Text Generation
Transformers
Safetensors
PyTorch
Korean
English
mistral
conversational
text-generation-inference
Instructions to use beomi/Mistral-Ko-Inst-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use beomi/Mistral-Ko-Inst-dev with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="beomi/Mistral-Ko-Inst-dev") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("beomi/Mistral-Ko-Inst-dev") model = AutoModelForCausalLM.from_pretrained("beomi/Mistral-Ko-Inst-dev", device_map="auto") 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 Settings
- vLLM
How to use beomi/Mistral-Ko-Inst-dev with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "beomi/Mistral-Ko-Inst-dev" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "beomi/Mistral-Ko-Inst-dev", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/beomi/Mistral-Ko-Inst-dev
- SGLang
How to use beomi/Mistral-Ko-Inst-dev 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 "beomi/Mistral-Ko-Inst-dev" \ --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": "beomi/Mistral-Ko-Inst-dev", "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 "beomi/Mistral-Ko-Inst-dev" \ --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": "beomi/Mistral-Ko-Inst-dev", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use beomi/Mistral-Ko-Inst-dev with Docker Model Runner:
docker model run hf.co/beomi/Mistral-Ko-Inst-dev
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,3 +12,43 @@ tags:
|
|
| 12 |
---
|
| 13 |
|
| 14 |
Experimental Repository :)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
Experimental Repository :)
|
| 15 |
+
|
| 16 |
+
Here's some test:
|
| 17 |
+
|
| 18 |
+
```python
|
| 19 |
+
from transformers import pipeline
|
| 20 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 21 |
+
|
| 22 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 23 |
+
'beomi/Mistral-Ko-Inst-dev',
|
| 24 |
+
torch_dtype='auto',
|
| 25 |
+
device_map='auto',
|
| 26 |
+
)
|
| 27 |
+
tokenizer = AutoTokenizer.from_pretrained('beomi/Mistral-Ko-Inst-dev')
|
| 28 |
+
|
| 29 |
+
pipe = pipeline(
|
| 30 |
+
'text-generation',
|
| 31 |
+
model=model,
|
| 32 |
+
tokenizer=tokenizer,
|
| 33 |
+
do_sample=True,
|
| 34 |
+
max_new_tokens=350,
|
| 35 |
+
return_full_text=False,
|
| 36 |
+
no_repeat_ngram_size=6,
|
| 37 |
+
eos_token_id=1, # not yet tuned to gen </s>, use <s> instead.
|
| 38 |
+
)
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
def gen(x):
|
| 42 |
+
chat = tokenizer.apply_chat_template([
|
| 43 |
+
{"role": "user", "content": x},
|
| 44 |
+
# {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
|
| 45 |
+
# {"role": "user", "content": "Do you have mayonnaise recipes? please say in Korean."}
|
| 46 |
+
], tokenize=False)
|
| 47 |
+
print(pipe(chat)[0]['generated_text'].strip())
|
| 48 |
+
|
| 49 |
+
gen("μ€νλ²
μ€μ μ€νλ²
μ€ μ½λ¦¬μμ μ°¨μ΄λ?")
|
| 50 |
+
|
| 51 |
+
# (μμ± μμ)
|
| 52 |
+
# μ€νλ²
μ€λ μ μΈκ³μ μΌλ‘ μ΄μνκ³ μλ μ»€νΌ μ λ¬Έμ¬μ΄λ€. νκ΅μλ μ€νλ²
μ€ μ½λ¦¬μλΌλ μ΄λ¦μΌλ‘ μ΄μλκ³ μλ€.
|
| 53 |
+
# μ€νλ²
μ€ μ½λ¦¬μλ λνλ―Όκ΅μ μ
μ ν μ΄ν 2009λ
κ³Ό 2010λ
μ λ μ°¨λ‘μ λΈλλκ³Όμ μ¬κ²ν λ° μλ‘μ΄ λμμΈμ ν΅ν΄ μλ‘μ΄ λΈλλλ€. μ»€νΌ μ λ¬Έμ ν리미μ μ΄λ―Έμ§λ₯Ό μ μ§νκ³ μκ³ , μ€νλ²
μ€ μ½λ¦¬μλ νκ΅μ λννλ ν리미μ μ»€νΌ μ λ¬Έ λΈλλμ λ§λ€κ³ μλ€.
|
| 54 |
+
```
|