Safetensors
English
mistral
codestral-22b
unsloth
finetuned
large-language-model
typeinference
python
Instructions to use rbharmal/finetuned_Codestral-22B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- Unsloth Studio
How to use rbharmal/finetuned_Codestral-22B-v0.1 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for rbharmal/finetuned_Codestral-22B-v0.1 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for rbharmal/finetuned_Codestral-22B-v0.1 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for rbharmal/finetuned_Codestral-22B-v0.1 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="rbharmal/finetuned_Codestral-22B-v0.1", max_seq_length=2048, )
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,64 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- codestral-22b
|
| 5 |
+
- unsloth
|
| 6 |
+
- finetuned
|
| 7 |
+
- large-language-model
|
| 8 |
+
- typeinference
|
| 9 |
+
- python
|
| 10 |
+
language:
|
| 11 |
+
- en
|
| 12 |
+
datasets:
|
| 13 |
+
- rbharmal/ManyType4Py
|
| 14 |
+
base_model:
|
| 15 |
+
- mistralai/Codestral-22B-v0.1
|
| 16 |
+
model_name: rbharmal/finetuned_Codestral-22B-v0.1
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# finetuned_Codestral-22B-v0.1
|
| 20 |
+
|
| 21 |
+
🚀 **Finetuned version of [mistralai/Codestral-22B-v0.1](https://huggingface.co/mistralai/Codestral-22B-v0.1) by [rbharmal](https://huggingface.co/rbharmal).**
|
| 22 |
+
|
| 23 |
+
This model is finetuned for Type Inference in Python.
|
| 24 |
+
It was trained using [Unsloth](https://github.com/unslothai/unsloth) for optimized fine-tuning and uses merged LoRA weights for easier deployment.
|
| 25 |
+
|
| 26 |
+
## Model Details
|
| 27 |
+
- **Base Model**: Codestral-22B-v0.1
|
| 28 |
+
- **Finetuning Method**: LoRA (merged)
|
| 29 |
+
- **Context Length**: 4,000 tokens
|
| 30 |
+
- **Quantization**: None (full precision, bfloat16)
|
| 31 |
+
- **Optimizations**: Gradient Checkpointing, 4-bit loading during training
|
| 32 |
+
|
| 33 |
+
## How to Use
|
| 34 |
+
|
| 35 |
+
```python
|
| 36 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 37 |
+
|
| 38 |
+
model = AutoModelForCausalLM.from_pretrained("rbharmal/finetuned_Codestral-22B-v0.1")
|
| 39 |
+
tokenizer = AutoTokenizer.from_pretrained("rbharmal/finetuned_Codestral-22B-v0.1")
|
| 40 |
+
|
| 41 |
+
prompt = "
|
| 42 |
+
## Task Description
|
| 43 |
+
|
| 44 |
+
**Objective**: Examine and identify the data types of various elements such as function parameters, local variables, and function return types in the given Python code.
|
| 45 |
+
|
| 46 |
+
**Instructions**:
|
| 47 |
+
1. For each question below, provide a concise, one-word answer indicating the data type.
|
| 48 |
+
2. For arguments and variables inside a function, list every data type they take within the current program context as a comma separated list.
|
| 49 |
+
3. Do not include additional explanations or commentary in your answers.
|
| 50 |
+
4. If a type's nested level exceeds 2, replace all components at that level and beyond with Any
|
| 51 |
+
|
| 52 |
+
**Python Code Provided**:
|
| 53 |
+
def param_func(x):
|
| 54 |
+
return x
|
| 55 |
+
|
| 56 |
+
c = param_func("Hello")
|
| 57 |
+
|
| 58 |
+
**Questions**:
|
| 59 |
+
1. What is the return type of the function 'param_func' at line 1, column 5?
|
| 60 |
+
2. What is the type of the parameter 'x' at line 1, column 15, in the function 'param_func'?
|
| 61 |
+
3. What is the type of the variable 'c' at line 4, column 1? "
|
| 62 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
| 63 |
+
outputs = model.generate(**inputs, max_new_tokens=200)
|
| 64 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|