Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,17 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
model-index:
|
| 3 |
- name: Tenete-8M
|
| 4 |
results:
|
| 5 |
-
|
| 6 |
-
# ====================== 0‑Shot ======================
|
| 7 |
-
# --- Multiple‑choice tasks ---
|
| 8 |
- task:
|
| 9 |
type: multiple-choice
|
| 10 |
name: ANLI R1 (0-Shot)
|
|
@@ -184,8 +191,6 @@ model-index:
|
|
| 184 |
- name: accuracy
|
| 185 |
type: acc
|
| 186 |
value: 0.4591
|
| 187 |
-
|
| 188 |
-
# --- Generation tasks ---
|
| 189 |
- task:
|
| 190 |
type: text-generation
|
| 191 |
name: GSM8K (0-Shot)
|
|
@@ -243,9 +248,6 @@ model-index:
|
|
| 243 |
- name: rougeL_max
|
| 244 |
type: rougeL_max
|
| 245 |
value: 20.7733
|
| 246 |
-
|
| 247 |
-
# ====================== 5‑Shot ======================
|
| 248 |
-
# --- Multiple‑choice tasks ---
|
| 249 |
- task:
|
| 250 |
type: multiple-choice
|
| 251 |
name: ANLI R1 (5-Shot)
|
|
@@ -414,8 +416,6 @@ model-index:
|
|
| 414 |
- name: accuracy
|
| 415 |
type: acc
|
| 416 |
value: 0.2705
|
| 417 |
-
# * 5‑shot setting not applicable; result identical to 0‑shot
|
| 418 |
-
|
| 419 |
- task:
|
| 420 |
type: multiple-choice
|
| 421 |
name: TruthfulQA MC2 (5-Shot)*
|
|
@@ -426,9 +426,6 @@ model-index:
|
|
| 426 |
- name: accuracy
|
| 427 |
type: acc
|
| 428 |
value: 0.4591
|
| 429 |
-
# * 5‑shot setting not applicable; result identical to 0‑shot
|
| 430 |
-
|
| 431 |
-
# --- Generation tasks ---
|
| 432 |
- task:
|
| 433 |
type: text-generation
|
| 434 |
name: GSM8K (5-Shot)
|
|
@@ -442,8 +439,6 @@ model-index:
|
|
| 442 |
- name: exact_match (strict-match)
|
| 443 |
type: exact_match
|
| 444 |
value: 0.0015
|
| 445 |
-
# 5‑shot yields identical numbers in this run
|
| 446 |
-
|
| 447 |
- task:
|
| 448 |
type: text-generation
|
| 449 |
name: TruthfulQA Gen (5-Shot)*
|
|
@@ -487,15 +482,4 @@ model-index:
|
|
| 487 |
- name: rougeL_max
|
| 488 |
type: rougeL_max
|
| 489 |
value: 20.7733
|
| 490 |
-
# * 5‑shot setting not applicable; result identical to 0‑shot
|
| 491 |
-
license: mit
|
| 492 |
-
language:
|
| 493 |
-
- en
|
| 494 |
-
tags:
|
| 495 |
-
- harley-ml
|
| 496 |
-
- tenete
|
| 497 |
-
- small
|
| 498 |
-
- sota
|
| 499 |
-
- slm
|
| 500 |
-
- text-generation
|
| 501 |
---
|
|
|
|
| 1 |
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- harley-ml
|
| 7 |
+
- tenete
|
| 8 |
+
- small
|
| 9 |
+
- sota
|
| 10 |
+
- slm
|
| 11 |
+
- text-generation
|
| 12 |
model-index:
|
| 13 |
- name: Tenete-8M
|
| 14 |
results:
|
|
|
|
|
|
|
|
|
|
| 15 |
- task:
|
| 16 |
type: multiple-choice
|
| 17 |
name: ANLI R1 (0-Shot)
|
|
|
|
| 191 |
- name: accuracy
|
| 192 |
type: acc
|
| 193 |
value: 0.4591
|
|
|
|
|
|
|
| 194 |
- task:
|
| 195 |
type: text-generation
|
| 196 |
name: GSM8K (0-Shot)
|
|
|
|
| 248 |
- name: rougeL_max
|
| 249 |
type: rougeL_max
|
| 250 |
value: 20.7733
|
|
|
|
|
|
|
|
|
|
| 251 |
- task:
|
| 252 |
type: multiple-choice
|
| 253 |
name: ANLI R1 (5-Shot)
|
|
|
|
| 416 |
- name: accuracy
|
| 417 |
type: acc
|
| 418 |
value: 0.2705
|
|
|
|
|
|
|
| 419 |
- task:
|
| 420 |
type: multiple-choice
|
| 421 |
name: TruthfulQA MC2 (5-Shot)*
|
|
|
|
| 426 |
- name: accuracy
|
| 427 |
type: acc
|
| 428 |
value: 0.4591
|
|
|
|
|
|
|
|
|
|
| 429 |
- task:
|
| 430 |
type: text-generation
|
| 431 |
name: GSM8K (5-Shot)
|
|
|
|
| 439 |
- name: exact_match (strict-match)
|
| 440 |
type: exact_match
|
| 441 |
value: 0.0015
|
|
|
|
|
|
|
| 442 |
- task:
|
| 443 |
type: text-generation
|
| 444 |
name: TruthfulQA Gen (5-Shot)*
|
|
|
|
| 482 |
- name: rougeL_max
|
| 483 |
type: rougeL_max
|
| 484 |
value: 20.7733
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 485 |
---
|