Downloads · 30 days
30
1% of all-time downloads
M4-ai_-_Hercules-Mini-1.8B-gguf
RichardErkhov/M4-ai_-_Hercules-Mini-1.8B-gguf
M4-ai_-_Hercules-Mini-1.8B-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
2.6K
Public
Repo size
19.8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf23.4 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 27, 2024
- Updated
- Oct 27, 2024
- SHA
- 10e534d2
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Hercules-Mini-1.8B - GGUF
- Model creator: https://huggingface.co/M4-ai/
- Original model: https://huggingface.co/M4-ai/Hercules-Mini-1.8B/
| Name | Quant method | Size |
|---|---|---|
| Hercules-Mini-1.8B.Q2_K.gguf | Q2_K | 0.79GB |
| Hercules-Mini-1.8B.Q3_K_S.gguf | Q3_K_S | 0.89GB |
| Hercules-Mini-1.8B.Q3_K.gguf | Q3_K | 0.95GB |
| Hercules-Mini-1.8B.Q3_K_M.gguf | Q3_K_M | 0.95GB |
| Hercules-Mini-1.8B.Q3_K_L.gguf | Q3_K_L | 0.98GB |
| Hercules-Mini-1.8B.IQ4_XS.gguf | IQ4_XS | 1.01GB |
| Hercules-Mini-1.8B.Q4_0.gguf | Q4_0 | 1.04GB |
| Hercules-Mini-1.8B.IQ4_NL.gguf | IQ4_NL | 1.05GB |
| Hercules-Mini-1.8B.Q4_K_S.gguf | Q4_K_S | 1.08GB |
| Hercules-Mini-1.8B.Q4_K.gguf | Q4_K | 1.13GB |
| Hercules-Mini-1.8B.Q4_K_M.gguf | Q4_K_M | 1.13GB |
| Hercules-Mini-1.8B.Q4_1.gguf | Q4_1 | 1.13GB |
| Hercules-Mini-1.8B.Q5_0.gguf | Q5_0 | 1.22GB |
| Hercules-Mini-1.8B.Q5_K_S.gguf | Q5_K_S | 1.24GB |
| Hercules-Mini-1.8B.Q5_K.gguf | Q5_K | 1.28GB |
| Hercules-Mini-1.8B.Q5_K_M.gguf | Q5_K_M | 1.28GB |
| Hercules-Mini-1.8B.Q5_1.gguf | Q5_1 | 1.31GB |
| Hercules-Mini-1.8B.Q6_K.gguf | Q6_K | 1.47GB |
| Hercules-Mini-1.8B.Q8_0.gguf | Q8_0 | 1.82GB |
Original model description:
library_name: transformers license: other datasets:
- Locutusque/hercules-v4.0 language:
- en inference: parameters: do_sample: true temperature: 1 top_p: 0.7 top_k: 4 max_new_tokens: 250 repetition_penalty: 1.1
Hercules-Mini-1.8B
<!-- Provide a quick summary of what the model is/does. -->We fine-tuned Qwen1.5-1.8B on Locutusque's Hercules-v4.
Model Details
Model Description
<!-- Provide a longer summary of what this model is. -->This model has capabilities in math, coding, function calling, roleplay, and more. We fine-tuned it using 700,000 examples of Hercules-v4.
- Developed by: M4-ai
- Language(s) (NLP): English and maybe Chinese
- License: tongyi-qianwen license
- Finetuned from model: Qwen1.5-1.8B
Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->General purpose assistant, question answering, chain-of-thought, etc..
Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->The eos token was not setup properly, so to prevent infinite generation you'll need to implement a stopping criteria when the model generates the <|im_end|> token.
Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
Evaluation
Coming soon
Training Details
Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->https://huggingface.co/datasets/Locutusque/hercules-v4.0
Training Hyperparameters
- Training regime: bf16 non-mixed precision
Technical Specifications
Hardware
We used 8 Kaggle TPUs, and we trained at a global batch size of 256 and sequence length of 1536
Contributions
Thanks to @Tonic, @aloobun, @fhai50032, and @Locutusque for their contributions to this model.
- Created
- Oct 27, 2024
- Updated
- Oct 27, 2024