Instructions to use Rwigle/C-MORAL-Mistral-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use Rwigle/C-MORAL-Mistral-GRPO with PEFT:
```
Task type is invalid.
```

How to use Rwigle/C-MORAL-Mistral-GRPO with Transformers:

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

pipe = pipeline("text-generation", model="Rwigle/C-MORAL-Mistral-GRPO")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Rwigle/C-MORAL-Mistral-GRPO", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Rwigle/C-MORAL-Mistral-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rwigle/C-MORAL-Mistral-GRPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rwigle/C-MORAL-Mistral-GRPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Rwigle/C-MORAL-Mistral-GRPO

SGLang

How to use Rwigle/C-MORAL-Mistral-GRPO 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 "Rwigle/C-MORAL-Mistral-GRPO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rwigle/C-MORAL-Mistral-GRPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Rwigle/C-MORAL-Mistral-GRPO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rwigle/C-MORAL-Mistral-GRPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Rwigle/C-MORAL-Mistral-GRPO with Docker Model Runner:
```
docker model run hf.co/Rwigle/C-MORAL-Mistral-GRPO
```

Rwigle commited on Apr 24

Commit

d39e65e

verified ·

1 Parent(s): 0d85b50

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

bdeq/README.md +46 -0
bdeq/adapter_config.json +47 -0
bdeq/adapter_model.safetensors +3 -0

bdeq/README.md ADDED Viewed

	@@ -0,0 +1,46 @@

+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- lora
+- peft
+- transformers
+- mistral
+- grpo
+- molecule-optimization
+- bdeq
+license: mit
+---
+# C-MORAL Mistral GRPO BDEQ Adapter
+LoRA adapter for molecule optimization trained with GRPO on the `bdeq` task.
+## Base Model
+- `mistralai/Mistral-7B-Instruct-v0.3`
+## Task
+- task alias: `bdeq`
+- property combination: `bbbp+drd2+herg+qed`
+## Method
+- algorithm: `GRPO`
+- adapter type: `LoRA`
+## Load With PEFT
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+base_model_id = "mistralai/Mistral-7B-Instruct-v0.3"
+adapter_id = "Rwigle/C-MORAL-Mistral-GRPO"
+tokenizer = AutoTokenizer.from_pretrained(base_model_id)
+model = AutoModelForCausalLM.from_pretrained(base_model_id)
+model = PeftModel.from_pretrained(model, adapter_id, subfolder="bdeq")
+```

bdeq/adapter_config.json ADDED Viewed

	@@ -0,0 +1,47 @@

+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "lm_head",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

bdeq/adapter_model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0e4144bc79ccb76fb1c7cf6eab5ae2cfe84bcb175e26cfa889ba7dd2499698a6
+size 438627360