Instructions to use jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge with Transformers:

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

pipe = pipeline("text-generation", model="jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge")
model = AutoModelForCausalLM.from_pretrained("jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge

SGLang

How to use jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge 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 "jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge" \
    --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": "jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge",
		"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 "jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge" \
        --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": "jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge with Docker Model Runner:
```
docker model run hf.co/jtatman/Tiny-Llama-Llama-Dolphin-laser-1b-merge
```

jtatman commited on Feb 25, 2024

Commit

e3aca75

verified ·

1 Parent(s): eda5870

Update special_tokens_map.json

Browse files

Files changed (1) hide show

special_tokens_map.json +2 -39

special_tokens_map.json CHANGED Viewed

@@ -1,41 +1,4 @@
 {
-  "additional_special_tokens": [
-    {
-      "content": "<|im_start|>user",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_start|>assistant",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -44,13 +7,13 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|im_end|>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

 {
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
     "single_word": false
   },
   "eos_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,