fix readme
Browse files- README.md +28 -1
- eval_loss.png +0 -0
- eval_runtime.png +0 -0
- eval_sample_per_secs.png +0 -0
- eval_sps.png +0 -0
- train_loss.png +0 -0
README.md
CHANGED
@@ -10,4 +10,31 @@ inference:
|
|
10 |
parameters:
|
11 |
model_file: meng-coding-skill.gguf
|
12 |
temperature: 1
|
13 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
parameters:
|
11 |
model_file: meng-coding-skill.gguf
|
12 |
temperature: 1
|
13 |
+
---
|
14 |
+
# Programming Skills Learning Path Model
|
15 |
+
|
16 |
+
This model is a fine-tuned version of the base mdoel designed to generate path of learning a skill based on input text. It's particularly useful for identifying emerging trends and skill combinations in the rapidly evolving tech landscape.
|
17 |
+
|
18 |
+
## Usage & Limitations
|
19 |
+
|
20 |
+
The model is intended for:
|
21 |
+
- Deploying in limited CPU resource, with average about 40 tps on 1 CPU core
|
22 |
+
|
23 |
+
The model has limits:
|
24 |
+
- The dataset might not capture the very latest tools development in programming world
|
25 |
+
- Chatbot usecase does not fit the model usecase
|
26 |
+
|
27 |
+
Please note that this model was trained on a custom dataset and may reflect biases present in that data.
|
28 |
+
|
29 |
+
### Training Hyperparameters
|
30 |
+
|
31 |
+
- **Batch Size:** 4
|
32 |
+
- **Optimizer:** Experimental GrokAdamW
|
33 |
+
|
34 |
+
## Metrics
|
35 |
+
|
36 |
+
![Eval Loss](eval_loss.png)
|
37 |
+
![Eval Runtime](eval_runtime.png)
|
38 |
+
![Eval Sample Per Seconds](eval_sample_per_secs.png)
|
39 |
+
![Eval Steps per Seconds](eval_sps.png)
|
40 |
+
![Loss on Train](train_loss.png)
|
eval_loss.png
ADDED
eval_runtime.png
ADDED
eval_sample_per_secs.png
ADDED
eval_sps.png
ADDED
train_loss.png
ADDED