messages = [
{"role": "system", "content": "You are Cobalt, expert math AI."},
{"role": "user", "content": "I'm buying a $50 shirt and a $80 pair of pants, both currently at a 25% discount. How much will I pay?"}
]
Cobalt is built on top of Llama 3.1 8b Instruct, using math-instruct data to supplement math-instruct performance using Llama 3.1 Instruct prompt style.
Our current version of the Cobalt math-instruct dataset is
sequelbox/Polytope
, supplemented with a small selection of data from
LDJnr/Pure-Dove
for general chat consistency.
Llama3.1-8B-Cobalt-GGUF huggingface.co is an AI model on huggingface.co that provides Llama3.1-8B-Cobalt-GGUF's model effect (), which can be used instantly with this QuantFactory Llama3.1-8B-Cobalt-GGUF model. huggingface.co supports a free trial of the Llama3.1-8B-Cobalt-GGUF model, and also provides paid use of the Llama3.1-8B-Cobalt-GGUF. Support call Llama3.1-8B-Cobalt-GGUF model through api, including Node.js, Python, http.
Llama3.1-8B-Cobalt-GGUF huggingface.co is an online trial and call api platform, which integrates Llama3.1-8B-Cobalt-GGUF's modeling effects, including api services, and provides a free online trial of Llama3.1-8B-Cobalt-GGUF, you can try Llama3.1-8B-Cobalt-GGUF online for free by clicking the link below.
QuantFactory Llama3.1-8B-Cobalt-GGUF online free url in huggingface.co:
Llama3.1-8B-Cobalt-GGUF is an open source model from GitHub that offers a free installation service, and any user can find Llama3.1-8B-Cobalt-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of Llama3.1-8B-Cobalt-GGUF install, users can directly use Llama3.1-8B-Cobalt-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Llama3.1-8B-Cobalt-GGUF install url in huggingface.co: