File size: 3,422 Bytes
88c0d5f 0ebcc3e 88c0d5f 0ebcc3e b48c71e 0ebcc3e |
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 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
---
library_name: transformers
tags:
- merge
language:
- en
- es
- ru
- zh
- de
- fr
- th
- ca
- it
- ja
- pl
- eo
- eu
- vi
- fi
- hu
- ar
- nl
- da
- tr
- ko
- he
- id
- cs
- bn
- sv
widget:
- text: |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
podrias escribir un codigo de ejemplo en Python<|im_end|>
<|im_start|>assistant
license: apache-2.0
---
# Model Card for Model MixLlama
<!-- Provide a quick summary of what the model is/does. -->
```Python
experts:
- source_model: NickyNicky/TinyDolphin-2.8-1.1b_oasst2_chatML_Cluster_1_V1
positive_prompts:
- ""
- source_model: NickyNicky/TinyDolphin-2.8-1.1b_oasst2_chatML_Cluster_2_V1
positive_prompts:
- ""
- source_model: NickyNicky/TinyDolphin-2.8-1.1b_oasst2_chatML_Cluster_3_V1
positive_prompts:
- ""
base_model: NickyNicky/TinyDolphin-2.8-1.1b_oasst2_chatML_Cluster_1_V1
gate_mode: random # one of "hidden", "cheap_embed", or "random"
dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
```
```Python
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
HfArgumentParser,
TrainingArguments,
pipeline,
logging,
GenerationConfig,
TextIteratorStreamer,
)
import torch
new_model= "NickyNicky/Mixtral-4x1.1B-TinyDolphin-2.8-1.1b_oasst2_chatML_Cluster"
model = AutoModelForCausalLM.from_pretrained(#f'NickyNicky/{new_model}',
new_model,
device_map="auto",
trust_remote_code=True,
torch_dtype=torch.bfloat16,
low_cpu_mem_usage= True,
# use_flash_attention_2=False,
)
tokenizer = AutoTokenizer.from_pretrained(new_model,
max_length=2048,
trust_remote_code=True,
use_fast = True,
)
tokenizer.pad_token = tokenizer.eos_token
# tokenizer.padding_side = 'left'
tokenizer.padding_side = 'right'
prompt= """<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
escribe una historia de amor.<|im_end|>
<|im_start|>assistant
"""
inputs = tokenizer.encode(prompt,
return_tensors="pt",
add_special_tokens=False).cuda()#.to("cuda") # False # True
generation_config = GenerationConfig(
max_new_tokens=700,
temperature=0.5,
top_p=0.9,
top_k=40,
repetition_penalty=1.1, #1.1, # 1.0 means no penalty, > 1.0 means penalty, 1.2 from CTRL paper
do_sample=True,
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id,
)
outputs = model.generate(
generation_config=generation_config,
input_ids=inputs,)
# tokenizer.decode(outputs[0], skip_special_tokens=False) #True
print(tokenizer.decode(outputs[0], skip_special_tokens=False))
``` |