Text Generation
Transformers
Safetensors
English
mistral
code-generation
AI
Mirror
LLM
conversational
text-generation-inference
Instructions to use dipeshmajithia/MirrorCode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dipeshmajithia/MirrorCode with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dipeshmajithia/MirrorCode") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dipeshmajithia/MirrorCode") model = AutoModelForCausalLM.from_pretrained("dipeshmajithia/MirrorCode") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use dipeshmajithia/MirrorCode with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dipeshmajithia/MirrorCode" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dipeshmajithia/MirrorCode", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/dipeshmajithia/MirrorCode
- SGLang
How to use dipeshmajithia/MirrorCode with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "dipeshmajithia/MirrorCode" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dipeshmajithia/MirrorCode", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "dipeshmajithia/MirrorCode" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dipeshmajithia/MirrorCode", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use dipeshmajithia/MirrorCode with Docker Model Runner:
docker model run hf.co/dipeshmajithia/MirrorCode
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,26 +16,46 @@ library_name: transformers
|
|
| 16 |
model_creator: "Dipesh Majithia"
|
| 17 |
model_name: Mirror
|
| 18 |
---
|
| 19 |
-
# Mirror Model License
|
| 20 |
|
| 21 |
-
#
|
| 22 |
-
Mirror is licensed under the Apache License, Version 2.0 (the "License");
|
| 23 |
-
you may not use this model except in compliance with the License.
|
| 24 |
-
You may obtain a copy of the License at:
|
| 25 |
|
| 26 |
-
|
|
|
|
| 27 |
|
| 28 |
-
|
| 29 |
-
distributed under the License is distributed on an "AS IS" BASIS,
|
| 30 |
-
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 31 |
|
| 32 |
-
|
| 33 |
-
This model's outputs (such as generated text) and non-code content are licensed under CC-BY-SA 4.0.
|
| 34 |
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
-
|
|
|
|
| 40 |
|
| 41 |
-
|
|
|
|
| 16 |
model_creator: "Dipesh Majithia"
|
| 17 |
model_name: Mirror
|
| 18 |
---
|
|
|
|
| 19 |
|
| 20 |
+
# **Mirror Model Card**
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
+
## **Summary**
|
| 23 |
+
Mirror is a fine-tuned large language model built on **Mistral**, optimized for **code generation, debugging, and structured technical assistance**. It has been trained on the **GPT CodeFeedback dataset**, enhancing its ability to provide **precise, context-aware programming suggestions**. While not a state-of-the-art model, Mirror demonstrates strong **code understanding, refactoring capabilities, and instruction-following behavior**.
|
| 24 |
|
| 25 |
+
The model is fine-tuned using **LoRA** with a focus on **efficient inference** and is designed to assist developers in writing clean, optimized, and well-structured code.
|
|
|
|
|
|
|
| 26 |
|
| 27 |
+
Mirror is available in different configurations to support various deployment environments.
|
|
|
|
| 28 |
|
| 29 |
+
---
|
| 30 |
+
|
| 31 |
+
## **Model Overview**
|
| 32 |
+
Mirror is a **causal language model** based on **Mistral**, trained using **instruction tuning** on a dataset designed to enhance **code review, debugging, and structured programming responses**. The model is intended for:
|
| 33 |
+
- **Code generation** across multiple programming languages.
|
| 34 |
+
- **Code optimization and refactoring suggestions**.
|
| 35 |
+
- **Explaining and debugging errors**.
|
| 36 |
+
- **Providing structured, detailed coding assistance**.
|
| 37 |
+
|
| 38 |
+
---
|
| 39 |
+
|
| 40 |
+
## **LangChain Usage**
|
| 41 |
+
For applications using **LangChain**, set `return_full_text=True` to ensure the full response is returned.
|
| 42 |
+
|
| 43 |
+
```python
|
| 44 |
+
from transformers import pipeline
|
| 45 |
+
from langchain import PromptTemplate, LLMChain
|
| 46 |
+
from langchain.llms import HuggingFacePipeline
|
| 47 |
+
|
| 48 |
+
generate_code = pipeline(model="your-huggingface-username/Mirror",
|
| 49 |
+
torch_dtype=torch.bfloat16,
|
| 50 |
+
trust_remote_code=True,
|
| 51 |
+
device_map="auto",
|
| 52 |
+
return_full_text=True)
|
| 53 |
+
|
| 54 |
+
prompt = PromptTemplate(
|
| 55 |
+
input_variables=["instruction"],
|
| 56 |
+
template="{instruction}")
|
| 57 |
|
| 58 |
+
hf_pipeline = HuggingFacePipeline(pipeline=generate_code)
|
| 59 |
+
llm_chain = LLMChain(llm=hf_pipeline, prompt=prompt)
|
| 60 |
|
| 61 |
+
print(llm_chain.predict(instruction="Write a Python function to check if a number is prime."))
|