Downloads · 30 days
28
3% of all-time downloads
RichardErkhov/mncai_-_agiin-13.6B-v0.0-gguf
mncai_-_agiin-13.6B-v0.0-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
28
3% of all-time downloads
All-time downloads
1.1K
Public
Repo size
156 GB
Likes
0
Public
Click a slice to open those files.
.gguf181 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
agiin-13.6B-v0.0 - GGUF
| Name | Quant method | Size |
|---|---|---|
| agiin-13.6B-v0.0.Q2_K.gguf | Q2_K | 4.77GB |
| agiin-13.6B-v0.0.IQ3_XS.gguf | IQ3_XS | 5.3GB |
| agiin-13.6B-v0.0.IQ3_S.gguf | IQ3_S | 5.6GB |
| agiin-13.6B-v0.0.Q3_K_S.gguf | Q3_K_S | 5.57GB |
| agiin-13.6B-v0.0.IQ3_M.gguf | IQ3_M | 5.78GB |
| agiin-13.6B-v0.0.Q3_K.gguf | Q3_K | 6.2GB |
| agiin-13.6B-v0.0.Q3_K_M.gguf | Q3_K_M | 6.2GB |
| agiin-13.6B-v0.0.Q3_K_L.gguf | Q3_K_L | 6.75GB |
| agiin-13.6B-v0.0.IQ4_XS.gguf | IQ4_XS | 6.96GB |
| agiin-13.6B-v0.0.Q4_0.gguf | Q4_0 | 7.26GB |
| agiin-13.6B-v0.0.IQ4_NL.gguf | IQ4_NL | 7.33GB |
| agiin-13.6B-v0.0.Q4_K_S.gguf | Q4_K_S | 7.31GB |
| agiin-13.6B-v0.0.Q4_K.gguf | Q4_K | 7.71GB |
| agiin-13.6B-v0.0.Q4_K_M.gguf | Q4_K_M | 7.71GB |
| agiin-13.6B-v0.0.Q4_1.gguf | Q4_1 | 8.05GB |
| agiin-13.6B-v0.0.Q5_0.gguf | Q5_0 | 8.84GB |
| agiin-13.6B-v0.0.Q5_K_S.gguf | Q5_K_S | 8.84GB |
| agiin-13.6B-v0.0.Q5_K.gguf | Q5_K | 9.08GB |
| agiin-13.6B-v0.0.Q5_K_M.gguf | Q5_K_M | 9.08GB |
| agiin-13.6B-v0.0.Q5_1.gguf | Q5_1 | 9.64GB |
| agiin-13.6B-v0.0.Q6_K.gguf | Q6_K | 10.53GB |
| agiin-13.6B-v0.0.Q8_0.gguf | Q8_0 | 13.64GB |
license: apache-2.0 language:
We create various AI models and develop solutions that can be applied to businesses. And as for generative AI, we are developing products like Code Assistant, TOD Chatbot, LLMOps, and are in the process of developing Enterprise AGI (Artificial General Intelligence).
based mistral arch. pretrain, instruction tuned and dpo.
Here give some examples of how to use our model.
from transformers import AutoConfig, AutoModel, AutoTokenizer
import transformers
import torch
hf_model = 'mncai/agiin-13.6B-v0.0'
message = "<|user|>\n두 개의 구가 있는데 각각 지름이 1, 2일때 각 구의 부피는 몇배야? 설명도 같이 해줘.\n<|assistant|>\n"
sequences = pipeline(
message,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
max_length=2048,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
If you have any questions, please raise an issue or contact us at [email protected]