Instructions to use pacozaa/mistral-unsloth-chatml-first with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pacozaa/mistral-unsloth-chatml-first with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pacozaa/mistral-unsloth-chatml-first", dtype="auto", device_map="auto")

llama-cpp-python

How to use pacozaa/mistral-unsloth-chatml-first with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="pacozaa/mistral-unsloth-chatml-first",
	filename="mistral-unsloth-chatml-first-unsloth.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use pacozaa/mistral-unsloth-chatml-first with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf pacozaa/mistral-unsloth-chatml-first:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf pacozaa/mistral-unsloth-chatml-first:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf pacozaa/mistral-unsloth-chatml-first:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf pacozaa/mistral-unsloth-chatml-first:Q4_K_M

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 pacozaa/mistral-unsloth-chatml-first:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf pacozaa/mistral-unsloth-chatml-first:Q4_K_M

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 pacozaa/mistral-unsloth-chatml-first:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pacozaa/mistral-unsloth-chatml-first:Q4_K_M

Use Docker

docker model run hf.co/pacozaa/mistral-unsloth-chatml-first:Q4_K_M

LM Studio
Jan
Ollama
How to use pacozaa/mistral-unsloth-chatml-first with Ollama:
```
ollama run hf.co/pacozaa/mistral-unsloth-chatml-first:Q4_K_M
```

Unsloth Studio

How to use pacozaa/mistral-unsloth-chatml-first 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 pacozaa/mistral-unsloth-chatml-first 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 pacozaa/mistral-unsloth-chatml-first to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pacozaa/mistral-unsloth-chatml-first to start chatting

Atomic Chat new
Docker Model Runner
How to use pacozaa/mistral-unsloth-chatml-first with Docker Model Runner:
```
docker model run hf.co/pacozaa/mistral-unsloth-chatml-first:Q4_K_M
```

Lemonade

How to use pacozaa/mistral-unsloth-chatml-first with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pacozaa/mistral-unsloth-chatml-first:Q4_K_M

Run and chat with the model

lemonade run user.mistral-unsloth-chatml-first-Q4_K_M

List all available models

lemonade list

pacozaa commited on Mar 25, 2024

Commit

77db516

verified ·

1 Parent(s): d9e1cfa

(Trained with Unsloth)

Browse files

Files changed (1) hide show

config.json +2 -39

config.json CHANGED Viewed

@@ -1,40 +1,3 @@
 {
-  "_name_or_path": "unsloth/mistral-7b-bnb-4bit",
-  "architectures": [
-    "MistralForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
-  "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "pad_token_id": 2,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
-  "rms_norm_eps": 1e-05,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.38.2",
-  "unsloth_version": "2024.3",
-  "use_cache": true,
-  "vocab_size": 32000
-}

 {
+    "model_type": "mistral"
+}