Instructions to use neural-coder/llama-3-8b-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neural-coder/llama-3-8b-ft with Transformers:

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

pipe = pipeline("text-generation", model="neural-coder/llama-3-8b-ft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("neural-coder/llama-3-8b-ft")
model = AutoModelForCausalLM.from_pretrained("neural-coder/llama-3-8b-ft", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use neural-coder/llama-3-8b-ft with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use neural-coder/llama-3-8b-ft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neural-coder/llama-3-8b-ft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neural-coder/llama-3-8b-ft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/neural-coder/llama-3-8b-ft

SGLang

How to use neural-coder/llama-3-8b-ft 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 "neural-coder/llama-3-8b-ft" \
    --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": "neural-coder/llama-3-8b-ft",
		"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 "neural-coder/llama-3-8b-ft" \
        --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": "neural-coder/llama-3-8b-ft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use neural-coder/llama-3-8b-ft with Docker Model Runner:
```
docker model run hf.co/neural-coder/llama-3-8b-ft
```

neural-coder commited on Apr 14, 2025

Commit

dfd954b

verified ·

1 Parent(s): 9d1f32f

Delete training_params.json

Browse files

Files changed (1) hide show

training_params.json +0 -49

training_params.json DELETED Viewed

@@ -1,49 +0,0 @@
-{
-    "model": "Team-ACE/ToolACE-2-Llama-3.1-8B",
-    "project_name": "llama-3-8b-ft",
-    "data_path": "llama-3-8b-ft/autotrain-data",
-    "train_split": "train",
-    "valid_split": null,
-    "add_eos_token": true,
-    "block_size": -1,
-    "model_max_length": 2048,
-    "padding": "right",
-    "trainer": "sft",
-    "use_flash_attention_2": false,
-    "log": "none",
-    "disable_gradient_checkpointing": false,
-    "logging_steps": 5,
-    "eval_strategy": "epoch",
-    "save_total_limit": 3,
-    "auto_find_batch_size": false,
-    "mixed_precision": null,
-    "lr": 5e-06,
-    "epochs": 1,
-    "batch_size": 1,
-    "warmup_ratio": 0.1,
-    "gradient_accumulation": 1,
-    "optimizer": "adamw_torch",
-    "scheduler": "cosine_with_restarts",
-    "weight_decay": 0.0001,
-    "max_grad_norm": 0.3,
-    "seed": 42,
-    "chat_template": null,
-    "quantization": "int8",
-    "target_modules": "q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj",
-    "merge_adapter": true,
-    "peft": true,
-    "lora_r": 128,
-    "lora_alpha": 256,
-    "lora_dropout": 0.05,
-    "model_ref": null,
-    "dpo_beta": 0.1,
-    "max_prompt_length": 128,
-    "max_completion_length": null,
-    "prompt_text_column": "autotrain_prompt",
-    "text_column": "autotrain_text",
-    "rejected_text_column": "autotrain_rejected_text",
-    "push_to_hub": true,
-    "username": "neural-coder",
-    "unsloth": false,
-    "distributed_backend": null
-}