Downloads · 30 days
946
19% of all-time downloads
ssec-uw_-_OLMo-7B-Instruct-hf-gguf
RichardErkhov/ssec-uw_-_OLMo-7B-Instruct-hf-gguf
ssec-uw_-_OLMo-7B-Instruct-hf-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
5K
Public
Repo size
78.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf91.1 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 19, 2024
- Updated
- Sep 19, 2024
- SHA
- 597cf796
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
OLMo-7B-Instruct-hf - GGUF
- Model creator: https://huggingface.co/ssec-uw/
- Original model: https://huggingface.co/ssec-uw/OLMo-7B-Instruct-hf/
| Name | Quant method | Size |
|---|---|---|
| OLMo-7B-Instruct-hf.Q2_K.gguf | Q2_K | 2.44GB |
| OLMo-7B-Instruct-hf.IQ3_XS.gguf | IQ3_XS | 2.69GB |
| OLMo-7B-Instruct-hf.IQ3_S.gguf | IQ3_S | 2.83GB |
| OLMo-7B-Instruct-hf.Q3_K_S.gguf | Q3_K_S | 2.83GB |
| OLMo-7B-Instruct-hf.IQ3_M.gguf | IQ3_M | 2.99GB |
| OLMo-7B-Instruct-hf.Q3_K.gguf | Q3_K | 3.16GB |
| OLMo-7B-Instruct-hf.Q3_K_M.gguf | Q3_K_M | 3.16GB |
| OLMo-7B-Instruct-hf.Q3_K_L.gguf | Q3_K_L | 3.44GB |
| OLMo-7B-Instruct-hf.IQ4_XS.gguf | IQ4_XS | 3.49GB |
| OLMo-7B-Instruct-hf.Q4_0.gguf | Q4_0 | 3.66GB |
| OLMo-7B-Instruct-hf.IQ4_NL.gguf | IQ4_NL | 3.68GB |
| OLMo-7B-Instruct-hf.Q4_K_S.gguf | Q4_K_S | 3.69GB |
| OLMo-7B-Instruct-hf.Q4_K.gguf | Q4_K | 3.9GB |
| OLMo-7B-Instruct-hf.Q4_K_M.gguf | Q4_K_M | 3.9GB |
| OLMo-7B-Instruct-hf.Q4_1.gguf | Q4_1 | 4.05GB |
| OLMo-7B-Instruct-hf.Q5_0.gguf | Q5_0 | 4.44GB |
| OLMo-7B-Instruct-hf.Q5_K_S.gguf | Q5_K_S | 4.44GB |
| OLMo-7B-Instruct-hf.Q5_K.gguf | Q5_K | 4.56GB |
| OLMo-7B-Instruct-hf.Q5_K_M.gguf | Q5_K_M | 4.56GB |
| OLMo-7B-Instruct-hf.Q5_1.gguf | Q5_1 | 4.83GB |
| OLMo-7B-Instruct-hf.Q6_K.gguf | Q6_K | 5.26GB |
| OLMo-7B-Instruct-hf.Q8_0.gguf | Q8_0 | 6.82GB |
Original model description:
license: apache-2.0
OLMo 7B-Instruct-hf
For more details on OLMO-7B-Instruct, refer to Allen AI's OLMo-7B-Instruct model card.
OLMo is a series of Open Language Models designed to enable the science of language models. The OLMo base models are trained on the Dolma dataset. The Instruct version is trained on the cleaned version of the UltraFeedback dataset.
OLMo 7B Instruct is trained for better question answering. They show the performance gain that OLMo base models can achieve with existing fine-tuning techniques.
This version is for direct use with HuggingFace Transformers from v4.40 on.
Run instructions are forthcoming.
For faster inference with llama.cpp or similar software supporting the GGUF format, you can find this model as GGUF at ssec-uw/OLMo-7B-Instruct-GGUF.
Contact
For errors in this model card, contact Don or Anant, {landungs, anmittal} at uw dot edu.
Acknowledgement
We would like to thank the hardworking folks at Allen AI for providing the original model.
Additionally, the work to convert the model to the new hf version was done by the
University of Washington Scientific Software Engineering Center (SSEC),
as part of the Schmidt Futures Virtual Institute for Scientific Software (VISS).
- Created
- Sep 19, 2024
- Updated
- Sep 19, 2024