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

Libraries

How to use codingwithlewis/mistralmeme with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codingwithlewis/mistralmeme")
model = AutoModelForCausalLM.from_pretrained("codingwithlewis/mistralmeme")
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]:]))

llama-cpp-python

How to use codingwithlewis/mistralmeme with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="codingwithlewis/mistralmeme",
	filename="mistralmemes.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use codingwithlewis/mistralmeme with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf codingwithlewis/mistralmeme
# Run inference directly in the terminal:
llama-cli -hf codingwithlewis/mistralmeme

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf codingwithlewis/mistralmeme
# Run inference directly in the terminal:
llama-cli -hf codingwithlewis/mistralmeme

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf codingwithlewis/mistralmeme
# Run inference directly in the terminal:
./llama-cli -hf codingwithlewis/mistralmeme

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf codingwithlewis/mistralmeme
# Run inference directly in the terminal:
./build/bin/llama-cli -hf codingwithlewis/mistralmeme

Use Docker

docker model run hf.co/codingwithlewis/mistralmeme

LM Studio
Jan

vLLM

How to use codingwithlewis/mistralmeme with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/codingwithlewis/mistralmeme

SGLang

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

Ollama
How to use codingwithlewis/mistralmeme with Ollama:
```
ollama run hf.co/codingwithlewis/mistralmeme
```

Unsloth Studio new

How to use codingwithlewis/mistralmeme 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 codingwithlewis/mistralmeme 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 codingwithlewis/mistralmeme to start chatting

Using HuggingFace Spaces for Unsloth

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

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

Lemonade

How to use codingwithlewis/mistralmeme with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull codingwithlewis/mistralmeme

Run and chat with the model

lemonade run user.mistralmeme-{{QUANT_TAG}}

List all available models

lemonade list

codingwithlewis commited on Apr 15, 2024

Commit

8e112c2

verified ·

1 Parent(s): 9375028

Upload tokenizer

Browse files

Files changed (4) hide show

special_tokens_map.json +1 -1
tokenizer.json +2 -2
tokenizer.model +2 -2
tokenizer_config.json +4 -8

special_tokens_map.json CHANGED Viewed

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

     "single_word": false
   },
   "eos_token": {
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json CHANGED Viewed

@@ -23,7 +23,7 @@
     },
     {
       "id": 2,
-      "content": "</s>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -137,7 +137,7 @@
     "vocab": {
       "<unk>": 0,
       "<s>": 1,
-      "</s>": 2,
       "<0x00>": 3,
       "<0x01>": 4,
       "<0x02>": 5,

     },
     {
       "id": 2,
+      "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,
+      "<|im_end|>": 2,
       "<0x00>": 3,
       "<0x01>": 4,
       "<0x02>": 5,

tokenizer.model CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443

 version https://git-lfs.github.com/spec/v1
+oid sha256:cc460a0129515b7579ec9f63218012601729de4fbd1b5de8d56dc47e8a204a29
+size 493449

tokenizer_config.json CHANGED Viewed

@@ -1,7 +1,6 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -20,7 +19,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -29,14 +28,11 @@
     }
   },
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": true,
-  "model_max_length": 32768,
   "pad_token": "<unk>",
-  "padding_side": "left",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false

 {
   "add_bos_token": true,
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
       "special": true
     },
     "2": {
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
     }
   },
   "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<unk>",
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false