Upload ./README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- mistralai/Ministral-8B-Instruct-2410
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
- fr
|
7 |
+
- de
|
8 |
+
- es
|
9 |
+
- it
|
10 |
+
- pt
|
11 |
+
- zh
|
12 |
+
- ja
|
13 |
+
- ru
|
14 |
+
- ko
|
15 |
+
license: other
|
16 |
+
license_name: mrl
|
17 |
+
license_link: https://mistral.ai/licenses/MRL-0.1.md
|
18 |
+
inference: false
|
19 |
+
---
|
20 |
+
### exl2 quant (measurement.json in main branch)
|
21 |
+
---
|
22 |
+
### check revisions for quants
|
23 |
+
---
|
24 |
+
|
25 |
+
|
26 |
+
# Ministral-8B-Instruct-2410-HF
|
27 |
+
|
28 |
+
## Model Description
|
29 |
+
|
30 |
+
Ministral-8B-Instruct-2410-HF is the Hugging Face version of Ministral-8B-Instruct-2410 by Mistral AI. It is a multilingual instruction-tuned language model based on the Mistral architecture, designed for various natural language processing tasks with a focus on chat-based interactions.
|
31 |
+
|
32 |
+
|
33 |
+
## Installation
|
34 |
+
|
35 |
+
To use this model, install the required packages:
|
36 |
+
|
37 |
+
```bash
|
38 |
+
pip install -U transformers
|
39 |
+
```
|
40 |
+
|
41 |
+
## Usage Example
|
42 |
+
|
43 |
+
Here's a Python script demonstrating how to use the model for chat completion:
|
44 |
+
|
45 |
+
```python
|
46 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
47 |
+
|
48 |
+
# Model setup
|
49 |
+
model_name = "prince-canuma/Ministral-8B-Instruct-2410-HF"
|
50 |
+
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
|
51 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
52 |
+
|
53 |
+
# Chat interaction
|
54 |
+
prompt = "Tell me a short story about a robot learning to paint."
|
55 |
+
messages = [{"role": "user", "content": prompt}]
|
56 |
+
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
57 |
+
input_ids = tokenizer(text, return_tensors="pt").to(model.device)
|
58 |
+
|
59 |
+
# Generate response
|
60 |
+
output = model.generate(**input_ids, max_new_tokens=500, temperature=0.7, do_sample=True)
|
61 |
+
response = tokenizer.decode(output[0][input_ids.input_ids.shape[1]:])
|
62 |
+
|
63 |
+
print("User:", prompt)
|
64 |
+
print("Model:", response)
|
65 |
+
```
|
66 |
+
|
67 |
+
## Model Details
|
68 |
+
|
69 |
+
- **Developed by:** Mistral AI
|
70 |
+
- **Model type:** Causal Language Model
|
71 |
+
- **Language(s):** English
|
72 |
+
- **License:** [mrl](https://mistral.ai/licenses/MRL-0.1.md)
|
73 |
+
- **Resources for more information:**
|
74 |
+
- [Model Repository](https://huggingface.co/prince-canuma/Ministral-8B-Instruct-2410-HF)
|
75 |
+
- [Mistral AI GitHub](https://github.com/mistralai)
|