Instructions to use pshashid/llama3.1B_8B_SQL_Finetuned_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pshashid/llama3.1B_8B_SQL_Finetuned_model with Transformers:

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

pipe = pipeline("text-generation", model="pshashid/llama3.1B_8B_SQL_Finetuned_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pshashid/llama3.1B_8B_SQL_Finetuned_model")
model = AutoModelForCausalLM.from_pretrained("pshashid/llama3.1B_8B_SQL_Finetuned_model")
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 pshashid/llama3.1B_8B_SQL_Finetuned_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pshashid/llama3.1B_8B_SQL_Finetuned_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": "pshashid/llama3.1B_8B_SQL_Finetuned_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pshashid/llama3.1B_8B_SQL_Finetuned_model

SGLang

How to use pshashid/llama3.1B_8B_SQL_Finetuned_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 "pshashid/llama3.1B_8B_SQL_Finetuned_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": "pshashid/llama3.1B_8B_SQL_Finetuned_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 "pshashid/llama3.1B_8B_SQL_Finetuned_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": "pshashid/llama3.1B_8B_SQL_Finetuned_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pshashid/llama3.1B_8B_SQL_Finetuned_model with Docker Model Runner:
```
docker model run hf.co/pshashid/llama3.1B_8B_SQL_Finetuned_model
```

Llama 3.1 8B SQL — NVFP4 Quantized (Blackwell)

SQL generation model fine-tuned on text-to-SQL tasks, quantized for NVIDIA Blackwell (RTX 50-series) using llm-compressor.

Quantization Details

Component	Format	Notes
Weights	NVFP4	~4.5GB — Blackwell 5th-gen Tensor Core native
KV-Cache	FP8	50% memory vs FP16 — configured via vLLM
Activations	FP16	`lm_head` kept in FP16 for output quality

vLLM Inference (RTX 5090)

vllm serve pshashid/llama3.1B_8B_SQL_Finetuned_model \
  --dtype float16 \
  --quantization fp4 \
  --kv-cache-dtype fp8 \
  --max-model-len 131072 \
  --gpu-memory-utilization 0.85 \
  --enable-prefix-caching \
  --port 8000

Performance Targets (Dual RTX 5090 Pod — 8 Replicas)

Metric	Target
Time to First Token	< 15ms
Throughput (1 replica)	~200 tok/s
Aggregate (8 replicas)	1,500+ tok/s
Max Concurrency	100+ users

Example Usage (Python)

from vllm import LLM, SamplingParams

llm = LLM(
    model                  = "pshashid/llama3.1B_8B_SQL_Finetuned_model",
    quantization           = "fp4",
    kv_cache_dtype         = "fp8",
    max_model_len          = 131072,
    enable_prefix_caching  = True,
)

sampling = SamplingParams(temperature=0, max_tokens=200)
outputs  = llm.generate(["SELECT"], sampling)
print(outputs[0].outputs[0].text)

Downloads last month: 6

Safetensors

Model size

5B params

Tensor type

F16

F32

F8_E4M3

Model tree for pshashid/llama3.1B_8B_SQL_Finetuned_model

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Quantized

(628)

this model