Downloads · 30 days
0
Meta-Llama-3-8B-openwebtext-distilled-80k-gpt4
JCX-kcuf/Meta-Llama-3-8B-openwebtext-distilled-80k-gpt4
Meta-Llama-3-8B-openwebtext-distilled-80k-gpt4 is a machine learning model from JCX-kcuf. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model is finetuned on the distillation data from GPT-4. The base model is meta-llama/Meta-Llama-3-8B The model has a query format as in llama-3. (https://huggingface.co/blog/llama3)
Access
Public
Updated Jun 2, 2024
Repo size
42 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors42 MB · 82%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 2, 2024
- Updated
- Jun 2, 2024
- SHA
- 59ac6ffd
Model card
From the Hugging Face model README
Description
This model is finetuned on the distillation data from GPT-4. The base model is meta-llama/Meta-Llama-3-8B
Usage
The model has a query format as in llama-3. (https://huggingface.co/blog/llama3)
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
{{ user_msg_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
{{ model_answer_1 }}<|eot_id|>
- License
- apache-2.0
- Created
- Jun 2, 2024
- Updated
- Jun 2, 2024