Instructions to use blesspearl/math-stackexchange with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blesspearl/math-stackexchange with Transformers:

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

pipe = pipeline("text-generation", model="blesspearl/math-stackexchange")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("blesspearl/math-stackexchange")
model = AutoModelForCausalLM.from_pretrained("blesspearl/math-stackexchange")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use blesspearl/math-stackexchange with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/blesspearl/math-stackexchange

SGLang

How to use blesspearl/math-stackexchange 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 "blesspearl/math-stackexchange" \
    --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": "blesspearl/math-stackexchange",
		"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 "blesspearl/math-stackexchange" \
        --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": "blesspearl/math-stackexchange",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use blesspearl/math-stackexchange with Docker Model Runner:
```
docker model run hf.co/blesspearl/math-stackexchange
```

blesspearl commited on Jul 29, 2024

Commit

ef51b5b

verified ·

1 Parent(s): f020d6e

Upload model

Browse files

Files changed (3) hide show

README.md +1 -1
adapter_config.json +5 -5
adapter_model.safetensors +1 -1

README.md CHANGED Viewed

@@ -1,10 +1,10 @@
 ---
-license: mit
 datasets:
 - blesspearl/stackexchange-math-sample
 language:
 - en
 library_name: transformers
 ---
 [Guide](https://medium.com/@rajatsharma_33357/fine-tuning-llama-using-lora-fb3f48a557d5)

 ---
 datasets:
 - blesspearl/stackexchange-math-sample
 language:
 - en
 library_name: transformers
+license: mit
 ---
 [Guide](https://medium.com/@rajatsharma_33357/fine-tuning-llama-using-lora-fb3f48a557d5)

adapter_config.json CHANGED Viewed

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "gate_proj",
-    "o_proj",
     "q_proj",
-    "down_proj",
     "v_proj",
-    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "q_proj",
     "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58739ed9457f3f2afc5b2a1e3cd1819457b9722fcc3a62c824c1894184eb0890
 size 2269211544

 version https://git-lfs.github.com/spec/v1
+oid sha256:cbd87b84c6b350ad422fb7445bce3884ab3fe483dd4128919b6c75cafea75c0a
 size 2269211544