Text Generation
Transformers
Safetensors
llama
Generated from Trainer
trl
grpo
conversational
text-generation-inference
Instructions to use cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO") model = AutoModelForCausalLM.from_pretrained("cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO
- SGLang
How to use cfei621/DeepSeek-R1-Distill-Llama-8B-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 "cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO" \ --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": "cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO", "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 "cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO" \ --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": "cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO with Docker Model Runner:
docker model run hf.co/cfei621/DeepSeek-R1-Distill-Llama-8B-GRPO
Model save
Browse files- README.md +1 -1
- all_results.json +5 -5
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- train_results.json +5 -5
- trainer_state.json +0 -0
README.md
CHANGED
|
@@ -26,7 +26,7 @@ print(output["generated_text"])
|
|
| 26 |
|
| 27 |
## Training procedure
|
| 28 |
|
| 29 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/cfei-kaust/huggingface/runs/
|
| 30 |
|
| 31 |
|
| 32 |
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
|
|
|
|
| 26 |
|
| 27 |
## Training procedure
|
| 28 |
|
| 29 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/cfei-kaust/huggingface/runs/g4fcc6et)
|
| 30 |
|
| 31 |
|
| 32 |
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"total_flos": 0.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second": 0.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"total_flos": 0.0,
|
| 3 |
+
"train_loss": 2.0727225511886656,
|
| 4 |
+
"train_runtime": 64632.8349,
|
| 5 |
+
"train_samples": 5455,
|
| 6 |
+
"train_samples_per_second": 0.084,
|
| 7 |
+
"train_steps_per_second": 0.021
|
| 8 |
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aefef14d0fa0e535974078bf6bcb49d7c8df57a6e51ee5d75ca97b8a3d8109e2
|
| 3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999802720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4e3bd4d81263468dbae202ea58905de4fc00db4f1b0c01b0917b153dfa77e67
|
| 3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915916176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0feb6e3fd440cd1b7db08ccf066c480172161987639690dda3ca7680c930f6ef
|
| 3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1168138808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:646ec58c6e3cd775c7ec73fa0c632e2d155fb68dadb8ec308cd29d06f7567d9a
|
| 3 |
size 1168138808
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"total_flos": 0.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second": 0.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"total_flos": 0.0,
|
| 3 |
+
"train_loss": 2.0727225511886656,
|
| 4 |
+
"train_runtime": 64632.8349,
|
| 5 |
+
"train_samples": 5455,
|
| 6 |
+
"train_samples_per_second": 0.084,
|
| 7 |
+
"train_steps_per_second": 0.021
|
| 8 |
}
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|