16_weight: False |
|
- bnb_4bit_quant_type: fp4 |
|
- bnb_4bit_use_double_quant: False |
|
- bnb_4bit_compute_dtype: float32 |
|
### Framework versions |
|
|
|
|
|
- PEFT 0.4.0 |
|
|
