Instructions to use cochi1706/codingassistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cochi1706/codingassistant with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B")
model = PeftModel.from_pretrained(base_model, "cochi1706/codingassistant")

Transformers

How to use cochi1706/codingassistant with Transformers:

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

pipe = pipeline("text-generation", model="cochi1706/codingassistant")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("cochi1706/codingassistant", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cochi1706/codingassistant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cochi1706/codingassistant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cochi1706/codingassistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cochi1706/codingassistant

SGLang

How to use cochi1706/codingassistant 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 "cochi1706/codingassistant" \
    --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": "cochi1706/codingassistant",
		"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 "cochi1706/codingassistant" \
        --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": "cochi1706/codingassistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cochi1706/codingassistant with Docker Model Runner:
```
docker model run hf.co/cochi1706/codingassistant
```

cochi1706 commited on Nov 30, 2025

Commit

bb13fba

verified ·

1 Parent(s): 807943c

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +2 -2
tokenizer_config.json +7 -0

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:574de68a0f63f2004784a421c7d42c2b2786c05cb38542d2ed3525757a1f7fde
-size 11422932

 version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json CHANGED Viewed

@@ -231,9 +231,16 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null
 }

   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "max_length": 512,
   "model_max_length": 131072,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "split_special_tokens": false,
+  "stride": 0,
   "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": null
 }