Hugging Face's logo

afrideva
/
phi-2-chat-GGUF

Text Generation
GGUF
English
ggml
quantized
q2_k
q3_k_m
q4_k_m
q5_k_m
q6_k
q8_0
Model card Files Community
phi-2-chat-GGUF / README.md
afrideva's picture
afrideva
Upload README.md with huggingface_hub
9db2788
preview code
|
raw
history blame contribute delete
3.14 kB
metadata
base_model: malhajar/phi-2-chat
datasets:
  - yahma/alpaca-cleaned
inference: false
language:
  - en
model_creator: malhajar
model_name: phi-2-chat
pipeline_tag: text-generation
quantized_by: afrideva
tags:
  - gguf
  - ggml
  - quantized
  - q2_k
  - q3_k_m
  - q4_k_m
  - q5_k_m
  - q6_k
  - q8_0

malhajar/phi-2-chat-GGUF

Quantized GGUF model files for phi-2-chat from malhajar

Name Quant method Size
phi-2-chat.fp16.gguf fp16 5.56 GB
phi-2-chat.q2_k.gguf q2_k 1.17 GB
phi-2-chat.q3_k_m.gguf q3_k_m 1.48 GB
phi-2-chat.q4_k_m.gguf q4_k_m 1.79 GB
phi-2-chat.q5_k_m.gguf q5_k_m 2.07 GB
phi-2-chat.q6_k.gguf q6_k 2.29 GB
phi-2-chat.q8_0.gguf q8_0 2.96 GB

Original Model Card:

Model Card for Model ID

malhajar/phi-2-chat is a finetuned version of phi-2 using SFT Training. This model can answer information in a chat format as it is finetuned specifically on instructions specifically alpaca-cleaned

Model Description

Prompt Template 

### Instruction:

<prompt> (without the <>)

### Response:

How to Get Started with the Model

Use the code sample provided in the original post to interact with the model.

from transformers import AutoTokenizer,AutoModelForCausalLM
 
model_id = "malhajar/phi-2-chat"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             torch_dtype=torch.float16,
                                             revision="main")

tokenizer = AutoTokenizer.from_pretrained(model_id)

question: "Türkiyenin en büyük şehir nedir?"
# For generating a response
prompt = '''
### Instruction:  {question} ### Response:
'''
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
output = model.generate(inputs=input_ids,max_new_tokens=512,pad_token_id=tokenizer.eos_token_id,top_k=50, do_sample=True,repetition_penalty=1.3
        top_p=0.95,trust_remote_code=True,)
response = tokenizer.decode(output[0])

print(response)