File size: 2,239 Bytes
b6cae30 cb71443 b6cae30 b98c24f 489f743 3c3b33d 489f743 3c3b33d 489f743 3c3b33d 489f743 b6cae30 c36136e b6cae30 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
---
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
library_name: peft
license: mit
language:
- en
pipeline_tag: text-generation
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## How to Use
```python
!pip install bitsandbytes
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
# **Model Name on Hugging Face**
MODEL_NAME = "Vijayendra/DeepSeek-Llama3.1-8B-DeepThinker-v1"
# 🛠 **Load Model & Tokenizer from Hugging Face**
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(
MODEL_NAME,
device_map="auto", # Automatically assigns model layers to available GPUs/CPUs
torch_dtype=torch.float16 # Use 16-bit precision for memory efficiency
).to("cuda" if torch.cuda.is_available() else "cpu") # Send model to GPU if available
# 🛠 **Define Inference Function**
def generate_response(model, tokenizer, prompt, max_new_tokens=2048, temperature=0.7):
# Tokenize input
inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True).to(model.device)
# Ensure attention mask is passed
attention_mask = inputs.attention_mask
# Generate response
with torch.no_grad():
generated_tokens = model.generate(
inputs.input_ids,
attention_mask=inputs.attention_mask, # Ensure attention mask is passed
max_new_tokens=max_new_tokens,
temperature=temperature,
do_sample=True,
top_k=40,
top_p=0.9,
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.pad_token_id
)
# Decode response
return tokenizer.decode(generated_tokens[0], skip_special_tokens=True)
# **Test Questions**
questions = [
"What happened yesterday?",
"If an unstoppable force hits an immovable object, what happens?",
"The sun orbits the Earth once every 365 days. Is this true?"
]
# **Generate and Print Responses**
for i, question in enumerate(questions, 1):
response = generate_response(model, tokenizer, question)
print(f"\n🟢 Question {i}: {question}")
print(f"🔵 Response: {response}")
```
### Framework versions
- PEFT 0.14.0 |