Instructions to use cipher982/report_builder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cipher982/report_builder with Transformers:

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

pipe = pipeline("text-generation", model="cipher982/report_builder")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cipher982/report_builder")
model = AutoModelForCausalLM.from_pretrained("cipher982/report_builder", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cipher982/report_builder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cipher982/report_builder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cipher982/report_builder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cipher982/report_builder

SGLang

How to use cipher982/report_builder 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 "cipher982/report_builder" \
    --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": "cipher982/report_builder",
		"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 "cipher982/report_builder" \
        --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": "cipher982/report_builder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cipher982/report_builder with Docker Model Runner:
```
docker model run hf.co/cipher982/report_builder
```

cipher982 commited on Aug 14, 2023

Commit

9c7a101

1 Parent(s): 998b96c

Upload LlamaForCausalLM

Browse files

Files changed (4) hide show

config.json +2 -2
model-00001-of-00002.safetensors +2 -2
model-00002-of-00002.safetensors +2 -2
model.safetensors.index.json +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -22,5 +22,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.31.0",
   "use_cache": true,
-  "vocab_size": 32000
 }

 {
+  "_name_or_path": "resized/llama-2-7b-hf-4tokens",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "torch_dtype": "bfloat16",
   "transformers_version": "4.31.0",
   "use_cache": true,
+  "vocab_size": 32004
 }

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e54e0ceac67dad811214504771b6fffa180897ec59e579b66a6a04753b9dd9fc
-size 9976579144

 version https://git-lfs.github.com/spec/v1
+oid sha256:7a801c432d7f9df00d5e0e78a871dce85b032def7783cbde2a9d67132fc603ea
+size 9976611912

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82132acda9e1eecc9c313ff0205ba0c66a4133186cbe7529b9f74f4f08567ff6
-size 3500297424

 version https://git-lfs.github.com/spec/v1
+oid sha256:c18c487c96ed880a09a8289264552801b1e490235e78cad449d72b6cc9b1e374
+size 3500330192

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13476839424
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",

 {
   "metadata": {
+    "total_size": 13476904960
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",