Instructions to use girish00/ConicAI_LLM_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use girish00/ConicAI_LLM_model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-0.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "girish00/ConicAI_LLM_model")

Transformers

How to use girish00/ConicAI_LLM_model with Transformers:

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

pipe = pipeline("text-generation", model="girish00/ConicAI_LLM_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("girish00/ConicAI_LLM_model")
model = AutoModelForCausalLM.from_pretrained("girish00/ConicAI_LLM_model", device_map="auto")
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 Settings

vLLM

How to use girish00/ConicAI_LLM_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "girish00/ConicAI_LLM_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "girish00/ConicAI_LLM_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/girish00/ConicAI_LLM_model

SGLang

How to use girish00/ConicAI_LLM_model 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 "girish00/ConicAI_LLM_model" \
    --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": "girish00/ConicAI_LLM_model",
		"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 "girish00/ConicAI_LLM_model" \
        --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": "girish00/ConicAI_LLM_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use girish00/ConicAI_LLM_model with Docker Model Runner:
```
docker model run hf.co/girish00/ConicAI_LLM_model
```

girish00 commited on Apr 19

Commit

0a19b76

verified ·

1 Parent(s): a9cd333

improve cloud inference fallback

Browse files

Files changed (1) hide show

IMPLEMENTATION.md +3 -1

IMPLEMENTATION.md CHANGED Viewed

@@ -26,6 +26,7 @@ Build and run a local fine-tuning pipeline for a coding assistant model with:
 - `infer_cloud.py`
   - Runs inference through the Hugging Face API using an HF token.
   - Reuses the local structured-output parser and repair checks so API output matches the local JSON contract.
 - `evaluate_model.py`
   - Runs a multi-prompt evaluation and reports pass rate (accuracy) for schema + quality checks.
 - `upload_to_hf.py`
@@ -55,6 +56,7 @@ Build and run a local fine-tuning pipeline for a coding assistant model with:
    - PowerShell: `$env:HF_TOKEN="your_huggingface_token"`
    - `python infer_cloud.py --repo-id your-username/your-model-name --prompt "Fix this code: def add(a,b) return a+b"`
    - If you already logged in with `hf auth login`, the saved token can be used without setting `HF_TOKEN`.
 ## One-Command Execution
@@ -112,4 +114,4 @@ Optional safer rollout:
 - `hallucination_check_reason`
 - `latency_ms`
-`infer_cloud.py` returns the same JSON keys through the Hugging Face API. Cloud responses may not include token-level probabilities, so `important_tokens` can be empty and `confidence` can be `0.0` unless the serving endpoint exposes token details.

 - `infer_cloud.py`
   - Runs inference through the Hugging Face API using an HF token.
   - Reuses the local structured-output parser and repair checks so API output matches the local JSON contract.
+  - Falls back to the local `model/` folder when Hugging Face does not serve the custom repo through an inference provider.
 - `evaluate_model.py`
   - Runs a multi-prompt evaluation and reports pass rate (accuracy) for schema + quality checks.
 - `upload_to_hf.py`
    - PowerShell: `$env:HF_TOKEN="your_huggingface_token"`
    - `python infer_cloud.py --repo-id your-username/your-model-name --prompt "Fix this code: def add(a,b) return a+b"`
    - If you already logged in with `hf auth login`, the saved token can be used without setting `HF_TOKEN`.
+   - Add `--no-local-fallback` if you want the command to fail when HF cloud serving is unavailable.
 ## One-Command Execution
 - `hallucination_check_reason`
 - `latency_ms`
+`infer_cloud.py` returns the same JSON keys through the Hugging Face API, or through local fallback if HF cannot serve the custom repo. Cloud responses may not include token-level probabilities, so `important_tokens` can be empty and `confidence` can be `0.0` unless the serving endpoint exposes token details.