Instructions to use dlibf/zephyr-7b-sft-math_code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dlibf/zephyr-7b-sft-math_code with Transformers:

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

pipe = pipeline("text-generation", model="dlibf/zephyr-7b-sft-math_code")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dlibf/zephyr-7b-sft-math_code")
model = AutoModelForCausalLM.from_pretrained("dlibf/zephyr-7b-sft-math_code")
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 dlibf/zephyr-7b-sft-math_code with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dlibf/zephyr-7b-sft-math_code

SGLang

How to use dlibf/zephyr-7b-sft-math_code 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 "dlibf/zephyr-7b-sft-math_code" \
    --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": "dlibf/zephyr-7b-sft-math_code",
		"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 "dlibf/zephyr-7b-sft-math_code" \
        --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": "dlibf/zephyr-7b-sft-math_code",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dlibf/zephyr-7b-sft-math_code with Docker Model Runner:
```
docker model run hf.co/dlibf/zephyr-7b-sft-math_code
```

dlibf commited on Feb 2, 2024

Commit

dcdc2db

verified ·

1 Parent(s): ffb2306

End of training

Browse files

Files changed (2) hide show

README.md +6 -2
config.json +1 -1

README.md CHANGED Viewed

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
 model-index:
 - name: zephyr-7b-sft-math_code
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 # zephyr-7b-sft-math_code
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9659

 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
+- alignment-handbook
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
+- HuggingFaceH4/ultrachat_200k
+- dlibf/glaive-code-assistant
+- dlibf/metamathqa_formatted
 model-index:
 - name: zephyr-7b-sft-math_code
   results: []
 # zephyr-7b-sft-math_code
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k, the dlibf/glaive-code-assistant and the dlibf/metamathqa_formatted datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.9659

config.json CHANGED Viewed

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
-  "use_cache": false,
   "vocab_size": 32000
 }

   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
+  "use_cache": true,
   "vocab_size": 32000
 }