Instructions to use AlSamCur123/Mistral-Small-InstructContinuedFine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlSamCur123/Mistral-Small-InstructContinuedFine with Transformers:

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

pipe = pipeline("text-generation", model="AlSamCur123/Mistral-Small-InstructContinuedFine")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlSamCur123/Mistral-Small-InstructContinuedFine")
model = AutoModelForCausalLM.from_pretrained("AlSamCur123/Mistral-Small-InstructContinuedFine")
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 AlSamCur123/Mistral-Small-InstructContinuedFine with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlSamCur123/Mistral-Small-InstructContinuedFine"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlSamCur123/Mistral-Small-InstructContinuedFine",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AlSamCur123/Mistral-Small-InstructContinuedFine

SGLang

How to use AlSamCur123/Mistral-Small-InstructContinuedFine 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 "AlSamCur123/Mistral-Small-InstructContinuedFine" \
    --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": "AlSamCur123/Mistral-Small-InstructContinuedFine",
		"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 "AlSamCur123/Mistral-Small-InstructContinuedFine" \
        --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": "AlSamCur123/Mistral-Small-InstructContinuedFine",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use AlSamCur123/Mistral-Small-InstructContinuedFine 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 AlSamCur123/Mistral-Small-InstructContinuedFine 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 AlSamCur123/Mistral-Small-InstructContinuedFine to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AlSamCur123/Mistral-Small-InstructContinuedFine to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="AlSamCur123/Mistral-Small-InstructContinuedFine",
    max_seq_length=2048,
)

Docker Model Runner
How to use AlSamCur123/Mistral-Small-InstructContinuedFine with Docker Model Runner:
```
docker model run hf.co/AlSamCur123/Mistral-Small-InstructContinuedFine
```

AlSamCur123 commited on Dec 24, 2024

Commit

7423e6a

verified ·

1 Parent(s): 79296b9

Trained with Unsloth

Browse files

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "AlSamCur123/Mistral-Small-InstructContinuedFine",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -24,7 +24,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.3",
-  "unsloth_version": "2024.12.4",
   "use_cache": true,
   "vocab_size": 32768
 }

 {
+  "_name_or_path": "AlSamCur123/Mistral-Small-Instruct",
   "architectures": [
     "MistralForCausalLM"
   ],
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.3",
+  "unsloth_version": "2024.12.8",
   "use_cache": true,
   "vocab_size": 32768
 }

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80deab751867395203779279b9c7150cb4578655c57be9d35198cd6e79855457
 size 4882298776

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2003048fbc5576098b6bcdabe9c88eb7446c81d184bee0a611fa4d967119cd13
 size 4983012160

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5896a90a6a7026e120cf9d8792d8de4476a855092fe2b7c1a45f06fb809258a0
 size 4957821336

 version https://git-lfs.github.com/spec/v1
+oid sha256:c79b155f58fd3b61e6d7d0b6315758f49c6fc4c0a259839a777a09f7aed74656
 size 4882323744

 version https://git-lfs.github.com/spec/v1
+oid sha256:654c88f06b044cfb946bc945c98e1277a443789525fb0319adb4c854c70c4e09
 size 4983012192

 version https://git-lfs.github.com/spec/v1
+oid sha256:6d38b9de03632a16c63cc9ac77fba80c9aaacce9548d14e7993b898a7b48cc40
 size 4982999056