Downloads · 30 days
240
7% of all-time downloads
RichardErkhov/openaccess-ai-collective_-_manticore-30b-chat-pyg-alpha-gguf
openaccess-ai-collective_-_manticore-30b-chat-pyg-alpha-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.
Downloads · 30 days
240
7% of all-time downloads
All-time downloads
3.7K
Public
Repo size
368 GB
Likes
0
Public
Click a slice to open those files.
.gguf426 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
manticore-30b-chat-pyg-alpha - GGUF
datasets:
💵 Donate to OpenAccess AI Collective to help us keep building great tools and models!
Manticore 30B Chat builds on Manticore v1 with new datasets, including a de-duped subset of the Pygmalion dataset. It also removes all Alpaca style prompts using ### in favor of
chat only style prompts using USER:,ASSISTANT: as well as pygmalion/metharme prompting using <|system|>, <|user|> and <|model|> tokens.
Questions, comments, feedback, looking to donate, or want to help? Reach out on our Discord or email [email protected]
Manticore 30B Chat is a Llama 30B model fine-tuned on the following datasets along with the datasets from the original Manticore 30B.
**Manticore 30B Chat was trained on effectively 40% of the datasets below due to only training for 0.4 epochs.
Manticore 30B
train splittrain splitNot added from Manticore 13B:
test split is used for benchmarksSpecial thanks to Nanobit for helping with Axolotl, TheBloke for quantizing these models are more accessible to all, ehartford for cleaned datasets, and 0x000011b for the RP dataset.
Try out the model in HF Spaces. The demo uses a quantized GGML version of the model to quickly return predictions on smaller GPUs (and even CPUs). Quantized GGML may have some minimal loss of model quality.
Manticore was built with Axolotl on 8xA100 80GB
Manticore has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). Manticore was fine-tuned from the base model LlaMa 13B, please refer to its model card's Limitations Section for relevant information.
TBD