Downloads · 30 days
29
2% of all-time downloads
tensorblock/h2oai_h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-GGUF
h2oai_h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-GGUF is a text generation model from tensorblock. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
<div style="width: auto; margin-left: auto; margin-right: auto" <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;" </div
Downloads · 30 days
29
2% of all-time downloads
All-time downloads
1.5K
Public
Repo size
61 GB
Likes
0
Public
Click a slice to open those files.
.gguf3.9 GB · 100%
From the Hugging Face model README
This repo contains GGUF format model files for h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5165.
Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q2_K.gguf | Q2_K | 3.860 GB | smallest, significant quality loss - not recommended for most purposes |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q3_K_S.gguf | Q3_K_S | 3.860 GB | very small, high quality loss |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q3_K_M.gguf | Q3_K_M | 4.141 GB | very small, high quality loss |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q3_K_L.gguf | Q3_K_L | 4.378 GB | small, substantial quality loss |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q4_0.gguf | Q4_0 | 4.211 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q4_K_S.gguf | Q4_K_S | 4.746 GB | small, greater quality loss |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q4_K_M.gguf | Q4_K_M | 4.975 GB | medium, balanced quality - recommended |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q5_0.gguf | Q5_0 | 5.076 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q5_K_S.gguf | Q5_K_S | 5.343 GB | large, low quality loss - recommended |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q5_K_M.gguf | Q5_K_M | 5.731 GB | large, very low quality loss - recommended |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q6_K.gguf | Q6_K | 7.031 GB | very large, extremely low quality loss |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q8_0.gguf | Q8_0 | 7.671 GB | very large, extremely low quality loss - not recommended |
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/h2oai_h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-GGUF --include "h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/h2oai_h2ogpt-gm-oasst1-en-2048-falcon-7b-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'