Instructions to use TechxGenus/Seed-Coder-8B-Base-DWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use TechxGenus/Seed-Coder-8B-Base-DWQ with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("TechxGenus/Seed-Coder-8B-Base-DWQ") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use TechxGenus/Seed-Coder-8B-Base-DWQ with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "TechxGenus/Seed-Coder-8B-Base-DWQ" --prompt "Once upon a time"
| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 0, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.009882118, | |
| "intermediate_size": 14336, | |
| "layer_norm_eps": null, | |
| "max_position_embeddings": 32768, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "resid_pdrop": 0.1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.2", | |
| "use_cache": true, | |
| "vocab_size": 155136 | |
| } |