Egrigor commited on
Commit
df0faf5
·
verified ·
1 Parent(s): e38ef18

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -19
README.md CHANGED
@@ -37,7 +37,7 @@ This model has been fine-tuned on [Egrigor/ValheimTestData](https://huggingface.
37
 
38
  To load and interact with the model, use the following code:
39
 
40
- ```python
41
  from transformers import AutoModelForCausalLM, AutoTokenizer
42
 
43
  model = AutoModelForCausalLM.from_pretrained("Egrigor/ValheimAssistantV1")
@@ -46,41 +46,44 @@ tokenizer = AutoTokenizer.from_pretrained("Egrigor/ValheimAssistantV1")
46
  inputs = tokenizer("How do I build a crafting station?", return_tensors="pt")
47
  outputs = model.generate(**inputs, max_length=100)
48
  print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 
49
  Training Details
 
 
 
50
  Framework: Unsloth
 
51
  Batch Size per Device: 2
 
52
  Gradient Accumulation Steps: 4
 
53
  Learning Rate: 2e-4
 
54
  Total Training Steps: 60
 
55
  Training Time: ~3.5 minutes
 
 
56
  Dataset
 
57
  The dataset consists of gameplay tips, lore insights, and strategic guidance, formatted into conversational question-and-answer pairs.
58
 
59
  Note: As this dataset was semi-automatically generated from community resources, it may contain inaccuracies or gaps. Feedback is welcome for future improvements.
60
 
 
61
  Limitations and Future Work
62
- Dataset Gaps: The dataset may not fully cover Valheim's gameplay and lore, and some responses may be incomplete or inaccurate.
 
 
63
  Generalization: This model is focused solely on Valheim-related content and may not perform well in other contexts.
 
64
  Iterative Improvement: Future versions will refine the dataset and model based on testing and community feedback.
 
 
65
  Contact and Feedback
66
- This is an experimental project created by a novice AI enthusiast. Feedback, suggestions, and collaborations are highly welcome! Feel free to reach out via Hugging Face.
67
 
68
- Citation
69
- If you use this model, please consider citing it:
70
-
71
- less
72
- Copy
73
- Edit
74
- @misc{Egrigor_ValheimAssistantV1_2025,
75
- author = {Egrigor},
76
- title = {Valheim Assistant V1 - Fine-Tuned with Unsloth},
77
- year = {2025},
78
- publisher = {Hugging Face},
79
- howpublished = {\url{https://huggingface.co/Egrigor/ValheimAssistantV1}},
80
- }
81
- yaml
82
- Copy
83
- Edit
84
 
85
  ---
86
 
 
37
 
38
  To load and interact with the model, use the following code:
39
 
40
+ python
41
  from transformers import AutoModelForCausalLM, AutoTokenizer
42
 
43
  model = AutoModelForCausalLM.from_pretrained("Egrigor/ValheimAssistantV1")
 
46
  inputs = tokenizer("How do I build a crafting station?", return_tensors="pt")
47
  outputs = model.generate(**inputs, max_length=100)
48
  print(tokenizer.decode(outputs[0], skip_special_tokens=True))
49
+
50
+
51
  Training Details
52
+
53
+
54
+
55
  Framework: Unsloth
56
+
57
  Batch Size per Device: 2
58
+
59
  Gradient Accumulation Steps: 4
60
+
61
  Learning Rate: 2e-4
62
+
63
  Total Training Steps: 60
64
+
65
  Training Time: ~3.5 minutes
66
+
67
+
68
  Dataset
69
+
70
  The dataset consists of gameplay tips, lore insights, and strategic guidance, formatted into conversational question-and-answer pairs.
71
 
72
  Note: As this dataset was semi-automatically generated from community resources, it may contain inaccuracies or gaps. Feedback is welcome for future improvements.
73
 
74
+
75
  Limitations and Future Work
76
+
77
+ Dataset Gaps: The dataset may not fully cover Valheims gameplay and lore, and some responses may be incomplete or inaccurate.
78
+
79
  Generalization: This model is focused solely on Valheim-related content and may not perform well in other contexts.
80
+
81
  Iterative Improvement: Future versions will refine the dataset and model based on testing and community feedback.
82
+
83
+
84
  Contact and Feedback
 
85
 
86
+ This is an experimental project created by a novice AI enthusiast. Feedback, suggestions, and collaborations are highly welcome! Feel free to reach out via Hugging Face.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
 
88
  ---
89