messages listlengths 31 123 | instance_id stringlengths 9 30 |
|---|---|
[
{
"role": "system",
"content": "You are a helpful assistant that can interact with a computer to solve tasks.\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"fun... | Red-DiscordBot_10191 |
[
{
"role": "system",
"content": "You are a helpful assistant that can interact with a computer to solve tasks.\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"fun... | modin_10213 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | mido_10087 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | stackprinter_10466 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | channels_10129 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | daphne_10257 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | addict_10065 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | markupsafe_10105 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | pygments_10257 |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | astroid_10174 |
End of preview. Expand in Data Studio
sera-subset-mixed-316
Random subset of 316 rows drawn from ethanlshen/sera-subset, mixed across the two
upstream stages (stage1 unresolved + stage2 resolved) and shuffled deterministically.
Source
Upstream: ethanlshen/sera-subset.
Two upstream JSONLs are concatenated:
22972_0.88_stage1_scaling_final_glm46_e2e_1ipf_swesmith_unresolved_ipf_1_atk_rft-think_SYSTEM_SIMPLE.jsonl(22 972 rows)25224_r0.88_stage2_scaling_final_glm46_e2e_1ipf_resolved_soft_t0_ipf_1_atk_rft-think_SYSTEM_SIMPLE.jsonl(25 244 rows)
Reproducibility
import json, random
all_rows = []
for f in [22972_...stage1...jsonl, 25224_...stage2...jsonl]:
all_rows.extend(open(f).read().splitlines())
random.seed(42)
random.shuffle(all_rows)
with open(sera_subset_mixed_.jsonl, w) as out:
for line in all_rows[:316]: out.write(line + \n)
Schema
Each row is JSON with messages (list of {role, content, train}) and instance_id. The
training mask is train: True only on assistant turns. Hermes <tool_call>/<tool_response>
tokens are pre-rendered into content.
Used by
laion/sera-subset-mixed-316-axolotl__Qwen3-8B-v8(SFT on Qwen3-8B base)
- Downloads last month
- 46