Edit model card

Llama-3-8B-Instruct-262k-GGUF

Original Model

gradientai/Llama-3-8B-Instruct-262k

Run with LlamaEdge

  • LlamaEdge version: v0.8.3 and above

  • Prompt template

    • Prompt type: llama-3-chat

    • Prompt string

      <|begin_of_text|><|start_header_id|>system<|end_header_id|>
      
      {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
      
      {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
      
      {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
      
      {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
      
  • Context size: 262144

  • Run as LlamaEdge service

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Instruct-262k-Q5_K_M.gguf \
      llama-api-server.wasm \
      --prompt-template llama-3-chat \
      --ctx-size 262144 \
      --model-name llama-3-8B-instruct-262k
    
  • Run as LlamaEdge command app

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Instruct-262k-Q5_K_M.gguf \
      llama-chat.wasm \
      --prompt-template llama-3-chat \
      --ctx-size 262144
    

Quantized GGUF Models

Name Quant method Bits Size Use case
Llama-3-8B-Instruct-262k-Q2_K.gguf Q2_K 2 3.18 GB smallest, significant quality loss - not recommended for most purposes
Llama-3-8B-Instruct-262k-Q3_K_L.gguf Q3_K_L 3 4.32 GB small, substantial quality loss
Llama-3-8B-Instruct-262k-Q3_K_M.gguf Q3_K_M 3 4.02 GB very small, high quality loss
Meta-Llama-3-70B-Instruct-Q3_K_S.gguf Q3_K_S 3 3.66 GB very small, high quality loss
Llama-3-8B-Instruct-262k-Q4_0.gguf Q4_0 4 4.66 GB legacy; small, very high quality loss - prefer using Q3_K_M
Llama-3-8B-Instruct-262k-Q4_K_M.gguf Q4_K_M 4 4.92 GB medium, balanced quality - recommended
Llama-3-8B-Instruct-262k-Q4_K_S.gguf Q4_K_S 4 4.69 GB small, greater quality loss
Llama-3-8B-Instruct-262k-Q5_0.gguf Q5_0 5 5.6 GB legacy; medium, balanced quality - prefer using Q4_K_M
Llama-3-8B-Instruct-262k-Q5_K_M.gguf Q5_K_M 5 5.73 GB large, very low quality loss - recommended
Llama-3-8B-Instruct-262k-Q5_K_S.gguf Q5_K_S 5 5.6 GB large, low quality loss - recommended
Llama-3-8B-Instruct-262k-Q6_K.gguf Q6_K 6 6.6 GB very large, extremely low quality loss
Llama-3-8B-Instruct-262k-Q8_0.gguf Q8_0 8 8.54 GB very large, extremely low quality loss - not recommended
Llama-3-8B-Instruct-262k-f16.gguf f16 16 16.1 GB

Quantized with llama.cpp b2734.

Downloads last month
299
GGUF
Model size
8.03B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference API (serverless) has been turned off for this model.

Quantized from