初始化项目，由ModelHub XC社区提供模型
Model: second-state/llm-compiler-7b-ftd-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
78
README.md
Normal file
78
README.md
Normal file
@@ -0,0 +1,78 @@
|
||||
---
|
||||
language:
|
||||
- code
|
||||
license: other
|
||||
model_name: llm-compiler-7b
|
||||
base_model: facebook/llm-compiler-7b-ftd
|
||||
inference: false
|
||||
model_creator: facebook
|
||||
quantized_by: Second State Inc.
|
||||
---
|
||||
|
||||
<!-- header start -->
|
||||
<!-- 200823 -->
|
||||
<div style="width: auto; margin-left: auto; margin-right: auto">
|
||||
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
||||
</div>
|
||||
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
||||
<!-- header end -->
|
||||
|
||||
|
||||
# llm-compiler-7b-ftd-GGUF
|
||||
|
||||
## Original Model
|
||||
|
||||
[facebook/llm-compiler-7b-ftd](https://huggingface.co/facebook/llm-compiler-7b-ftd)
|
||||
|
||||
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
|
||||
|
||||
## Run with LlamaEdge
|
||||
|
||||
<!-- - LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above -->
|
||||
|
||||
- LlamaEdge version: coming soon
|
||||
|
||||
<!-- - Prompt template
|
||||
|
||||
- Prompt type: `codellama-instruct`
|
||||
|
||||
- Prompt string
|
||||
|
||||
```text
|
||||
[INST] {system_message}
|
||||
|
||||
<code>
|
||||
{user_message}
|
||||
</code>[/INST]
|
||||
```
|
||||
|
||||
**Note** that the `system_message` should be `Tell me how to optimize this LLVM-IR for object file size:` or `Disassemble this code to LLVM-IR:`.
|
||||
|
||||
- Context size: `4096`
|
||||
|
||||
- Run as LlamaEdge command app
|
||||
|
||||
```bash
|
||||
wasmedge --dir .:. --nn-preload default:GGML:AUTO:llm-compiler-7b-ftd-Q5_K_M.gguf llama-chat.wasm -p codellama-instruct
|
||||
``` -->
|
||||
|
||||
|
||||
## Quantized GGUF Models
|
||||
|
||||
| Name | Quant method | Bits | Size | Use case |
|
||||
| ---- | ---- | ---- | ---- | ----- |
|
||||
| [llm-compiler-7b-ftd-Q2_K.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q2_K.gguf) | Q2_K | 2 | 2.53 GB| smallest, significant quality loss - not recommended for most purposes |
|
||||
| [llm-compiler-7b-ftd-Q3_K_L.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q3_K_L.gguf) | Q3_K_L | 3 | 3.6 GB| small, substantial quality loss |
|
||||
| [llm-compiler-7b-ftd-Q3_K_M.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q3_K_M.gguf) | Q3_K_M | 3 | 3.3 GB| very small, high quality loss |
|
||||
| [llm-compiler-7b-ftd-Q3_K_S.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| very small, high quality loss |
|
||||
| [llm-compiler-7b-ftd-Q4_0.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
||||
| [llm-compiler-7b-ftd-Q4_K_M.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| medium, balanced quality - recommended |
|
||||
| [llm-compiler-7b-ftd-Q4_K_S.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| small, greater quality loss |
|
||||
| [llm-compiler-7b-ftd-Q5_0.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
||||
| [llm-compiler-7b-ftd-Q5_K_M.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| large, very low quality loss - recommended |
|
||||
| [llm-compiler-7b-ftd-Q5_K_S.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| large, low quality loss - recommended |
|
||||
| [llm-compiler-7b-ftd-Q6_K.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q6_K.gguf) | Q6_K | 6 | 5.53 GB| very large, extremely low quality loss |
|
||||
| [llm-compiler-7b-ftd-Q8_0.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| very large, extremely low quality loss - not recommended |
|
||||
| [llm-compiler-7b-ftd-f16.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-f16.gguf) | f16 | f16 | 13.5 GB| |
|
||||
|
||||
*Quantized with llama.cpp b3259*
|
||||
Reference in New Issue
Block a user