Commit
•
dbeb915
1
Parent(s):
ac6ce97
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: gpl-3.0
|
|
| 3 |
---
|
| 4 |
# A Chat Model
|
| 5 |
|
|
|
|
|
|
|
| 6 |
Use the transformers library that does not require remote/external code to load the model, AutoModelForCausalLM and AutoTokenizer (or manually specify LlamaForCausalLM to load LM, GPT2Tokenizer to load Tokenizer), and model quantization should be fully compatible with GGUF (llama.cpp), GPTQ, and AWQ.
|
| 7 |
|
| 8 |
*Do not use wikitext for recalibration.*
|
|
|
|
| 3 |
---
|
| 4 |
# A Chat Model
|
| 5 |
|
| 6 |
+
It should take an hour or so to be uploaded, and I am working on a gguf version.
|
| 7 |
+
|
| 8 |
Use the transformers library that does not require remote/external code to load the model, AutoModelForCausalLM and AutoTokenizer (or manually specify LlamaForCausalLM to load LM, GPT2Tokenizer to load Tokenizer), and model quantization should be fully compatible with GGUF (llama.cpp), GPTQ, and AWQ.
|
| 9 |
|
| 10 |
*Do not use wikitext for recalibration.*
|