Instructions to use tensorplex-labs/pretraining-sn9-7B-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorplex-labs/pretraining-sn9-7B-4 with Transformers:

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

pipe = pipeline("text-generation", model="tensorplex-labs/pretraining-sn9-7B-4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tensorplex-labs/pretraining-sn9-7B-4")
model = AutoModelForCausalLM.from_pretrained("tensorplex-labs/pretraining-sn9-7B-4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tensorplex-labs/pretraining-sn9-7B-4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorplex-labs/pretraining-sn9-7B-4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorplex-labs/pretraining-sn9-7B-4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tensorplex-labs/pretraining-sn9-7B-4

SGLang

How to use tensorplex-labs/pretraining-sn9-7B-4 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 "tensorplex-labs/pretraining-sn9-7B-4" \
    --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": "tensorplex-labs/pretraining-sn9-7B-4",
		"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 "tensorplex-labs/pretraining-sn9-7B-4" \
        --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": "tensorplex-labs/pretraining-sn9-7B-4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tensorplex-labs/pretraining-sn9-7B-4 with Docker Model Runner:
```
docker model run hf.co/tensorplex-labs/pretraining-sn9-7B-4
```

tensorplex-labs commited on Apr 23, 2024

Commit

6d3c838

verified ·

1 Parent(s): 6c7002c

Upload LlamaForCausalLM

Browse files

Files changed (5) hide show

config.json +3 -3
model-00001-of-00003.safetensors +2 -2
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +2 -2
model.safetensors.index.json +1 -1

config.json CHANGED Viewed

@@ -5,8 +5,8 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 100257,
-  "eos_token_id": 100257,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -24,5 +24,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.0",
   "use_cache": true,
-  "vocab_size": 100263
 }

   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.0",
   "use_cache": true,
+  "vocab_size": 100288
 }

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4af6268936ddca2f363220d6e88a0af6bb18c8511138962f2e0f87a8e54c67
-size 4969695904

 version https://git-lfs.github.com/spec/v1
+oid sha256:9604f6216e503eb57d1c9b140e7b475ab183018fd40d70bf2c5515d8cb39a7fb
+size 4969900704

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20efc28896cb595e8e3056e7a9a51ea5c137ebb2306cfe05f009213e2161f483
 size 4980945440

 version https://git-lfs.github.com/spec/v1
+oid sha256:75b25e7b53c8a6b9b6c402c84c52027405fcfef15f082ea8c1bbd53808c7e5ff
 size 4980945440

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f078855a23f9a01682ff0ff94af2000c93a9d410479b80efcd79584fd4a8e2e4
-size 3835109216

 version https://git-lfs.github.com/spec/v1
+oid sha256:c3dfcd4971e51efc3b3ab41e14897f227b69f0ec03c85c4fec8975257b0773df
+size 3835314016

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13785718784
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",

 {
   "metadata": {
+    "total_size": 13786128384
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",