Instructions to use Nayan7r839/echooai-coding-beast-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nayan7r839/echooai-coding-beast-v0.1 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "Nayan7r839/echooai-coding-beast-v0.1")

Transformers

How to use Nayan7r839/echooai-coding-beast-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="Nayan7r839/echooai-coding-beast-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Nayan7r839/echooai-coding-beast-v0.1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nayan7r839/echooai-coding-beast-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nayan7r839/echooai-coding-beast-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nayan7r839/echooai-coding-beast-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nayan7r839/echooai-coding-beast-v0.1

SGLang

How to use Nayan7r839/echooai-coding-beast-v0.1 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 "Nayan7r839/echooai-coding-beast-v0.1" \
    --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": "Nayan7r839/echooai-coding-beast-v0.1",
		"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 "Nayan7r839/echooai-coding-beast-v0.1" \
        --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": "Nayan7r839/echooai-coding-beast-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nayan7r839/echooai-coding-beast-v0.1 with Docker Model Runner:
```
docker model run hf.co/Nayan7r839/echooai-coding-beast-v0.1
```

real-session data for the next coding beast (free)

by Sumama-Dev1 - opened about 1 hour ago

Discussion

Sumama-Dev1

about 1 hour ago

hey Nayan, saw echooai-coding-beast and that you published the training data next to the model. that habit is rare, so I'll match it: my data ships with its own checker. 66 recorded sessions of an AI fixing real bugs in real repos. every command actually ran, real errors and retries kept, tests passing at the end, each session scored against the human fix. verify.py re-checks the whole set offline before you spend a minute of GPU on it.

built to improve coding, tool calling, agentic execution, and recovery from failure. it's for pretraining (continued pretraining), not fine-tuning.

first 100 are free, and we're at 66, so everything is free right now:
https://github.com/Sumama-Jameel/megabit-trajectories

if you fold it into the next beast version, tell me what it did to your evals, good or bad.
Sumama

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment