utkmst commited on
Commit
3218d26
·
verified ·
1 Parent(s): 673f949

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -81
README.md CHANGED
@@ -1,109 +1,39 @@
1
  ---
2
- base_model:
3
- - meta-llama/Llama-3.1-8B-Instruct
4
- language:
5
- - en
 
6
  tags:
7
  - llama-3.1
8
  - instruction-tuned
9
- - fine-tuned
10
- - merged-lora
11
- license: llama3.1
12
  datasets:
13
  - OpenAssistant/oasst1
14
  - databricks/databricks-dolly-15k
15
  - Open-Orca/OpenOrca
16
- - mlabonne/open-perfectblend
17
- - tatsu-lab/alpaca
18
- model-index:
19
- - name: utkmst/chimera-beta-test2-lora-merged
20
- results:
21
- - task:
22
- type: text-generation
23
- name: Text Generation
24
- metrics:
25
- - name: Training Loss
26
- type: loss
27
- value: 2.143046485595703
28
- pipeline_tag: text-generation
29
  ---
30
 
 
31
  # utkmst/chimera-beta-test2-lora-merged
32
 
33
  ## Model Description
34
- This model (`utkmst/chimera-beta-test2-lora-merged`) is a fine-tuned version of Meta's Llama-3.1-8B-Instruct model. It was created through LoRA fine-tuning on a mixture of high-quality instruction datasets, followed by merging the adapter weights with the base model, producing a fully-merged model in SafeTensors format.
35
-
36
- ## Architecture
37
- - **Base Model**: meta-llama/Llama-3.1-8B-Instruct
38
- - **Size**: 8.03B parameters
39
- - **Type**: Decoder-only transformer
40
- - **Format**: SafeTensors (full precision)
41
 
42
  ## Training Details
 
43
  - **Training Method**: LoRA fine-tuning followed by adapter merging
44
- - **LoRA Configuration**:
45
- - Rank: 8
46
- - Alpha: 16
47
- - Trainable modules: Attention layers and feed-forward networks
48
- - **Training Hyperparameters**:
49
- - Learning rate: 2e-4
50
- - Batch size: 2
51
- - Training epochs: 1
52
- - Optimizer: AdamW with constant scheduler
53
 
54
- ## Dataset
55
- The model was trained on a curated mixture of high-quality instruction datasets:
56
- - OpenAssistant/oasst1: Human-generated conversations with AI assistants
57
- - databricks/databricks-dolly-15k: Instruction-following examples
58
- - Open-Orca/OpenOrca: Augmented training data based on GPT-4 generations
59
- - mlabonne/open-perfectblend: A carefully balanced blend of open-source instruction data
60
- - tatsu-lab/alpaca: Self-instructed data based on demonstrations
61
-
62
- ## Intended Use
63
- This model is designed for:
64
- - General purpose assistant capabilities
65
- - Question answering and knowledge retrieval
66
- - Creative content generation
67
- - Instructional guidance
68
-
69
- ## Limitations
70
- - Base model limitations including potential hallucinations and factual inaccuracies
71
- - Limited context window compared to larger models
72
- - Knowledge cutoff from the base Llama-3.1 model
73
- - May exhibit biases present in training data
74
- - Performance on specialized tasks may vary
75
 
76
  ## Usage with Transformers
77
 
78
  ```python
79
  from transformers import AutoModelForCausalLM, AutoTokenizer
80
 
81
- # Load model
82
  model = AutoModelForCausalLM.from_pretrained("utkmst/chimera-beta-test2-lora-merged")
83
  tokenizer = AutoTokenizer.from_pretrained("utkmst/chimera-beta-test2-lora-merged")
84
-
85
- # Format prompt according to Llama 3.1 chat template
86
- messages = [
87
- {"role": "user", "content": "Tell me about the solar system."}
88
- ]
89
- prompt = tokenizer.apply_chat_template(messages, tokenize=False)
90
-
91
- # Generate response
92
- inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
93
- outputs = model.generate(
94
- inputs["input_ids"],
95
- max_new_tokens=512,
96
- temperature=0.7,
97
- top_p=0.9,
98
- )
99
- response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
100
- print(response)
101
  ```
102
-
103
- ## Quantized Version
104
-
105
- A quantized GGUF version of this model is also available at utkmst/chimera-beta-test2-lora-merged-Q4_K_M-GGUF for deployment in resource-constrained environments.
106
-
107
  ## License
108
 
109
- This model inherits the license from Meta's Llama 3.1. Users must comply with the Llama 3 license terms and conditions.
 
1
  ---
2
+ language: en
3
+ library_name: transformers
4
+ license: llama3.1
5
+ base_model: meta-llama/Llama-3.1-8B-Instruct
6
+ pipeline_tag: text-generation
7
  tags:
8
  - llama-3.1
9
  - instruction-tuned
 
 
 
10
  datasets:
11
  - OpenAssistant/oasst1
12
  - databricks/databricks-dolly-15k
13
  - Open-Orca/OpenOrca
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
 
16
+
17
  # utkmst/chimera-beta-test2-lora-merged
18
 
19
  ## Model Description
20
+ This model is a fine-tuned version of Meta's Llama-3.1-8B-Instruct model, created through LoRA fine-tuning on multiple instruction datasets, followed by merging the adapter weights with the base model.
 
 
 
 
 
 
21
 
22
  ## Training Details
23
+ - **Base Model**: meta-llama/Llama-3.1-8B-Instruct
24
  - **Training Method**: LoRA fine-tuning followed by adapter merging
25
+ - **Datasets Used**: OpenAssistant/oasst1, databricks/databricks-dolly-15k, Open-Orca/OpenOrca, and others
 
 
 
 
 
 
 
 
26
 
27
+ (You can add more details from your original card here if desired)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
 
29
  ## Usage with Transformers
30
 
31
  ```python
32
  from transformers import AutoModelForCausalLM, AutoTokenizer
33
 
 
34
  model = AutoModelForCausalLM.from_pretrained("utkmst/chimera-beta-test2-lora-merged")
35
  tokenizer = AutoTokenizer.from_pretrained("utkmst/chimera-beta-test2-lora-merged")
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  ```
 
 
 
 
 
37
  ## License
38
 
39
+ This model inherits the license from Meta's Llama 3.1.