Instructions to use RedHatAI/MiniChat-3B-pruned50-quant-ds with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/MiniChat-3B-pruned50-quant-ds with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/MiniChat-3B-pruned50-quant-ds")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/MiniChat-3B-pruned50-quant-ds")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/MiniChat-3B-pruned50-quant-ds")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RedHatAI/MiniChat-3B-pruned50-quant-ds with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/MiniChat-3B-pruned50-quant-ds"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/MiniChat-3B-pruned50-quant-ds",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RedHatAI/MiniChat-3B-pruned50-quant-ds

SGLang

How to use RedHatAI/MiniChat-3B-pruned50-quant-ds 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 "RedHatAI/MiniChat-3B-pruned50-quant-ds" \
    --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": "RedHatAI/MiniChat-3B-pruned50-quant-ds",
		"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 "RedHatAI/MiniChat-3B-pruned50-quant-ds" \
        --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": "RedHatAI/MiniChat-3B-pruned50-quant-ds",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RedHatAI/MiniChat-3B-pruned50-quant-ds with Docker Model Runner:
```
docker model run hf.co/RedHatAI/MiniChat-3B-pruned50-quant-ds
```

mwitiderrick commited on Dec 5, 2023

Commit

90674f3

1 Parent(s): 845468e

Upload folder using huggingface_hub

Browse files

Files changed (5) hide show

config.json +1 -1
model-orig.onnx +2 -2
model.data +1 -1
model.onnx +2 -2
tokenizer.json +1 -6

config.json CHANGED Viewed

@@ -22,7 +22,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "1.6.0.20231130",
   "use_cache": true,
   "vocab_size": 49216
 }

   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
+  "transformers_version": "1.6.0.20231205",
   "use_cache": true,
   "vocab_size": 49216
 }

model-orig.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4d7c8c89d861413caac70764d92b5bdf6240751e767bf6588741c7034ec774
-size 904618

 version https://git-lfs.github.com/spec/v1
+oid sha256:cd8e00a9d30202eeb3426665186fa115ef10b39925aace6a85770bc1c21381f5
+size 904409

model.data CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:259aef73892c15fb3dc236512a60f6470b0b728edd4c6287dcb0a7f11db50fa4
 size 3402575872

 version https://git-lfs.github.com/spec/v1
+oid sha256:39ba695da27a446bce712d75f38ea9b0037c2c8b9bba4f3b7984081690cafa2b
 size 3402575872

model.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8de9ffc0f173b531637b97a9aaeb316060719a15886c37d2f0f29cf95127321
-size 892083

 version https://git-lfs.github.com/spec/v1
+oid sha256:ed898b9720df09367e587f53069ba48d54570ab09e2a0a1d723d3cd7a3c4d164
+size 891874

tokenizer.json CHANGED Viewed

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 4096,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
   "padding": null,
   "added_tokens": [
     {

 {
   "version": "1.0",
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {