Update README.md
Browse files
README.md
CHANGED
|
@@ -238,44 +238,4 @@ You can either specify a new local-dir (Meta-Llama-3.1-8B-Q8_0) or download them
|
|
| 238 |
|
| 239 |
## Reproducibility
|
| 240 |
|
| 241 |
-
|
| 242 |
-
|
| 243 |
-
```
|
| 244 |
-
git lfs install
|
| 245 |
-
git clone https://huggingface.co/meta-llama/Meta-Llama-3.1-8B
|
| 246 |
-
```
|
| 247 |
-
|
| 248 |
-
### Quantization
|
| 249 |
-
|
| 250 |
-
```
|
| 251 |
-
cd llama.cpp
|
| 252 |
-
python ./convert_hf_to_gguf.py ../Meta-Llama-3.1-8B --outtype bf16 --outfile ../Meta-Llama-3.1-8B.BF16.gguf
|
| 253 |
-
python ./convert_hf_to_gguf.py ../Meta-Llama-3.1-8B --outtype f16 --outfile ../Meta-Llama-3.1-8B-FP16.gguf
|
| 254 |
-
python ./convert_hf_to_gguf.py ../Meta-Llama-3.1-8B --outtype q8_0 --outfile ../Meta-Llama-3.1-8B-Q8_0.gguf
|
| 255 |
-
./llama-quantize ../Meta-Llama-3.1-8B.BF16.gguf ../Meta-Llama-3.1-8B-Q6_K.gguf Q6_K
|
| 256 |
-
./llama-quantize ../Meta-Llama-3.1-8B.BF16.gguf ../Meta-Llama-3.1-8B-Q5_K_S.gguf Q5_K_S
|
| 257 |
-
./llama-quantize ../Meta-Llama-3.1-8B.BF16.gguf ../Meta-Llama-3.1-8B-Q5_K_M.gguf Q5_K_M
|
| 258 |
-
./llama-quantize ../Meta-Llama-3.1-8B.BF16.gguf ../Meta-Llama-3.1-8B-Q4_K_M.gguf Q4_K_M
|
| 259 |
-
./llama-quantize ../Meta-Llama-3.1-8B.BF16.gguf ../Meta-Llama-3.1-8B-Q4_K_S.gguf Q4_K_S
|
| 260 |
-
./llama-quantize ../Meta-Llama-3.1-8B.BF16.gguf ../Meta-Llama-3.1-8B-Q3_K_L.gguf Q3_K_L
|
| 261 |
-
./llama-quantize ../Meta-Llama-3.1-8B.BF16.gguf ../Meta-Llama-3.1-8B-Q3_K_M.gguf Q3_K_M
|
| 262 |
-
./llama-quantize ../Meta-Llama-3.1-8B.BF16.gguf ../Meta-Llama-3.1-8B-Q3_K_S.gguf Q3_K_S
|
| 263 |
-
./llama-quantize ../Meta-Llama-3.1-8B.BF16.gguf ../Meta-Llama-3.1-8B-Q2_K.gguf Q2_K
|
| 264 |
-
```
|
| 265 |
-
|
| 266 |
-
### Perplexity
|
| 267 |
-
|
| 268 |
-
```
|
| 269 |
-
cd llama.cpp
|
| 270 |
-
./llama-perplexity -m ../Meta-Llama-3.1-8B.BF16.gguf -f ../wikitext-2-raw/wiki.test.raw
|
| 271 |
-
./llama-perplexity -m ../Meta-Llama-3.1-8B-Q8_0.gguf -f ../wikitext-2-raw/wiki.test.raw
|
| 272 |
-
./llama-perplexity -m ../Meta-Llama-3.1-8B-Q6_K.gguf -f ../wikitext-2-raw/wiki.test.raw
|
| 273 |
-
./llama-perplexity -m ../Meta-Llama-3.1-8B-Q5_K_M.gguf -f ../wikitext-2-raw/wiki.test.raw
|
| 274 |
-
./llama-perplexity -m ../Meta-Llama-3.1-8B-Q5_K_S.gguf -f ../wikitext-2-raw/wiki.test.raw
|
| 275 |
-
./llama-perplexity -m ../Meta-Llama-3.1-8B-Q4_K_M.gguf -f ../wikitext-2-raw/wiki.test.raw
|
| 276 |
-
./llama-perplexity -m ../Meta-Llama-3.1-8B-Q4_K_S.gguf -f ../wikitext-2-raw/wiki.test.raw
|
| 277 |
-
./llama-perplexity -m ../Meta-Llama-3.1-8B-Q3_K_L.gguf -f ../wikitext-2-raw/wiki.test.raw
|
| 278 |
-
./llama-perplexity -m ../Meta-Llama-3.1-8B-Q3_K_M.gguf -f ../wikitext-2-raw/wiki.test.raw
|
| 279 |
-
./llama-perplexity -m ../Meta-Llama-3.1-8B-Q3_K_S.gguf -f ../wikitext-2-raw/wiki.test.raw
|
| 280 |
-
./llama-perplexity -m ../Meta-Llama-3.1-8B-Q2_K.gguf -f ../wikitext-2-raw/wiki.test.raw
|
| 281 |
-
```
|
|
|
|
| 238 |
|
| 239 |
## Reproducibility
|
| 240 |
|
| 241 |
+
https://github.com/ggerganov/llama.cpp/issues/8650#issuecomment-2261497976
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|