Update README.md
Browse files
README.md
CHANGED
|
@@ -1,76 +1,3 @@
|
|
| 1 |
-
Hugging Face's logo
|
| 2 |
-
Hugging Face
|
| 3 |
-
Search models, datasets, users...
|
| 4 |
-
Models
|
| 5 |
-
Datasets
|
| 6 |
-
Spaces
|
| 7 |
-
Posts
|
| 8 |
-
Docs
|
| 9 |
-
Solutions
|
| 10 |
-
Pricing
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
DarqueDante
|
| 16 |
-
/
|
| 17 |
-
LLama-3-Mega-Dolphin-2.9.1-120b
|
| 18 |
-
|
| 19 |
-
like
|
| 20 |
-
0
|
| 21 |
-
Text Generation
|
| 22 |
-
Transformers
|
| 23 |
-
Safetensors
|
| 24 |
-
|
| 25 |
-
cognitivecomputations/Dolphin-2.9
|
| 26 |
-
|
| 27 |
-
teknium/OpenHermes-2.5
|
| 28 |
-
|
| 29 |
-
m-a-p/CodeFeedback-Filtered-Instruction
|
| 30 |
-
|
| 31 |
-
cognitivecomputations/dolphin-coder
|
| 32 |
-
|
| 33 |
-
cognitivecomputations/samantha-data
|
| 34 |
-
|
| 35 |
-
HuggingFaceH4/ultrachat_200k
|
| 36 |
-
|
| 37 |
-
microsoft/orca-math-word-problems-200k
|
| 38 |
-
|
| 39 |
-
abacusai/SystemChat-1.1
|
| 40 |
-
|
| 41 |
-
Locutusque/function-calling-chatml
|
| 42 |
-
|
| 43 |
-
internlm/Agent-FLAN
|
| 44 |
-
English
|
| 45 |
-
llama
|
| 46 |
-
mergekit
|
| 47 |
-
Merge
|
| 48 |
-
conversational
|
| 49 |
-
Inference Endpoints
|
| 50 |
-
text-generation-inference
|
| 51 |
-
Model card
|
| 52 |
-
Files and versions
|
| 53 |
-
Community
|
| 54 |
-
Settings
|
| 55 |
-
LLama-3-Mega-Dolphin-2.9.1-120b
|
| 56 |
-
/
|
| 57 |
-
README.md
|
| 58 |
-
|
| 59 |
-
DarqueDante's picture
|
| 60 |
-
DarqueDante
|
| 61 |
-
Update README.md
|
| 62 |
-
9f0a74b
|
| 63 |
-
VERIFIED
|
| 64 |
-
3 minutes ago
|
| 65 |
-
Preview
|
| 66 |
-
Code
|
| 67 |
-
|
|
| 68 |
-
raw
|
| 69 |
-
history
|
| 70 |
-
blame
|
| 71 |
-
edit
|
| 72 |
-
delete
|
| 73 |
-
2.68 kB
|
| 74 |
---
|
| 75 |
base_model:
|
| 76 |
- cognitivecomputations/dolphin-2.9.1-llama-3-70b
|
|
@@ -92,6 +19,7 @@ datasets:
|
|
| 92 |
- Locutusque/function-calling-chatml
|
| 93 |
- internlm/Agent-FLAN
|
| 94 |
---
|
|
|
|
| 95 |
|
| 96 |
|
| 97 |
# merge
|
|
@@ -152,6 +80,7 @@ You are Dolphin, a helpful AI assistant.<|im_end|>
|
|
| 152 |
|
| 153 |
|
| 154 |
## 💻 Usage
|
|
|
|
| 155 |
```python
|
| 156 |
!pip install -qU transformers accelerate
|
| 157 |
|
|
@@ -170,6 +99,7 @@ pipeline = transformers.pipeline(
|
|
| 170 |
torch_dtype=torch.float16,
|
| 171 |
device_map="auto",
|
| 172 |
)
|
|
|
|
| 173 |
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
| 174 |
print(outputs[0]["generated_text"])
|
| 175 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
- cognitivecomputations/dolphin-2.9.1-llama-3-70b
|
|
|
|
| 19 |
- Locutusque/function-calling-chatml
|
| 20 |
- internlm/Agent-FLAN
|
| 21 |
---
|
| 22 |
+
|
| 23 |
|
| 24 |
|
| 25 |
# merge
|
|
|
|
| 80 |
|
| 81 |
|
| 82 |
## 💻 Usage
|
| 83 |
+
|
| 84 |
```python
|
| 85 |
!pip install -qU transformers accelerate
|
| 86 |
|
|
|
|
| 99 |
torch_dtype=torch.float16,
|
| 100 |
device_map="auto",
|
| 101 |
)
|
| 102 |
+
|
| 103 |
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
| 104 |
print(outputs[0]["generated_text"])
|
| 105 |
```
|