Instructions to use Sharan1712/mistralai-7-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sharan1712/mistralai-7-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Sharan1712/mistralai-7-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sharan1712/mistralai-7-Instruct")
model = AutoModelForCausalLM.from_pretrained("Sharan1712/mistralai-7-Instruct")
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 Sharan1712/mistralai-7-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sharan1712/mistralai-7-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sharan1712/mistralai-7-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sharan1712/mistralai-7-Instruct

SGLang

How to use Sharan1712/mistralai-7-Instruct 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 "Sharan1712/mistralai-7-Instruct" \
    --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": "Sharan1712/mistralai-7-Instruct",
		"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 "Sharan1712/mistralai-7-Instruct" \
        --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": "Sharan1712/mistralai-7-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sharan1712/mistralai-7-Instruct with Docker Model Runner:
```
docker model run hf.co/Sharan1712/mistralai-7-Instruct
```

Sharan1712 commited on Nov 7, 2023

Commit

de657d6

1 Parent(s): 5cf91d6

Upload MistralForCausalLM

Browse files

Files changed (4) hide show

config.json +1 -1
pytorch_model-00001-of-00003.bin +1 -1
pytorch_model-00002-of-00003.bin +1 -1
pytorch_model-00003-of-00003.bin +1 -1

config.json CHANGED Viewed

@@ -18,7 +18,7 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
   "transformers_version": "4.35.0.dev0",
   "use_cache": true,
   "vocab_size": 32000

   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.35.0.dev0",
   "use_cache": true,
   "vocab_size": 32000

pytorch_model-00001-of-00003.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35d5c05ba5d0636fd3cab132d1c727a28bf51d052abbfc860ecc2cc0212b5db6
 size 4943184288

 version https://git-lfs.github.com/spec/v1
+oid sha256:c592e00b47ce0443eec12d264fb58d0678a01d3853b0be7a7ac84b6d4ee85542
 size 4943184288

pytorch_model-00002-of-00003.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d56795a5379193b303368ae3159595a734ea16b0beb331b0db8cb8cc017046f
 size 4999843272

 version https://git-lfs.github.com/spec/v1
+oid sha256:238a9a789c46b3b2d8288d0fb0663a9ae255b8da28d29bfda4cc89264fd355fe
 size 4999843272

pytorch_model-00003-of-00003.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4007d42f36be62868a03805f388a6b545422715d492d8a27235c315ea144d98
 size 4540536134

 version https://git-lfs.github.com/spec/v1
+oid sha256:29ed03f334b3edde26cfce8b763fcbffb22cfed259603792adfc1e5e9ac592d6
 size 4540536134