Instructions to use Ahmad-11/Reporter_Phi3Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ahmad-11/Reporter_Phi3Mini with Transformers:

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

pipe = pipeline("text-generation", model="Ahmad-11/Reporter_Phi3Mini", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ahmad-11/Reporter_Phi3Mini", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Ahmad-11/Reporter_Phi3Mini", trust_remote_code=True)
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 Settings

vLLM

How to use Ahmad-11/Reporter_Phi3Mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ahmad-11/Reporter_Phi3Mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ahmad-11/Reporter_Phi3Mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ahmad-11/Reporter_Phi3Mini

SGLang

How to use Ahmad-11/Reporter_Phi3Mini 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 "Ahmad-11/Reporter_Phi3Mini" \
    --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": "Ahmad-11/Reporter_Phi3Mini",
		"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 "Ahmad-11/Reporter_Phi3Mini" \
        --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": "Ahmad-11/Reporter_Phi3Mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ahmad-11/Reporter_Phi3Mini with Docker Model Runner:
```
docker model run hf.co/Ahmad-11/Reporter_Phi3Mini
```

Ahmad-11 commited on May 27, 2024

Commit

901cd39

verified ·

1 Parent(s): b1af576

Upload tokenizer

Browse files

Files changed (3) hide show

special_tokens_map.json +7 -1
tokenizer.json +2 -43
tokenizer_config.json +2 -2

special_tokens_map.json CHANGED Viewed

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

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

tokenizer.json CHANGED Viewed

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 510,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 510
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 32000,
-    "pad_type_id": 0,
-    "pad_token": "<|endoftext|>"
-  },
   "added_tokens": [
     {
       "id": 0,
@@ -175,12 +161,6 @@
           "id": "A",
           "type_id": 0
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 0
-        }
       }
     ],
     "pair": [
@@ -196,12 +176,6 @@
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 0
-        }
-      },
       {
         "SpecialToken": {
           "id": "<s>",
@@ -213,12 +187,6 @@
           "id": "B",
           "type_id": 1
         }
-      },
-      {
-        "SpecialToken": {
-          "id": "<|endoftext|>",
-          "type_id": 1
-        }
       }
     ],
     "special_tokens": {
@@ -230,15 +198,6 @@
         "tokens": [
           "<s>"
         ]
-      },
-      "<|endoftext|>": {
-        "id": "<|endoftext|>",
-        "ids": [
-          32000
-        ],
-        "tokens": [
-          "<|endoftext|>"
-        ]
       }
     }
   },

 {
   "version": "1.0",
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,
           "id": "A",
           "type_id": 0
         }
       }
     ],
     "pair": [
           "type_id": 0
         }
       },
       {
         "SpecialToken": {
           "id": "<s>",
           "id": "B",
           "type_id": 1
         }
       }
     ],
     "special_tokens": {
         "tokens": [
           "<s>"
         ]
       }
     }
   },

tokenizer_config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "add_bos_token": true,
-  "add_eos_token": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -122,7 +122,7 @@
   "legacy": false,
   "model_max_length": 4096,
   "pad_token": "<|endoftext|>",
-  "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",

 {
   "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
   "legacy": false,
   "model_max_length": 4096,
   "pad_token": "<|endoftext|>",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",