Instructions to use DCAgent/a1-magicoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DCAgent/a1-magicoder with Transformers:

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

pipe = pipeline("text-generation", model="DCAgent/a1-magicoder")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DCAgent/a1-magicoder")
model = AutoModelForCausalLM.from_pretrained("DCAgent/a1-magicoder")
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 DCAgent/a1-magicoder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DCAgent/a1-magicoder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DCAgent/a1-magicoder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DCAgent/a1-magicoder

SGLang

How to use DCAgent/a1-magicoder 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 "DCAgent/a1-magicoder" \
    --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": "DCAgent/a1-magicoder",
		"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 "DCAgent/a1-magicoder" \
        --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": "DCAgent/a1-magicoder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DCAgent/a1-magicoder with Docker Model Runner:
```
docker model run hf.co/DCAgent/a1-magicoder
```

EtashGuha commited on Apr 4

Commit

7114d11

verified ·

1 Parent(s): f436e9b

Upload folder using huggingface_hub

Browse files

Files changed (8) hide show

all_results.json +9 -9
model-00001-of-00004.safetensors +1 -1
model-00002-of-00004.safetensors +1 -1
model-00003-of-00004.safetensors +1 -1
model-00004-of-00004.safetensors +1 -1
train_results.json +9 -9
trainer_log.jsonl +0 -0
training_loss.png +0 -0

all_results.json CHANGED Viewed

@@ -1,16 +1,16 @@
 {
-    "achieved_tflops_per_gpu": 0.002110187398451811,
-    "achieved_tflops_per_gpu_theoretical": 650.4776760620482,
     "epoch": 7.0,
     "loss_nan_ranks": 0,
-    "loss_rank_avg": 0.2384590357542038,
-    "mfu_percent": 0.00014912985148069337,
-    "mfu_percent_theoretical": 45.97015378530376,
     "total_flos": 688651439570944.0,
-    "train_loss": 0.26049303336732077,
-    "train_runtime": 20396.6316,
-    "train_samples_per_second": 3.064,
-    "train_steps_per_second": 0.192,
     "valid_targets_mean": 4082.4,
     "valid_targets_min": 866
 }

 {
+    "achieved_tflops_per_gpu": 0.002083037344637663,
+    "achieved_tflops_per_gpu_theoretical": 640.3139623735788,
     "epoch": 7.0,
     "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.2396668791770935,
+    "mfu_percent": 0.000147211119762379,
+    "mfu_percent_theoretical": 45.25187013240839,
     "total_flos": 688651439570944.0,
+    "train_loss": 0.26112440031201767,
+    "train_runtime": 20662.4788,
+    "train_samples_per_second": 3.025,
+    "train_steps_per_second": 0.189,
     "valid_targets_mean": 4082.4,
     "valid_targets_min": 866
 }

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daffa32e7444e736a1c517d62c2a55d9f96260371213ac37e97ac9827b55b478
 size 4902257696

 version https://git-lfs.github.com/spec/v1
+oid sha256:47f3aa434710f7fda3f3fa23057b2e062a6aa19ca2d59a9b13e40fdd97429883
 size 4902257696

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfe4bb96e03e07782586ca63884f59543a475c5932ac4ccf440848b3736ff540
 size 4915960368

 version https://git-lfs.github.com/spec/v1
+oid sha256:b1a0fd930bff3c69df9149615c3cf4e670eed5c7a0c04e8c233a8bab64be4fac
 size 4915960368

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc931313941b618ca7de44a63927fa3a1e43ed4b723a103c01493d683889d17b
 size 4983068496

 version https://git-lfs.github.com/spec/v1
+oid sha256:dca3424fb65168ebb5b237c408c5676171d377664a4284a3e8789d97f07f9644
 size 4983068496

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab55fd4c4fd1cdb8d41f5aee283940231d28eba52cc99ebf70cf3cbf11b598d
 size 1580230264

 version https://git-lfs.github.com/spec/v1
+oid sha256:4ee02a580f9fe64b849fa281316175c784a52a8823b4120b1f3a7330abd09598
 size 1580230264

train_results.json CHANGED Viewed

@@ -1,16 +1,16 @@
 {
-    "achieved_tflops_per_gpu": 0.002110187398451811,
-    "achieved_tflops_per_gpu_theoretical": 650.4776760620482,
     "epoch": 7.0,
     "loss_nan_ranks": 0,
-    "loss_rank_avg": 0.2384590357542038,
-    "mfu_percent": 0.00014912985148069337,
-    "mfu_percent_theoretical": 45.97015378530376,
     "total_flos": 688651439570944.0,
-    "train_loss": 0.26049303336732077,
-    "train_runtime": 20396.6316,
-    "train_samples_per_second": 3.064,
-    "train_steps_per_second": 0.192,
     "valid_targets_mean": 4082.4,
     "valid_targets_min": 866
 }

 {
+    "achieved_tflops_per_gpu": 0.002083037344637663,
+    "achieved_tflops_per_gpu_theoretical": 640.3139623735788,
     "epoch": 7.0,
     "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.2396668791770935,
+    "mfu_percent": 0.000147211119762379,
+    "mfu_percent_theoretical": 45.25187013240839,
     "total_flos": 688651439570944.0,
+    "train_loss": 0.26112440031201767,
+    "train_runtime": 20662.4788,
+    "train_samples_per_second": 3.025,
+    "train_steps_per_second": 0.189,
     "valid_targets_mean": 4082.4,
     "valid_targets_min": 866
 }

trainer_log.jsonl CHANGED Viewed

The diff for this file is too large to render. See raw diff

training_loss.png CHANGED Viewed