YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
Llama-2-7b-WikiChat - GGUF
- Model creator: https://huggingface.co/stanford-oval/
- Original model: https://huggingface.co/stanford-oval/Llama-2-7b-WikiChat/
Name | Quant method | Size |
---|---|---|
Llama-2-7b-WikiChat.Q2_K.gguf | Q2_K | 2.36GB |
Llama-2-7b-WikiChat.IQ3_XS.gguf | IQ3_XS | 2.6GB |
Llama-2-7b-WikiChat.IQ3_S.gguf | IQ3_S | 2.75GB |
Llama-2-7b-WikiChat.Q3_K_S.gguf | Q3_K_S | 2.75GB |
Llama-2-7b-WikiChat.IQ3_M.gguf | IQ3_M | 2.9GB |
Llama-2-7b-WikiChat.Q3_K.gguf | Q3_K | 3.07GB |
Llama-2-7b-WikiChat.Q3_K_M.gguf | Q3_K_M | 3.07GB |
Llama-2-7b-WikiChat.Q3_K_L.gguf | Q3_K_L | 3.35GB |
Llama-2-7b-WikiChat.IQ4_XS.gguf | IQ4_XS | 3.4GB |
Llama-2-7b-WikiChat.Q4_0.gguf | Q4_0 | 3.56GB |
Llama-2-7b-WikiChat.IQ4_NL.gguf | IQ4_NL | 3.58GB |
Llama-2-7b-WikiChat.Q4_K_S.gguf | Q4_K_S | 3.59GB |
Llama-2-7b-WikiChat.Q4_K.gguf | Q4_K | 3.8GB |
Llama-2-7b-WikiChat.Q4_K_M.gguf | Q4_K_M | 3.8GB |
Llama-2-7b-WikiChat.Q4_1.gguf | Q4_1 | 3.95GB |
Llama-2-7b-WikiChat.Q5_0.gguf | Q5_0 | 4.33GB |
Llama-2-7b-WikiChat.Q5_K_S.gguf | Q5_K_S | 4.33GB |
Llama-2-7b-WikiChat.Q5_K.gguf | Q5_K | 4.45GB |
Llama-2-7b-WikiChat.Q5_K_M.gguf | Q5_K_M | 4.45GB |
Llama-2-7b-WikiChat.Q5_1.gguf | Q5_1 | 4.72GB |
Llama-2-7b-WikiChat.Q6_K.gguf | Q6_K | 5.15GB |
Llama-2-7b-WikiChat.Q8_0.gguf | Q8_0 | 6.67GB |
Original model description:
license: llama2 language: - en
This model is a fine-tuned LLaMA-2 (7B) model. Please accept the LLaMA-2 license agreement before downloading this model.
Refer to the following for more information:
GitHub repository: https://github.com/stanford-oval/WikiChat
Paper: https://aclanthology.org/2023.findings-emnlp.157/
WikiChat
Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia
Online demo:
https://wikichat.genie.stanford.edu
- Downloads last month
- 576