metadata
base_model: ByteDance-Seed/Seed-Coder-8B-Reasoning
license: mit
model_creator: ByteDance-Seed
model_name: Seed-Coder-8B-Reasoning
quantized_by: Second State Inc.
Seed-Coder-8B-Reasoning-GGUF
Original Model
ByteDance-Seed/Seed-Coder-8B-Reasoning
Run with LlamaEdge
- LlamaEdge version: coming soon
Prompt template
Prompt type:
seed-reasoningPrompt string
<[begin▁of▁sentence]>user {user_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant {assistant_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>user {user_message_2}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant
Context size:
32000Run as LlamaEdge service
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Seed-Coder-8B-Reasoning-Q5_K_M.gguf \ llama-api-server.wasm \ --model-name Seed-Coder-8B-Reasoning \ --prompt-template seed-reasoning \ --ctx-size 32000
Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| Seed-Coder-8B-Reasoning-Q2_K.gguf | Q2_K | 2 | 3.30 GB | smallest, significant quality loss - not recommended for most purposes |
| Seed-Coder-8B-Reasoning-Q3_K_L.gguf | Q3_K_L | 3 | 4.46 GB | small, substantial quality loss |
| Seed-Coder-8B-Reasoning-Q3_K_M.gguf | Q3_K_M | 3 | 4.15 GB | very small, high quality loss |
| Seed-Coder-8B-Reasoning-Q3_K_S.gguf | Q3_K_S | 3 | 3.80 GB | very small, high quality loss |
| Seed-Coder-8B-Reasoning-Q4_0.gguf | Q4_0 | 4 | 4.81 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Seed-Coder-8B-Reasoning-Q4_K_M.gguf | Q4_K_M | 4 | 5.07 GB | medium, balanced quality - recommended |
| Seed-Coder-8B-Reasoning-Q4_K_S.gguf | Q4_K_S | 4 | 4.84 GB | small, greater quality loss |
| Seed-Coder-8B-Reasoning-Q5_0.gguf | Q5_0 | 5 | 5.76 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Seed-Coder-8B-Reasoning-Q5_K_M.gguf | Q5_K_M | 5 | 5.90 GB | large, very low quality loss - recommended |
| Seed-Coder-8B-Reasoning-Q5_K_S.gguf | Q5_K_S | 5 | 5.76 GB | large, low quality loss - recommended |
| Seed-Coder-8B-Reasoning-Q6_K.gguf | Q6_K | 6 | 6.78 GB | very large, extremely low quality loss |
| Seed-Coder-8B-Reasoning-Q8_0.gguf | Q8_0 | 8 | 8.77 GB | very large, extremely low quality loss - not recommended |
| Seed-Coder-8B-Reasoning-f16.gguf | f16 | 16 | 16.6 GB |
Quantized with llama.cpp b5341