Instructions to use MatrixIA/LLama-3-8B-SQL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MatrixIA/LLama-3-8B-SQL with Transformers:

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

pipe = pipeline("text-generation", model="MatrixIA/LLama-3-8B-SQL")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MatrixIA/LLama-3-8B-SQL")
model = AutoModelForCausalLM.from_pretrained("MatrixIA/LLama-3-8B-SQL")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MatrixIA/LLama-3-8B-SQL with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MatrixIA/LLama-3-8B-SQL

SGLang

How to use MatrixIA/LLama-3-8B-SQL 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 "MatrixIA/LLama-3-8B-SQL" \
    --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": "MatrixIA/LLama-3-8B-SQL",
		"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 "MatrixIA/LLama-3-8B-SQL" \
        --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": "MatrixIA/LLama-3-8B-SQL",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use MatrixIA/LLama-3-8B-SQL 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 MatrixIA/LLama-3-8B-SQL 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 MatrixIA/LLama-3-8B-SQL to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MatrixIA/LLama-3-8B-SQL to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="MatrixIA/LLama-3-8B-SQL",
    max_seq_length=2048,
)

Docker Model Runner
How to use MatrixIA/LLama-3-8B-SQL with Docker Model Runner:
```
docker model run hf.co/MatrixIA/LLama-3-8B-SQL
```

MatrixIA commited on Apr 22, 2024

Commit

d618572

verified ·

1 Parent(s): 5384dd1

Update config.json

Browse files

Files changed (1) hide show

config.json +39 -31

config.json CHANGED Viewed

@@ -1,34 +1,42 @@
 {
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 16,
-  "rank_pattern": {},
-  "revision": "unsloth",
-  "target_modules": [
-    "q_proj",
-    "gate_proj",
-    "up_proj",
-    "v_proj",
-    "k_proj",
-    "o_proj",
-    "down_proj"
   ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
 }

 {
+  "_name_or_path": "MatrixIA/LLama-3-8B-SQL",
+  "architectures": [
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 128256
 }