File size: 1,332 Bytes
887486f 077a648 e3464c0 077a648 d74711b 6e02c4c d74711b b5689bb d74711b 7fd60cb e3464c0 046a2ae |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 |
---
license: apache-2.0
---
### Quantization config
```
"zero_point": true,
"q_group_size": 128,
"w_bit": 4,
"version": "GEMM"
```
### Generate
```
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
from transformers import GenerationConfig
model_path = "gradjitta/Poro-34B-AWQ"
model = AutoAWQForCausalLM.from_quantized(model_path, fuse_layers=True, trust_remote_code=False, safetensors=True)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=False)
def generate(prompt):
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].cuda()
generation_output = model.generate(
input_ids=input_ids,
generation_config=GenerationConfig(pad_token_id=tokenizer.pad_token_id, temperature=1.0, top_p=0.99, top_k=50, num_beams=1, do_sample=True),
return_dict_in_generate=True,
output_scores=True,
max_new_tokens=256
)
for seq in generation_output.sequences:
output = tokenizer.decode(seq)
print(output)
generate("Suomalainen runo elämästä:")
```
### output
```
Suomalainen runo elämästä:
- se alkaa
- sitten ei enää mikään riitä
- se päättyy ja se alkaa</s>
```
### Work supported by https://datacrunch.io/
#### Quantized by: gradjitta |