Instructions to use jrc/phi3-mini-math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jrc/phi3-mini-math with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jrc/phi3-mini-math", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jrc/phi3-mini-math", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("jrc/phi3-mini-math", trust_remote_code=True, 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jrc/phi3-mini-math with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jrc/phi3-mini-math" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jrc/phi3-mini-math", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/jrc/phi3-mini-math
- SGLang
How to use jrc/phi3-mini-math 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 "jrc/phi3-mini-math" \ --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": "jrc/phi3-mini-math", "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 "jrc/phi3-mini-math" \ --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": "jrc/phi3-mini-math", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use jrc/phi3-mini-math with Docker Model Runner:
docker model run hf.co/jrc/phi3-mini-math
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ Phi-3 Mini 4k Instruct model finetuned on math datasets.
|
|
| 25 |
|
| 26 |
Use the code below to get started with the model.
|
| 27 |
|
| 28 |
-
```
|
| 29 |
# Load model directly
|
| 30 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 31 |
|
|
@@ -38,7 +38,7 @@ model = AutoModelForCausalLM.from_pretrained("jrc/phi3-mini-math", trust_remote_
|
|
| 38 |
Phi3 was trained using [torchtune]() and the training script + config file are located in this repository.
|
| 39 |
|
| 40 |
CMD:
|
| 41 |
-
```
|
| 42 |
tune run lora_finetune_distributed.py --config mini_lora.yaml
|
| 43 |
```
|
| 44 |
|
|
@@ -57,7 +57,7 @@ tune run lora_finetune_distributed.py --config mini_lora.yaml
|
|
| 57 |
The finetuned model is evaluated on [minerva-math](https://research.google/blog/minerva-solving-quantitative-reasoning-problems-with-language-models/) using [EleutherAI Eval Harness](https://github.com/EleutherAI/lm-evaluation-harness) through torchtune.
|
| 58 |
|
| 59 |
CMD:
|
| 60 |
-
```
|
| 61 |
tune run eleuther_eval --config eleuther_evaluation \
|
| 62 |
checkpoint.checkpoint_dir=./lora-phi3-math \
|
| 63 |
tasks=["minerva_math"] \
|
|
@@ -65,7 +65,7 @@ tune run eleuther_eval --config eleuther_evaluation \
|
|
| 65 |
```
|
| 66 |
|
| 67 |
RESULTS:
|
| 68 |
-
|
| 69 |
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
| 70 |
|------------------------------------|-------|------|-----:|-----------|-----:|---|-----:|
|
| 71 |
|minerva_math |N/A |none | 4|exact_match|0.1670|± |0.0051|
|
|
@@ -76,7 +76,7 @@ RESULTS:
|
|
| 76 |
| - minerva_math_num_theory | 1|none | 4|exact_match|0.1148|± |0.0137|
|
| 77 |
| - minerva_math_prealgebra | 1|none | 4|exact_match|0.3077|± |0.0156|
|
| 78 |
| - minerva_math_precalc | 1|none | 4|exact_match|0.0623|± |0.0104|
|
| 79 |
-
|
| 80 |
|
| 81 |
|
| 82 |
## Technical Specifications [optional]
|
|
|
|
| 25 |
|
| 26 |
Use the code below to get started with the model.
|
| 27 |
|
| 28 |
+
```python
|
| 29 |
# Load model directly
|
| 30 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 31 |
|
|
|
|
| 38 |
Phi3 was trained using [torchtune]() and the training script + config file are located in this repository.
|
| 39 |
|
| 40 |
CMD:
|
| 41 |
+
```bash
|
| 42 |
tune run lora_finetune_distributed.py --config mini_lora.yaml
|
| 43 |
```
|
| 44 |
|
|
|
|
| 57 |
The finetuned model is evaluated on [minerva-math](https://research.google/blog/minerva-solving-quantitative-reasoning-problems-with-language-models/) using [EleutherAI Eval Harness](https://github.com/EleutherAI/lm-evaluation-harness) through torchtune.
|
| 58 |
|
| 59 |
CMD:
|
| 60 |
+
```bash
|
| 61 |
tune run eleuther_eval --config eleuther_evaluation \
|
| 62 |
checkpoint.checkpoint_dir=./lora-phi3-math \
|
| 63 |
tasks=["minerva_math"] \
|
|
|
|
| 65 |
```
|
| 66 |
|
| 67 |
RESULTS:
|
| 68 |
+
|
| 69 |
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
| 70 |
|------------------------------------|-------|------|-----:|-----------|-----:|---|-----:|
|
| 71 |
|minerva_math |N/A |none | 4|exact_match|0.1670|± |0.0051|
|
|
|
|
| 76 |
| - minerva_math_num_theory | 1|none | 4|exact_match|0.1148|± |0.0137|
|
| 77 |
| - minerva_math_prealgebra | 1|none | 4|exact_match|0.3077|± |0.0156|
|
| 78 |
| - minerva_math_precalc | 1|none | 4|exact_match|0.0623|± |0.0104|
|
| 79 |
+
|
| 80 |
|
| 81 |
|
| 82 |
## Technical Specifications [optional]
|