Commit
•
303f01c
1
Parent(s):
85649a3
Adding missing intel orca dataset in reference
Browse files
README.md
CHANGED
|
@@ -12,6 +12,7 @@ tags:
|
|
| 12 |
base_model: MaziyarPanahi/calme-2.1-rys-78b
|
| 13 |
datasets:
|
| 14 |
- MaziyarPanahi/truthy-dpo-v0.1-axolotl
|
|
|
|
| 15 |
model_name: calme-2.4-rys-78b
|
| 16 |
pipeline_tag: text-generation
|
| 17 |
inference: false
|
|
@@ -33,7 +34,8 @@ model-index:
|
|
| 33 |
value: 80.11
|
| 34 |
name: strict accuracy
|
| 35 |
source:
|
| 36 |
-
url:
|
|
|
|
| 37 |
name: Open LLM Leaderboard
|
| 38 |
- task:
|
| 39 |
type: text-generation
|
|
@@ -48,7 +50,8 @@ model-index:
|
|
| 48 |
value: 62.16
|
| 49 |
name: normalized accuracy
|
| 50 |
source:
|
| 51 |
-
url:
|
|
|
|
| 52 |
name: Open LLM Leaderboard
|
| 53 |
- task:
|
| 54 |
type: text-generation
|
|
@@ -63,7 +66,8 @@ model-index:
|
|
| 63 |
value: 37.69
|
| 64 |
name: exact match
|
| 65 |
source:
|
| 66 |
-
url:
|
|
|
|
| 67 |
name: Open LLM Leaderboard
|
| 68 |
- task:
|
| 69 |
type: text-generation
|
|
@@ -78,7 +82,8 @@ model-index:
|
|
| 78 |
value: 20.36
|
| 79 |
name: acc_norm
|
| 80 |
source:
|
| 81 |
-
url:
|
|
|
|
| 82 |
name: Open LLM Leaderboard
|
| 83 |
- task:
|
| 84 |
type: text-generation
|
|
@@ -93,7 +98,8 @@ model-index:
|
|
| 93 |
value: 34.57
|
| 94 |
name: acc_norm
|
| 95 |
source:
|
| 96 |
-
url:
|
|
|
|
| 97 |
name: Open LLM Leaderboard
|
| 98 |
- task:
|
| 99 |
type: text-generation
|
|
@@ -110,7 +116,8 @@ model-index:
|
|
| 110 |
value: 66.69
|
| 111 |
name: accuracy
|
| 112 |
source:
|
| 113 |
-
url:
|
|
|
|
| 114 |
name: Open LLM Leaderboard
|
| 115 |
---
|
| 116 |
|
|
@@ -190,5 +197,4 @@ model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.4-rys-78b")
|
|
| 190 |
|
| 191 |
# Ethical Considerations
|
| 192 |
|
| 193 |
-
As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.
|
| 194 |
-
|
|
|
|
| 12 |
base_model: MaziyarPanahi/calme-2.1-rys-78b
|
| 13 |
datasets:
|
| 14 |
- MaziyarPanahi/truthy-dpo-v0.1-axolotl
|
| 15 |
+
- Intel/orca_dpo_pairs
|
| 16 |
model_name: calme-2.4-rys-78b
|
| 17 |
pipeline_tag: text-generation
|
| 18 |
inference: false
|
|
|
|
| 34 |
value: 80.11
|
| 35 |
name: strict accuracy
|
| 36 |
source:
|
| 37 |
+
url: >-
|
| 38 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.4-rys-78b
|
| 39 |
name: Open LLM Leaderboard
|
| 40 |
- task:
|
| 41 |
type: text-generation
|
|
|
|
| 50 |
value: 62.16
|
| 51 |
name: normalized accuracy
|
| 52 |
source:
|
| 53 |
+
url: >-
|
| 54 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.4-rys-78b
|
| 55 |
name: Open LLM Leaderboard
|
| 56 |
- task:
|
| 57 |
type: text-generation
|
|
|
|
| 66 |
value: 37.69
|
| 67 |
name: exact match
|
| 68 |
source:
|
| 69 |
+
url: >-
|
| 70 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.4-rys-78b
|
| 71 |
name: Open LLM Leaderboard
|
| 72 |
- task:
|
| 73 |
type: text-generation
|
|
|
|
| 82 |
value: 20.36
|
| 83 |
name: acc_norm
|
| 84 |
source:
|
| 85 |
+
url: >-
|
| 86 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.4-rys-78b
|
| 87 |
name: Open LLM Leaderboard
|
| 88 |
- task:
|
| 89 |
type: text-generation
|
|
|
|
| 98 |
value: 34.57
|
| 99 |
name: acc_norm
|
| 100 |
source:
|
| 101 |
+
url: >-
|
| 102 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.4-rys-78b
|
| 103 |
name: Open LLM Leaderboard
|
| 104 |
- task:
|
| 105 |
type: text-generation
|
|
|
|
| 116 |
value: 66.69
|
| 117 |
name: accuracy
|
| 118 |
source:
|
| 119 |
+
url: >-
|
| 120 |
+
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.4-rys-78b
|
| 121 |
name: Open LLM Leaderboard
|
| 122 |
---
|
| 123 |
|
|
|
|
| 197 |
|
| 198 |
# Ethical Considerations
|
| 199 |
|
| 200 |
+
As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.
|
|
|