Downloads · 30 days
134
3% of all-time downloads
llmat_-_Mistral-v0.3-7B-ORPO-gguf
RichardErkhov/llmat_-_Mistral-v0.3-7B-ORPO-gguf
llmat_-_Mistral-v0.3-7B-ORPO-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
4K
Public
Repo size
76.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf84.2 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 15, 2024
- Updated
- Aug 16, 2024
- SHA
- 6173b44d
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Mistral-v0.3-7B-ORPO - GGUF
- Model creator: https://huggingface.co/llmat/
- Original model: https://huggingface.co/llmat/Mistral-v0.3-7B-ORPO/
| Name | Quant method | Size |
|---|---|---|
| Mistral-v0.3-7B-ORPO.Q2_K.gguf | Q2_K | 2.54GB |
| Mistral-v0.3-7B-ORPO.IQ3_XS.gguf | IQ3_XS | 2.82GB |
| Mistral-v0.3-7B-ORPO.IQ3_S.gguf | IQ3_S | 2.97GB |
| Mistral-v0.3-7B-ORPO.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| Mistral-v0.3-7B-ORPO.IQ3_M.gguf | IQ3_M | 3.06GB |
| Mistral-v0.3-7B-ORPO.Q3_K.gguf | Q3_K | 3.28GB |
| Mistral-v0.3-7B-ORPO.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| Mistral-v0.3-7B-ORPO.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| Mistral-v0.3-7B-ORPO.IQ4_XS.gguf | IQ4_XS | 3.68GB |
| Mistral-v0.3-7B-ORPO.Q4_0.gguf | Q4_0 | 3.83GB |
| Mistral-v0.3-7B-ORPO.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| Mistral-v0.3-7B-ORPO.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| Mistral-v0.3-7B-ORPO.Q4_K.gguf | Q4_K | 3.87GB |
| Mistral-v0.3-7B-ORPO.Q4_K_M.gguf | Q4_K_M | 3.87GB |
| Mistral-v0.3-7B-ORPO.Q4_1.gguf | Q4_1 | 3.87GB |
| Mistral-v0.3-7B-ORPO.Q5_0.gguf | Q5_0 | 3.87GB |
| Mistral-v0.3-7B-ORPO.Q5_K_S.gguf | Q5_K_S | 3.87GB |
| Mistral-v0.3-7B-ORPO.Q5_K.gguf | Q5_K | 3.87GB |
| Mistral-v0.3-7B-ORPO.Q5_K_M.gguf | Q5_K_M | 3.87GB |
| Mistral-v0.3-7B-ORPO.Q5_1.gguf | Q5_1 | 3.87GB |
| Mistral-v0.3-7B-ORPO.Q6_K.gguf | Q6_K | 3.87GB |
| Mistral-v0.3-7B-ORPO.Q8_0.gguf | Q8_0 | 3.87GB |
Original model description:
base_model: unsloth/mistral-7b-v0.3-bnb-4bit language:
- en license: apache-2.0 tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
- orpo
Uploaded model
- Developed by: llmat
- License: apache-2.0
- Finetuned from model : unsloth/mistral-7b-v0.3-bnb-4bit
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "llmat/Mistral-v0.3-7B-ORPO"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
- Created
- Aug 15, 2024
- Updated
- Aug 16, 2024