Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Adding Evaluation Results (#1)

Browse Source 
- Adding Evaluation Results (1b67be324314b0c5ca026fc130682db4d42e713e)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
This commit is contained in:
Eugenio Schiavoni
2024-09-19 13:18:09 +00:00
committed by system
parent 1fe849c1e7
commit c35899dadc
1 changed files with 110 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

112
README.md
View File

@@ -1,4 +1,5 @@
--- ---
license: other
tags: tags:
- merge - merge
- mergekit - mergekit
@@ -10,7 +11,101 @@ base_model:
- mlabonne/ChimeraLlama-3-8B-v2 - mlabonne/ChimeraLlama-3-8B-v2
- nbeerbower/llama-3-stella-8B - nbeerbower/llama-3-stella-8B
- uygarkurt/llama-3-merged-linear - uygarkurt/llama-3-merged-linear
license: other model-index:
- name: NeuralLLaMa-3-8b-DT-v0.1
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 43.71
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 28.01
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 7.25
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 7.05
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 9.69
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 31.02
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
name: Open LLM Leaderboard
--- ---
# NeuralLLaMa-3-8b-DT-v0.1 # NeuralLLaMa-3-8b-DT-v0.1
@@ -89,4 +184,17 @@ stop_token = "<|eot_id|>"
stop = tokenizer.encode(stop_token)[0] stop = tokenizer.encode(stop_token)[0]
_ = model.generate(**inputs, streamer=streamer, max_new_tokens=1024, do_sample=True, temperature=0.7, repetition_penalty=1.2, top_p=0.9, eos_token_id=stop) _ = model.generate(**inputs, streamer=streamer, max_new_tokens=1024, do_sample=True, temperature=0.7, repetition_penalty=1.2, top_p=0.9, eos_token_id=stop)
``` ```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Kukedlc__NeuralLLaMa-3-8b-DT-v0.1)
| Metric |Value|
|-------------------|----:|
|Avg. |21.12|
|IFEval (0-Shot) |43.71|
|BBH (3-Shot) |28.01|
|MATH Lvl 5 (4-Shot)| 7.25|
|GPQA (0-shot) | 7.05|
|MuSR (0-shot) | 9.69|
|MMLU-PRO (5-shot) |31.02|