Instructions to use deadcode99/mistral-7b-finetuned-lime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deadcode99/mistral-7b-finetuned-lime with Transformers:

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

pipe = pipeline("text-generation", model="deadcode99/mistral-7b-finetuned-lime")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deadcode99/mistral-7b-finetuned-lime")
model = AutoModelForCausalLM.from_pretrained("deadcode99/mistral-7b-finetuned-lime")
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 deadcode99/mistral-7b-finetuned-lime with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deadcode99/mistral-7b-finetuned-lime"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deadcode99/mistral-7b-finetuned-lime",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deadcode99/mistral-7b-finetuned-lime

SGLang

How to use deadcode99/mistral-7b-finetuned-lime 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 "deadcode99/mistral-7b-finetuned-lime" \
    --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": "deadcode99/mistral-7b-finetuned-lime",
		"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 "deadcode99/mistral-7b-finetuned-lime" \
        --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": "deadcode99/mistral-7b-finetuned-lime",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deadcode99/mistral-7b-finetuned-lime with Docker Model Runner:
```
docker model run hf.co/deadcode99/mistral-7b-finetuned-lime
```

deadcode99 commited on Apr 21, 2024

Commit

2f78039

verified ·

1 Parent(s): eb3eb56

Model save

Browse files

Files changed (5) hide show

README.md +4 -4
model-00001-of-00003.safetensors +1 -1
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5940
 ## Model description
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8813        | 1.0   | 21   | 0.9554          |
-| 0.2776        | 2.0   | 42   | 0.6229          |
-| 0.1085        | 3.0   | 63   | 0.5940          |
 ### Framework versions

 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.6517
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 1.3745        | 1.0   | 90   | 1.4860          |
+| 0.8717        | 2.0   | 180  | 1.4783          |
+| 0.3929        | 3.0   | 270  | 1.6517          |
 ### Framework versions

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497ad2bec4f9ea2424b77d6b697c4412c12a037396577d11e459d79ea6681763
 size 4943162336

 version https://git-lfs.github.com/spec/v1
+oid sha256:d91aae6074caabf4675a783a79a49ea071f9e361cacd088d49765d70af30a2ac
 size 4943162336

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f83c147d9be367fa0bd890d454a3793bf9e84498016084b40360dba81deaaee
 size 4999819336

 version https://git-lfs.github.com/spec/v1
+oid sha256:b1b7d70babde7b949c5755253e069d62f0bf61c71b9f46f728d7afc8a879bac4
 size 4999819336

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4cf9b6ce3e236869e89abe0a686ae46a46a01a9cb44b70c2d46aa51aa3688c
 size 4540516344

 version https://git-lfs.github.com/spec/v1
+oid sha256:a13fe0615f5f3950c2f748cd84da941b7f5194fdbda5e921f92e5a74d919fcbf
 size 4540516344

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be30a2d27a6e84eb268207650ddd3fb12d85464e19d21881b1bc0a98b298e86
 size 6008

 version https://git-lfs.github.com/spec/v1
+oid sha256:4b5d1df0bf7fef9330a1c6d6bf5e3c7b91f82932a2ac9f35fcc38826648e3df4
 size 6008