Instructions to use bigscience/test-bloomd-6b3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bigscience/test-bloomd-6b3 with Transformers:

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

pipe = pipeline("text-generation", model="bigscience/test-bloomd-6b3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bigscience/test-bloomd-6b3")
model = AutoModelForCausalLM.from_pretrained("bigscience/test-bloomd-6b3")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bigscience/test-bloomd-6b3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bigscience/test-bloomd-6b3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bigscience/test-bloomd-6b3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bigscience/test-bloomd-6b3

SGLang

How to use bigscience/test-bloomd-6b3 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 "bigscience/test-bloomd-6b3" \
    --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": "bigscience/test-bloomd-6b3",
		"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 "bigscience/test-bloomd-6b3" \
        --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": "bigscience/test-bloomd-6b3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bigscience/test-bloomd-6b3 with Docker Model Runner:
```
docker model run hf.co/bigscience/test-bloomd-6b3
```

justheuristic commited on Aug 8, 2022

Commit

9159e0b

1 Parent(s): c10cdb6

push-o-matic

Browse files

Files changed (3) hide show

config.json +6 -3
pytorch_model.bin +1 -1
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,8 @@
 {
   "apply_residual_connection_post_layernorm": false,
   "attention_dropout": 0.0,
   "attention_softmax_in_fp32": true,
   "bias_dropout_fusion": true,
@@ -7,14 +10,14 @@
   "dht_prefix": "bigscience/test-bloomd-6b3",
   "eos_token_id": 2,
   "hidden_dropout": 0.0,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "masked_softmax_fusion": true,
   "model_type": "bloom",
-  "n_embed": 4096,
   "n_inner": null,
   "n_layer": 30,
-  "num_attention_heads": 32,
   "offset_alibi": 100,
   "pad_token_id": 3,
   "pretraining_tp": 4,
@@ -24,6 +27,6 @@
   "slow_but_exact": false,
   "transformers_version": "4.21.0.dev0",
   "unk_token_id": 0,
-  "use_cache": false,
   "vocab_size": 250880
 }

 {
   "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomModel"
+  ],
   "attention_dropout": 0.0,
   "attention_softmax_in_fp32": true,
   "bias_dropout_fusion": true,
   "dht_prefix": "bigscience/test-bloomd-6b3",
   "eos_token_id": 2,
   "hidden_dropout": 0.0,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "masked_softmax_fusion": true,
   "model_type": "bloom",
+  "n_head": 32,
   "n_inner": null,
   "n_layer": 30,
   "offset_alibi": 100,
   "pad_token_id": 3,
   "pretraining_tp": 4,
   "slow_but_exact": false,
   "transformers_version": "4.21.0.dev0",
   "unk_token_id": 0,
+  "use_cache": true,
   "vocab_size": 250880
 }

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a16a76ab0ef60497ad99fe7c5f6e76f455b1dae5d08fadeaebc849d14d1f5093
 size 2055243291

 version https://git-lfs.github.com/spec/v1
+oid sha256:50f206263e7636fc72a42747e86c39d576f3b6790f209132bdb8b03fa0660fb7
 size 2055243291

tokenizer_config.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "add_prefix_space": false,
   "bos_token": "<s>",
   "eos_token": "</s>",
-  "model_max_length": 1024,
   "name_or_path": "bigscience/bloom-6b3",
   "pad_token": "<pad>",
   "special_tokens_map_file": null,
   "tokenizer_class": "BloomTokenizer",
   "unk_token": "<unk>"

   "add_prefix_space": false,
   "bos_token": "<s>",
   "eos_token": "</s>",
   "name_or_path": "bigscience/bloom-6b3",
   "pad_token": "<pad>",
+  "padding_side": "left",
   "special_tokens_map_file": null,
   "tokenizer_class": "BloomTokenizer",
   "unk_token": "<unk>"