Instructions to use S-miguel/The-Trinity-Coder-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use S-miguel/The-Trinity-Coder-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="S-miguel/The-Trinity-Coder-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("S-miguel/The-Trinity-Coder-7B")
model = AutoModelForCausalLM.from_pretrained("S-miguel/The-Trinity-Coder-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use S-miguel/The-Trinity-Coder-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "S-miguel/The-Trinity-Coder-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "S-miguel/The-Trinity-Coder-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/S-miguel/The-Trinity-Coder-7B

SGLang

How to use S-miguel/The-Trinity-Coder-7B 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 "S-miguel/The-Trinity-Coder-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "S-miguel/The-Trinity-Coder-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "S-miguel/The-Trinity-Coder-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "S-miguel/The-Trinity-Coder-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use S-miguel/The-Trinity-Coder-7B with Docker Model Runner:
```
docker model run hf.co/S-miguel/The-Trinity-Coder-7B
```

S-miguel commited on Mar 22, 2024

Commit

e2628b8

verified ·

1 Parent(s): 284cf27

Update README.md

Browse files

Files changed (1) hide show

README.md +34 -3

README.md CHANGED Viewed

@@ -1,3 +1,34 @@
----
-license: apache-2.0
----

+<h1>The-Trinity-Coder-7B: III Blended Coder Models - Unified Coding Intelligence</h1>
+<p><strong>Overview</strong></p>
+<p>The-Trinity-Coder-7B derives from the fusion of three distinct AI models, each specializing in unique aspects of coding and programming challenges. This model unifies the capabilities of CodeNinja, NeuralExperiment-7b-MagicCoder, and Speechless-Zephyr-Code-Functionary-7B, creating a versatile and powerful new blended model. The integration of these models was achieved through a merging technique, in order to harmonize their strengths and mitigate their individual weaknesses.</p>
+<h2>The Blend</h2>
+<ul>
+  <li><strong>Comprehensive Coding Knowledge:</strong> TrinityAI combines over 400,000 coding instructions across a wide array of programming languages, including Python, C, C++, Rust, Java, JavaScript, and more, making it a versatile assistant for coding projects of any scale.</li>
+  <li><strong>Advanced Code Completion:</strong> With its extensive context window, TrinityAI excels in project-level code completion, offering suggestions that are contextually relevant and syntactically accurate.</li>
+  <li><strong>Specialized Skills Integration:</strong> By incorporating specific datasets and fine-tuning approaches, The-Trinity-Coder not only provides code completion but also excels in logical reasoning, mathematical problem-solving, and understanding complex programming concepts.</li>
+</ul>
+<h2>Model Synthesis Approach</h2>
+<p>The blending of the three models into TrinityAI utilized a unique merging technique that focused on preserving the core strengths of each component model:</p>
+<ul>
+  <li><strong>CodeNinja:</strong> This model brings an expansive database of coding instructions, refined through Supervised Fine Tuning, making it an advanced coding assistant.</li>
+  <li><strong>NeuralExperiment-7b-MagicCoder:</strong> Trained on datasets focusing on logical reasoning, mathematics, and programming, this model enhances TrinityAI's problem-solving and logical reasoning capabilities.</li>
+  <li><strong>Speechless-Zephyr-Code-Functionary-7B:</strong> Part of the Moloras experiments, this model contributes enhanced coding proficiency and dynamic skill integration through its unique LoRA modules.</li>
+</ul>
+<h2>Usage and Implementation</h2>
+<pre><code>from transformers import AutoTokenizer, AutoModelForCausalLM
+model_name = "YourRepository/The-Trinity-Coder-7B"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+prompt = "Your prompt here"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+</code></pre>
+<h2>Acknowledgments</h2>
+<p>Special thanks to the creators and contributors of CodeNinja, NeuralExperiment-7b-MagicCoder, and Speechless-Zephyr-Code-Functionary-7B for providing the base models for blending.</p>