Instructions to use dbands/llama-3-8b-sql-instruct_4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dbands/llama-3-8b-sql-instruct_4bit with Transformers:

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

pipe = pipeline("text-generation", model="dbands/llama-3-8b-sql-instruct_4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dbands/llama-3-8b-sql-instruct_4bit")
model = AutoModelForCausalLM.from_pretrained("dbands/llama-3-8b-sql-instruct_4bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dbands/llama-3-8b-sql-instruct_4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dbands/llama-3-8b-sql-instruct_4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbands/llama-3-8b-sql-instruct_4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dbands/llama-3-8b-sql-instruct_4bit

SGLang

How to use dbands/llama-3-8b-sql-instruct_4bit 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 "dbands/llama-3-8b-sql-instruct_4bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbands/llama-3-8b-sql-instruct_4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "dbands/llama-3-8b-sql-instruct_4bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbands/llama-3-8b-sql-instruct_4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use dbands/llama-3-8b-sql-instruct_4bit with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for dbands/llama-3-8b-sql-instruct_4bit to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for dbands/llama-3-8b-sql-instruct_4bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dbands/llama-3-8b-sql-instruct_4bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="dbands/llama-3-8b-sql-instruct_4bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use dbands/llama-3-8b-sql-instruct_4bit with Docker Model Runner:
```
docker model run hf.co/dbands/llama-3-8b-sql-instruct_4bit
```

dbands commited on Apr 28, 2024

Commit

91e761c

verified ·

1 Parent(s): 40c8826

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (4) hide show

config.json +2 -2
model-00001-of-00002.safetensors +2 -2
model-00002-of-00002.safetensors +1 -1
model.safetensors.index.json +1 -1

config.json CHANGED Viewed

@@ -18,7 +18,7 @@
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -33,7 +33,7 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
   "transformers_version": "4.40.0",
   "unsloth_version": "2024.4",
   "use_cache": true,

   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",
   "unsloth_version": "2024.4",
   "use_cache": true,

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3e2fff3576c64acf996583a43bc5cefffb977cc2bda189b40b4117b120d9bef
-size 4652072867

 version https://git-lfs.github.com/spec/v1
+oid sha256:ed8dafd1e3ecabbec909d807581eb3030a61086f0efaf2d30295a9f0f5540283
+size 4652072923

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f15e64381b74dcb7857c03cbfb62806534f7582ab885c738980a12e5b78989
 size 1050673280

 version https://git-lfs.github.com/spec/v1
+oid sha256:7c5394fe848f6eafef2a44f085e7b72e5ef0d315f98aa87b3827c2b1e6983b89
 size 1050673280

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5702577747
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",

 {
   "metadata": {
+    "total_size": 5702577739
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",