Text Generation
Transformers
PyTorch
English
crystalcoder
llm
code
custom_code
Eval Results (legacy)
Instructions to use LLM360/CrystalChat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LLM360/CrystalChat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LLM360/CrystalChat", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("LLM360/CrystalChat", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LLM360/CrystalChat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LLM360/CrystalChat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM360/CrystalChat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LLM360/CrystalChat
- SGLang
How to use LLM360/CrystalChat 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 "LLM360/CrystalChat" \ --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": "LLM360/CrystalChat", "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 "LLM360/CrystalChat" \ --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": "LLM360/CrystalChat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LLM360/CrystalChat with Docker Model Runner:
docker model run hf.co/LLM360/CrystalChat
Update README.md
Browse files
README.md
CHANGED
|
@@ -201,6 +201,13 @@ As always, the training data, training code, and metrics are publicly available.
|
|
| 201 |
| Llama-2-7b-Chat | 2T | 34.11 | 52.86 | 15.35 | 53.07 | 78.39 | 48.42 | 18.88 | 73.09 | 45.30 | 13.26 | 17.43 |
|
| 202 |
| AmberChat 7B | 1.25T | - | 44.76 | - | 42.83 | 74.03 | 38.88 | 5.31 | 66.77 | 40.72 | - | - |
|
| 203 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 204 |
|
| 205 |
|
| 206 |
| Combined Language and Coding Ability |
|
|
|
|
| 201 |
| Llama-2-7b-Chat | 2T | 34.11 | 52.86 | 15.35 | 53.07 | 78.39 | 48.42 | 18.88 | 73.09 | 45.30 | 13.26 | 17.43 |
|
| 202 |
| AmberChat 7B | 1.25T | - | 44.76 | - | 42.83 | 74.03 | 38.88 | 5.31 | 66.77 | 40.72 | - | - |
|
| 203 |
|
| 204 |
+
| Model | Trained Tokens | ARC | HellaSwag | MMLU (5-shot) | GSM8K | Winogrande(5-shot) | TruthfulQA | HumanEval (pass@1) | MBPP (pass@1) |
|
| 205 |
+
|:------------------------:|:--------------:|:------------:|:-------------:|:-----------:|:-----:|:---------:|:-------------:|:-----:|:------------------:|
|
| 206 |
+
| CrystalChat 7B | 1.275T | 51.71 | 76.12 | 53.22 | 28.05 | 70.64 | 47.29 | 34.12 | 39.11 |
|
| 207 |
+
| Mistral-7B-Instruct-v0.1 | - | 58.05 | 75.71 | 55.56 | 32.00 | 74.27 | 55.90 | 29.27 | 31.96 |
|
| 208 |
+
| CodeLlama-7b-Instruct | 2.5T | 43.35 | 66.14 | 42.75 | 15.92 | 64.33 | 39.23 | 34.12 | 38.91 |
|
| 209 |
+
| Llama-2-7b-Chat | 2T | 53.07 | 78.39 | 48.42 | 18.88 | 73.09 | 45.30 | 13.26 | 17.43 |
|
| 210 |
+
| AmberChat 7B | 1.25T | 42.83 | 74.03 | 38.88 | 5.31 | 66.77 | 40.72 | - | - |
|
| 211 |
|
| 212 |
|
| 213 |
| Combined Language and Coding Ability |
|