Downloads · 30 days
196
0% of all-time downloads
speechless-coder-ds-1.3b
uukuguy/speechless-coder-ds-1.3b
speechless-coder-ds-1.3b is a text generation model from uukuguy. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
40K
Public
Repo size
5.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin2.7 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Dec 30, 2023
- Updated
- Dec 30, 2023
- SHA
- 12302c9d
Try a prompt
Model card
From the Hugging Face model README
<p><h1> speechless-coder-ds-1.3b </h1></p>
Use the following dataset to fine-tune deepseek-ai/deepseek-coder-1.3b in order to improve the model's reasoning and planning abilities.
context window length: 8192 max_tokens > 128 && < 8192
Total 185,193 samples 426 MB
- ise-uiuc/Magicoder-OSS-Instruct-75K 75,186 samples
- ise-uiuc/Magicoder-Evol-Instruct-110K 110,007 samples
50 samples/T=0.2/MaxTokens=512/Top_P=0.95
Code: https://github.com/uukuguy/speechless
How to Prompt the Model
This model accepts the Alpaca instruction format.
For example:
You are an intelligent programming assistant.
### Instruction:
Implement a linked list in C++
### Response:
HumanEval
| Metric | Value |
|---|---|
| humaneval-python |
CodeLlama-34B-Python: 53.29
CodeLlama-34B-Instruct: 50.79
CodeLlama-13B-Instruct: 50.6
CodeLlama-34B: 45.11
CodeLlama-13B-Python: 42.89
CodeLlama-13B: 35.07
BigCode Eval
0.205055
- metrics_humanevalfixtests-cpp: "pass@1": 0.054878048780487805
- metrics_humanevalfixtests-go: "pass@1": 0.054878048780487805
- metrics_humanevalfixtests-java: "pass@1": 0.042682926829268296
- metrics_humanevalfixtests-js: "pass@1": 0.0975609756097561
- metrics_humanevalfixtests-python: "pass@1": 0.06707317073170732
- metrics_humanevalfixtests-rust: "pass@1": 0.018292682926829267
0.332906
- metrics_humanevalsynthesize-cpp: "pass@1": 0.3475609756097561
- metrics_humanevalsynthesize-go: "pass@1": 0.25609756097560976
- metrics_humanevalsynthesize-java: "pass@1": 0.3353658536585366
- metrics_humanevalsynthesize-js: "pass@1": 0.35365853658536583
- metrics_humanevalsynthesize-python: "pass@1": 0.4024390243902439
- metrics_humanevalsynthesize-rust: "pass@1": 0.20121951219512196
- metrics_mbpp: "pass@1": 0.434
LMEval
| Metric | Value |
|---|---|
| ARC | |
| HellaSwag | |
| MMLU | |
| TruthfulQA | |
| Average |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- apache-2.0
- Languages
- en
- Created
- Dec 30, 2023
- Updated
- Dec 30, 2023