Update README.md
Browse files
README.md
CHANGED
@@ -62,6 +62,11 @@ language:
|
|
62 |
|
63 |
Original model: [rubra-ai/Meta-Llama-3-70B-Instruct](https://huggingface.co/rubra-ai/Meta-Llama-3-70B-Instruct)
|
64 |
|
|
|
|
|
|
|
|
|
|
|
65 |
## Model description
|
66 |
The model is the result of further post-training [meta-llama/Meta-Llama-3-70B](https://huggingface.co/meta-llama/Meta-Llama-3-70B). This model is designed for high performance in various instruction-following tasks and complex interactions, including multi-turn function calling and detailed conversations.
|
67 |
|
|
|
62 |
|
63 |
Original model: [rubra-ai/Meta-Llama-3-70B-Instruct](https://huggingface.co/rubra-ai/Meta-Llama-3-70B-Instruct)
|
64 |
|
65 |
+
AWQ quant config:
|
66 |
+
```
|
67 |
+
quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }
|
68 |
+
```
|
69 |
+
|
70 |
## Model description
|
71 |
The model is the result of further post-training [meta-llama/Meta-Llama-3-70B](https://huggingface.co/meta-llama/Meta-Llama-3-70B). This model is designed for high performance in various instruction-following tasks and complex interactions, including multi-turn function calling and detailed conversations.
|
72 |
|