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

Libraries

How to use Phimabri/top_model with Transformers:

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

pipe = pipeline("text-generation", model="Phimabri/top_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Phimabri/top_model")
model = AutoModelForCausalLM.from_pretrained("Phimabri/top_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Phimabri/top_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Phimabri/top_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Phimabri/top_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Phimabri/top_model

SGLang

How to use Phimabri/top_model 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 "Phimabri/top_model" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Phimabri/top_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Phimabri/top_model" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Phimabri/top_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Phimabri/top_model with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Phimabri/top_model to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Phimabri/top_model to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Phimabri/top_model to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Phimabri/top_model",
    max_seq_length=2048,
)

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

Phimabri commited on May 13, 2024

Commit

aa1131f

verified ·

1 Parent(s): cbf13a6

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (3) hide show

special_tokens_map.json +2 -2
tokenizer.json +12 -12
tokenizer_config.json +15 -14

special_tokens_map.json CHANGED Viewed

@@ -14,10 +14,10 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
-    "rstrip": false,
     "single_word": false
   },
   "unk_token": {

     "single_word": false
   },
   "pad_token": {
+    "content": "<|placeholder6|>",
     "lstrip": false,
     "normalized": false,
+    "rstrip": true,
     "single_word": false
   },
   "unk_token": {

tokenizer.json CHANGED Viewed

@@ -26,9 +26,9 @@
       "content": "</s>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
       "normalized": false,
-      "special": true
     },
     {
       "id": 32000,
@@ -44,7 +44,7 @@
       "content": "<|assistant|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -53,7 +53,7 @@
       "content": "<|placeholder1|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -62,7 +62,7 @@
       "content": "<|placeholder2|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -71,7 +71,7 @@
       "content": "<|placeholder3|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -80,7 +80,7 @@
       "content": "<|placeholder4|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -89,7 +89,7 @@
       "content": "<|system|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -98,7 +98,7 @@
       "content": "<|end|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -107,7 +107,7 @@
       "content": "<|placeholder5|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -116,7 +116,7 @@
       "content": "<|placeholder6|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -125,7 +125,7 @@
       "content": "<|user|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
       "normalized": false,
       "special": true
     }

       "content": "</s>",
       "single_word": false,
       "lstrip": false,
+      "rstrip": true,
       "normalized": false,
+      "special": false
     },
     {
       "id": 32000,
       "content": "<|assistant|>",
       "single_word": false,
       "lstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
       "content": "<|placeholder1|>",
       "single_word": false,
       "lstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
       "content": "<|placeholder2|>",
       "single_word": false,
       "lstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
       "content": "<|placeholder3|>",
       "single_word": false,
       "lstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
       "content": "<|placeholder4|>",
       "single_word": false,
       "lstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
       "content": "<|system|>",
       "single_word": false,
       "lstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
       "content": "<|end|>",
       "single_word": false,
       "lstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
       "content": "<|placeholder5|>",
       "single_word": false,
       "lstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
       "content": "<|placeholder6|>",
       "single_word": false,
       "lstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
       "content": "<|user|>",
       "single_word": false,
       "lstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     }

tokenizer_config.json CHANGED Viewed

@@ -22,9 +22,9 @@
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
       "single_word": false,
-      "special": true
     },
     "32000": {
       "content": "<|endoftext|>",
@@ -38,7 +38,7 @@
       "content": "<|assistant|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -46,7 +46,7 @@
       "content": "<|placeholder1|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -54,7 +54,7 @@
       "content": "<|placeholder2|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -62,7 +62,7 @@
       "content": "<|placeholder3|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -70,7 +70,7 @@
       "content": "<|placeholder4|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -78,7 +78,7 @@
       "content": "<|system|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -86,7 +86,7 @@
       "content": "<|end|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -94,7 +94,7 @@
       "content": "<|placeholder5|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -102,7 +102,7 @@
       "content": "<|placeholder6|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -110,17 +110,18 @@
       "content": "<|user|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] in ['user', 'system']) %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "model_max_length": 4096,
-  "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",

       "content": "</s>",
       "lstrip": false,
       "normalized": false,
+      "rstrip": true,
       "single_word": false,
+      "special": false
     },
     "32000": {
       "content": "<|endoftext|>",
       "content": "<|assistant|>",
       "lstrip": false,
       "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
       "content": "<|placeholder1|>",
       "lstrip": false,
       "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
       "content": "<|placeholder2|>",
       "lstrip": false,
       "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
       "content": "<|placeholder3|>",
       "lstrip": false,
       "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
       "content": "<|placeholder4|>",
       "lstrip": false,
       "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
       "content": "<|system|>",
       "lstrip": false,
       "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
       "content": "<|end|>",
       "lstrip": false,
       "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
       "content": "<|placeholder5|>",
       "lstrip": false,
       "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
       "content": "<|placeholder6|>",
       "lstrip": false,
       "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
       "content": "<|user|>",
       "lstrip": false,
       "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     }
   },
   "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "legacy": false,
   "model_max_length": 4096,
+  "pad_token": "<|placeholder6|>",
   "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",