Instructions to use amkyawdev/amk-coder-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amkyawdev/amk-coder-v2 with Transformers:

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

pipe = pipeline("text-generation", model="amkyawdev/amk-coder-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("amkyawdev/amk-coder-v2")
model = AutoModelForCausalLM.from_pretrained("amkyawdev/amk-coder-v2")
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 amkyawdev/amk-coder-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amkyawdev/amk-coder-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amkyawdev/amk-coder-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amkyawdev/amk-coder-v2

SGLang

How to use amkyawdev/amk-coder-v2 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 "amkyawdev/amk-coder-v2" \
    --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": "amkyawdev/amk-coder-v2",
		"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 "amkyawdev/amk-coder-v2" \
        --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": "amkyawdev/amk-coder-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amkyawdev/amk-coder-v2 with Docker Model Runner:
```
docker model run hf.co/amkyawdev/amk-coder-v2
```

amkyawdev commited on 2 days ago

Commit

0ded1ae

verified ·

1 Parent(s): 5dd6c3c

Update config.json

Browse files

Files changed (1) hide show

config.json +6 -40

config.json CHANGED Viewed

@@ -4,58 +4,24 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "dtype": "bfloat16",
   "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
-  "layer_types": [
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention"
-  ],
   "max_position_embeddings": 32768,
-  "max_window_layers": 28,
   "model_type": "qwen2",
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
-  "pad_token_id": null,
   "rms_norm_eps": 1e-06,
-  "rope_parameters": {
-    "rope_theta": 1000000.0,
-    "rope_type": "default"
-  },
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "transformers_version": "5.0.0",
-  "use_cache": false,
-  "use_sliding_window": false,
   "vocab_size": 151936
 }

   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
+  "dtype": "float16",
   "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
   "max_position_embeddings": 32768,
   "model_type": "qwen2",
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
+  "pad_token_id": 151643,
   "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
+  "transformers_version": "4.45.0",
+  "use_cache": true,
   "vocab_size": 151936
 }