ByteForge/DS-7b-1.5_Instruct-ct2-int8_float32

[🏠Homepage] | [🤖 Chat with DeepSeek Coder] | [Discord] | [Wechat(微信)]

---

1. Introduction of Deepseek-Coder-7B-Instruct v1.5

Deepseek-Coder-7B-Instruct-v1.5 is continue pre-trained from Deepseek-LLM 7B on 2T tokens by employing a window size of 4K and next token prediction objective, and then fine-tuned on 2B tokens of instruction data.

• Home Page: DeepSeek
• Repository: deepseek-ai/deepseek-coder
• Chat With DeepSeek Coder: DeepSeek-Coder

2. Evaluation Results

3. How to Use

Here give some examples of how to use our model.

Chat Model Inference

import ctranslate2
import transformers

from huggingface_hub import snapshot_download
model_id = "ByteForge/DS-7b-1.5_Instruct-ct2-int8_float32"
model_path = snapshot_download(model_id)
model = ctranslate2.Generator(model_path, device='cuda')
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)

prompt= "plot a cgart for visualising employee and their years of experience.Assume any sample data df"

messages = [
    {"role": "system", "content": "You are world class python programmer with deep expertise in Ploty for data visualisation and analysis. Given a input question and schema, answer with correct python plotly code"},
    {"role": "user", "content": prompt},
]

input_ids = tokenizer1.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

terminators = [
    tokenizer1.eos_token_id,
    tokenizer1.convert_tokens_to_ids("<|eot_id|>")
]

input_tokens = tokenizer1.convert_ids_to_tokens(tokenizer1.encode(input_ids))

results = model1.generate_batch([input_tokens], include_prompt_in_result=False, max_length=700, sampling_temperature=0.6, sampling_topp=0.9, end_token=terminators)
output = tokenizer1.decode(results[0].sequences_ids[0])

print(output)

4. License

This code repository is licensed under the MIT License. The use of DeepSeek Coder models is subject to the Model License. DeepSeek Coder supports commercial use.

See the LICENSE-MODEL for more details.

5. Contact

If you have any questions, please raise an issue or contact us at [email protected].