Instructions to use isemmanuelolowe/Ikhou3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use isemmanuelolowe/Ikhou3b with Transformers:

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

pipe = pipeline("text-generation", model="isemmanuelolowe/Ikhou3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("isemmanuelolowe/Ikhou3b")
model = AutoModelForCausalLM.from_pretrained("isemmanuelolowe/Ikhou3b")
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 isemmanuelolowe/Ikhou3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "isemmanuelolowe/Ikhou3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "isemmanuelolowe/Ikhou3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/isemmanuelolowe/Ikhou3b

SGLang

How to use isemmanuelolowe/Ikhou3b 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 "isemmanuelolowe/Ikhou3b" \
    --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": "isemmanuelolowe/Ikhou3b",
		"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 "isemmanuelolowe/Ikhou3b" \
        --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": "isemmanuelolowe/Ikhou3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use isemmanuelolowe/Ikhou3b with Docker Model Runner:
```
docker model run hf.co/isemmanuelolowe/Ikhou3b
```

isemmanuelolowe commited on Apr 15, 2024

Commit

2885f90

verified ·

1 Parent(s): 96c956d

Training in progress, step 100

Browse files

Files changed (4) hide show

config.json +1 -1
special_tokens_map.json +1 -7
tokenizer.json +18 -0
tokenizer_config.json +24 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./Ikhou1b/checkpoint-200",
   "architectures": [
     "MambaForCausalLM"
   ],

 {
+  "_name_or_path": "./Ikhou3b/checkpoint-1400",
   "architectures": [
     "MambaForCausalLM"
   ],

special_tokens_map.json CHANGED Viewed

@@ -13,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

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

tokenizer.json CHANGED Viewed

@@ -241,6 +241,24 @@
       "rstrip": false,
       "normalized": true,
       "special": false
     }
   ],
   "normalizer": {

       "rstrip": false,
       "normalized": true,
       "special": false
+    },
+    {
+      "id": 50277,
+      "content": "\n\n\nUser: ",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": false
+    },
+    {
+      "id": 50278,
+      "content": "\n\n\nAssistant: ",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": false
     }
   ],
   "normalizer": {

tokenizer_config.json CHANGED Viewed

@@ -200,14 +200,37 @@
       "rstrip": false,
       "single_word": false,
       "special": false
     }
   },
   "bos_token": "<|endoftext|>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'system' %}\n{{ message['content'] }}\n\n\n{% endif %}\n{% if message['role'] == 'user' %}\nUser: {{ message['content'] }}\n\n\n{% endif %}\n{% if message['role'] == 'assistant' %}\nAssistant: {{ message['content'] }}\n\n\n{% endif %}\n{% endfor %}\nAssistant:",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }

       "rstrip": false,
       "single_word": false,
       "special": false
+    },
+    "50277": {
+      "content": "\n\n\nUser: ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "\n\n\nAssistant: ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'system' %}\n{{ message['content'] }}\n{% endif %}\n{% if message['role'] == 'user' %}\n\n\nUser: {{ message['content'] }}\n{% endif %}\n{% if message['role'] == 'assistant' %}\n\n\nAssistant: {{ message['content'] }}\n{% endif %}\n{% endfor %}\n\n\nAssistant: ",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 2048,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
   "tokenizer_class": "GPTNeoXTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }