CoolFace
Modelpublic

RichardErkhov/frnka_-_Llama-3.2-3B-Instruct-DMP-synthetic-context-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes514downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.2-3B-Instruct-DMP-synthetic-context - GGUF

  • —Model creator: https://huggingface.co/frnka/
  • —Original model: https://huggingface.co/frnka/Llama-3.2-3B-Instruct-DMP-synthetic-context/
NameQuant methodSize
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q2_K.ggufQ2_K1.27GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.IQ3_XS.ggufIQ3_XS1.38GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.IQ3_S.ggufIQ3_S1.44GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q3_K_S.ggufQ3KS1.44GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.IQ3_M.ggufIQ3_M1.49GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q3_K.ggufQ3_K1.57GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q3_K_M.ggufQ3KM1.57GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q3_K_L.ggufQ3KL1.69GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.IQ4_XS.ggufIQ4_XS1.71GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q4_0.ggufQ4_01.79GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.IQ4_NL.ggufIQ4_NL1.79GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q4_K_S.ggufQ4KS1.8GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q4_K.ggufQ4_K1.88GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q4_K_M.ggufQ4KM1.88GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q4_1.ggufQ4_11.95GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q5_0.ggufQ5_02.11GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q5_K_S.ggufQ5KS2.11GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q5_K.ggufQ5_K2.16GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q5_K_M.ggufQ5KM2.16GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q5_1.ggufQ5_12.28GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q6_K.ggufQ6_K2.46GB
Llama-3.2-3B-Instruct-DMP-synthetic-context.Q8_0.ggufQ8_03.19GB

Original model description: --- library_name: transformers tags:

  • —unsloth datasets:
  • —frnka/dmp-qa-with-context-2 base_model:
  • —meta-llama/Llama-3.2-3B-Instruct pipeline_tag: question-answering ---

Improved with data generated by Qwen 2.5 14B

Model info

Model is used for finding answers to questions in Data Management Plans. It achieves F1 score of 49.1 on the user annotated dmps dataset.

Prompts used:

System:

You are an AI assistant specialized in extracting exact answers from given contexts. Your task is to:
1. Read the provided Data management plan carefully.
2. Find the specific answer to the given question within the context.
3. Extract and present the answer exactly as it appears, without any modifications.

Guidelines:
- Provide the answer word-for-word, preserving all original formatting, punctuation, and capitalization.
- If no exact answer is found, respond with "NO ANSWER"
- Do not offer any explanations, interpretations, or additional information beyond the exact answer found in the context.
- Do not modify, paraphrase, or summarize the answer in any way.

If you follow the guidelines exactly, I will give you a 10$ tip.

User:

Context:
{dmp}


Question:
{question}