Instructions to use CharlesLi/mistral_llama_2_code_math_3_full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CharlesLi/mistral_llama_2_code_math_3_full with Transformers:

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

pipe = pipeline("text-generation", model="CharlesLi/mistral_llama_2_code_math_3_full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CharlesLi/mistral_llama_2_code_math_3_full")
model = AutoModelForCausalLM.from_pretrained("CharlesLi/mistral_llama_2_code_math_3_full")
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 CharlesLi/mistral_llama_2_code_math_3_full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CharlesLi/mistral_llama_2_code_math_3_full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CharlesLi/mistral_llama_2_code_math_3_full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CharlesLi/mistral_llama_2_code_math_3_full

SGLang

How to use CharlesLi/mistral_llama_2_code_math_3_full 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 "CharlesLi/mistral_llama_2_code_math_3_full" \
    --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": "CharlesLi/mistral_llama_2_code_math_3_full",
		"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 "CharlesLi/mistral_llama_2_code_math_3_full" \
        --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": "CharlesLi/mistral_llama_2_code_math_3_full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CharlesLi/mistral_llama_2_code_math_3_full with Docker Model Runner:
```
docker model run hf.co/CharlesLi/mistral_llama_2_code_math_3_full
```

CharlesLi commited on Jan 20, 2025

Commit

b37144c

verified ·

1 Parent(s): a3d7a09

Model save

Browse files

Files changed (5) hide show

README.md +1 -6
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

@@ -3,12 +3,9 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.1
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
 - generator
@@ -23,8 +20,6 @@ should probably proofread and complete it, then remove this comment. -->
 # mistral_llama_2_code_math_3_full
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.5239
 ## Model description

 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.1
 tags:
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 datasets:
 - generator
 # mistral_llama_2_code_math_3_full
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
 ## Model description

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649114522d121b65947cd358118949a03d9012605ad96ab266982998d69ebb54
 size 4943162336

 version https://git-lfs.github.com/spec/v1
+oid sha256:5ab6c1dce9fc9fe3e80d241a48a835f5c6cd8ab9c7dea6f12b8b6ceeef7c89a6
 size 4943162336

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef506c4738bfb39a61dcefb4f5c3b31689c0c3e65b29ced8fb832d44e7e0d4b
 size 4999819336

 version https://git-lfs.github.com/spec/v1
+oid sha256:8569a0e447099b428d092f96237ca550cd2a15c235c81f15f7dfc43b2b283a15
 size 4999819336

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de36501d54334f61063797d330186d2c01374901801b9c1a75bb2c1a11bd3936
 size 4540516344

 version https://git-lfs.github.com/spec/v1
+oid sha256:f06d0c19e04315ae2caedf95a769ed0db6c2fcab7efd1dc42502c10ae91866b6
 size 4540516344

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1078058b6b6924cc9bb76df6ec6be247eb288e5a159f76ae5da1abca7f69a208
 size 7032

 version https://git-lfs.github.com/spec/v1
+oid sha256:a2c0ad1c7fd3d2b953ab634ee284d737f50746da04fb49280c72364bfbfa0ec3
 size 7032