Instructions to use roif123/mistral_7b-instruct-data2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use roif123/mistral_7b-instruct-data2 with Transformers:

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

pipe = pipeline("text-generation", model="roif123/mistral_7b-instruct-data2")

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

tokenizer = AutoTokenizer.from_pretrained("roif123/mistral_7b-instruct-data2")
model = AutoModelForCausalLM.from_pretrained("roif123/mistral_7b-instruct-data2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use roif123/mistral_7b-instruct-data2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "roif123/mistral_7b-instruct-data2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "roif123/mistral_7b-instruct-data2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/roif123/mistral_7b-instruct-data2

SGLang

How to use roif123/mistral_7b-instruct-data2 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 "roif123/mistral_7b-instruct-data2" \
    --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": "roif123/mistral_7b-instruct-data2",
		"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 "roif123/mistral_7b-instruct-data2" \
        --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": "roif123/mistral_7b-instruct-data2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use roif123/mistral_7b-instruct-data2 with Docker Model Runner:
```
docker model run hf.co/roif123/mistral_7b-instruct-data2
```

roif123 commited on May 22, 2024

Commit

00c2212

verified ·

1 Parent(s): e884126

Upload config.json

Browse files

Files changed (1) hide show

config.json +21 -0

config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+    "architectures": [
+        "GPT2LMHeadModel"
+    ],
+    "model_type": "gpt2",
+    "vocab_size": 50257,
+    "n_positions": 1024,
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_layer": 12,
+    "n_head": 12,
+    "activation_function": "gelu_new",
+    "initializer_range": 0.02,
+    "layer_norm_epsilon": 1e-05,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "summary_activation": "gelu",
+    "summary_proj_to_labels": true,
+    "summary_first_dropout": 0.1,
+    "use_cache": true
+}