Instructions to use CharlesLi/mistral_cot_simplest_code_math_5_3_epoch_full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CharlesLi/mistral_cot_simplest_code_math_5_3_epoch_full with Transformers:

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

pipe = pipeline("text-generation", model="CharlesLi/mistral_cot_simplest_code_math_5_3_epoch_full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CharlesLi/mistral_cot_simplest_code_math_5_3_epoch_full")
model = AutoModelForCausalLM.from_pretrained("CharlesLi/mistral_cot_simplest_code_math_5_3_epoch_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

vLLM

How to use CharlesLi/mistral_cot_simplest_code_math_5_3_epoch_full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CharlesLi/mistral_cot_simplest_code_math_5_3_epoch_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_cot_simplest_code_math_5_3_epoch_full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CharlesLi/mistral_cot_simplest_code_math_5_3_epoch_full

SGLang

How to use CharlesLi/mistral_cot_simplest_code_math_5_3_epoch_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_cot_simplest_code_math_5_3_epoch_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_cot_simplest_code_math_5_3_epoch_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_cot_simplest_code_math_5_3_epoch_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_cot_simplest_code_math_5_3_epoch_full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CharlesLi/mistral_cot_simplest_code_math_5_3_epoch_full with Docker Model Runner:
```
docker model run hf.co/CharlesLi/mistral_cot_simplest_code_math_5_3_epoch_full
```

CharlesLi commited on Jan 21, 2025

Commit

28a43a1

verified ·

1 Parent(s): 7a2d949

End of training

Browse files

Files changed (5) hide show

README.md +5 -1
all_results.json +5 -0
config.json +1 -1
eval_results.json +8 -0
runs/Jan21_12-50-51_dgx-a100-18/events.out.tfevents.1737462614.dgx-a100-18.3833790.1 +3 -0

README.md CHANGED Viewed

@@ -3,6 +3,10 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.1
 tags:
 - trl
 - sft
 - generated_from_trainer
@@ -20,7 +24,7 @@ should probably proofread and complete it, then remove this comment. -->
 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: 0.6092
 ## Model description

 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
 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: 0.6105
 ## Model description

all_results.json CHANGED Viewed

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
     "total_flos": 37321923624960.0,
     "train_loss": 0.3315402416288018,
     "train_runtime": 1986.7751,

 {
     "epoch": 3.0,
+    "eval_loss": 0.6104772090911865,
+    "eval_runtime": 0.7136,
+    "eval_samples": 20,
+    "eval_samples_per_second": 7.007,
+    "eval_steps_per_second": 1.401,
     "total_flos": 37321923624960.0,
     "train_loss": 0.3315402416288018,
     "train_runtime": 1986.7751,

config.json CHANGED Viewed

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
   "vocab_size": 32000
 }

   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 3.0,
+    "eval_loss": 0.6104772090911865,
+    "eval_runtime": 0.7136,
+    "eval_samples": 20,
+    "eval_samples_per_second": 7.007,
+    "eval_steps_per_second": 1.401
+}

runs/Jan21_12-50-51_dgx-a100-18/events.out.tfevents.1737462614.dgx-a100-18.3833790.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1a63380d2311dc60129eb1b874e53d9e6ad2bea024fed008ccd345b0f1d58f08
+size 359