Make Your LLM Fully Utilize the Context
Paper β’ 2404.16811 β’ Published β’ 55
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Quantization made by Richard Erkhov.
FILM-7B - GGUF
- Model creator: https://huggingface.co/In2Training/
- Original model: https://huggingface.co/In2Training/FILM-7B/
| Name | Quant method | Size |
|---|---|---|
| FILM-7B.Q2_K.gguf | Q2_K | 2.53GB |
| FILM-7B.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| FILM-7B.IQ3_S.gguf | IQ3_S | 2.96GB |
| FILM-7B.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| FILM-7B.IQ3_M.gguf | IQ3_M | 3.06GB |
| FILM-7B.Q3_K.gguf | Q3_K | 3.28GB |
| FILM-7B.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| FILM-7B.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| FILM-7B.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| FILM-7B.Q4_0.gguf | Q4_0 | 3.83GB |
| FILM-7B.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| FILM-7B.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| FILM-7B.Q4_K.gguf | Q4_K | 4.07GB |
| FILM-7B.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| FILM-7B.Q4_1.gguf | Q4_1 | 4.24GB |
| FILM-7B.Q5_0.gguf | Q5_0 | 4.65GB |
| FILM-7B.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| FILM-7B.Q5_K.gguf | Q5_K | 4.78GB |
| FILM-7B.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| FILM-7B.Q5_1.gguf | Q5_1 | 5.07GB |
| FILM-7B.Q6_K.gguf | Q6_K | 5.53GB |
| FILM-7B.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
license: apache-2.0 language: - en
FILM-7B
π» [Github Repo] β’ π [Paper] β’ β [VaLProbing-32K]
FILM-7B is a 32K-context LLM that overcomes the lost-in-the-middle problem. It is trained from Mistral-7B-Instruct-v0.2 by applying Information-Intensie (In2) Training. FILM-7B achieves near-perfect performance on probing tasks, SOTA-level performance on real-world long-context tasks among ~7B size LLMs, and does not compromise the short-context performance.
Model Usage
The system tempelate for FILM-7B:
'''[INST] Below is a context and an instruction. Based on the information provided in the context, write a response for the instruction.
### Context:
{YOUR LONG CONTEXT}
### Instruction:
{YOUR QUESTION & INSTRUCTION} [/INST]
'''
Probing Results
To reproduce the results on our VaL Probing, see the guidance in https://github.com/microsoft/FILM/tree/main/VaLProbing.
Real-World Long-Context Tasks
To reproduce the results on real-world long-context tasks, see the guidance in https://github.com/microsoft/FILM/tree/main/real_world_long.
Short-Context Tasks
To reproduce the results on short-context tasks, see the guidance in https://github.com/microsoft/FILM/tree/main/short_tasks.
π Citation
@misc{an2024make,
title={Make Your LLM Fully Utilize the Context},
author={Shengnan An and Zexiong Ma and Zeqi Lin and Nanning Zheng and Jian-Guang Lou},
year={2024},
eprint={2404.16811},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
Disclaimer: This model is strictly for research purposes, and not an official product or service from Microsoft.
- Downloads last month
- 343
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support