185 lines
5.7 KiB
YAML
185 lines
5.7 KiB
YAML
target_model:
|
|
id: Nanthasit/sakthai-context-1.5b-merged-v2
|
|
pipeline_tag: text-generation
|
|
library_name: transformers
|
|
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
|
downloads: 337
|
|
likes: 0
|
|
private: false
|
|
gated: false
|
|
created: '2026-07-30T10:46:30.000Z'
|
|
last_modified: '2026-07-31T07:58:17.000Z'
|
|
model_age_days: 0.9950
|
|
model_type: llm
|
|
has_weights: true
|
|
|
|
architecture:
|
|
model_type: qwen2
|
|
architectures:
|
|
- Qwen2ForCausalLM
|
|
hidden_size: 1536
|
|
num_hidden_layers: 28
|
|
num_attention_heads: 12
|
|
num_key_value_heads: 2
|
|
intermediate_size: 8960
|
|
vocab_size: 151936
|
|
max_position_embeddings: 32768
|
|
rope_theta: 1000000.0
|
|
tie_word_embeddings: true
|
|
total_parameters: 1543714304
|
|
dtype: bfloat16
|
|
quantization: none
|
|
transformers_version: 5.14.1
|
|
arch_source: config.json (fetched live 2026-07-31)
|
|
|
|
repo_summary:
|
|
siblings_count: 20
|
|
total_repo_bytes: 3098928651
|
|
total_gb: 2.886
|
|
has_weights: true
|
|
weight_file_count: 1
|
|
weight_bytes: 3087467144
|
|
config_present: true
|
|
tokenizer_present: true
|
|
chat_template_present: true
|
|
readme_present: true
|
|
readme_size_bytes: 12252
|
|
weight_note: Single BF16 shard model.safetensors (2.875 GiB), clean monolith.
|
|
eval_files_count: 12
|
|
eval_files:
|
|
- .eval_results/sakthai-bench-v2.yaml
|
|
- .eval_results/benchmark-20260731_061627.yaml
|
|
- .eval_results/cron-eval-sakthai-context-1.5b-merged-v2-2026-07-31-1.yaml
|
|
- .eval_results/health-check-2026-07-30-cron.yaml
|
|
- .eval_results/health-check-2026-07-30.yaml
|
|
- .eval_results/health-check-context-1.5b-v2-2026-07-30-cron.yaml
|
|
- .eval_results/health-check-sakthai-context-1.5b-merged-v2-2026-07-30-cron.yaml
|
|
- .eval_results/health-check-sakthai-context-1.5b-merged-v2-2026-07-30.yaml
|
|
- .eval_results/health-check.yaml
|
|
- .eval_results/inference-check-2026-07-30.yaml
|
|
- .eval_results/inference-check-20260731T001536Z.yaml
|
|
|
|
benchmarks:
|
|
model_index_count: 1
|
|
metrics_count: 3
|
|
all_verified: true
|
|
pending_metrics: 0
|
|
entries:
|
|
- dataset: Nanthasit/sakthai-bench-v2
|
|
task: text-generation
|
|
config: default
|
|
split: test
|
|
metrics:
|
|
- name: Selection Accuracy
|
|
value: 34.9
|
|
verified: true
|
|
- name: Arguments Accuracy
|
|
value: 44.2
|
|
verified: true
|
|
- name: Strict Accuracy
|
|
value: 34.2
|
|
verified: true
|
|
source: .eval_results/sakthai-bench-v2.yaml (in-repo, marks verified:true)
|
|
notes: >-
|
|
Real model-index present with 3 verified metrics from sakthai-bench-v2
|
|
(500 multi-turn tool-calling rows). The repo's own .eval_results/sakthai-bench-v2.yaml
|
|
marks all three metrics verified:true. Bench-v2 is an intentionally hard
|
|
multi-turn suite — scores are lower than v1 single-turn by design. No
|
|
inference re-run possible in cron env; existing metrics accepted as-is.
|
|
|
|
card_quality:
|
|
license: apache-2.0
|
|
base_model_documented: true
|
|
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
|
tags_count: 16
|
|
tags:
|
|
- qwen2.5
|
|
- sakthai
|
|
- house-of-sak
|
|
- tool-calling
|
|
- function-calling
|
|
- agent
|
|
- instruct
|
|
- finetuned
|
|
- merged
|
|
- text-generation
|
|
- rslora
|
|
- conversational
|
|
- assistant
|
|
- safetensors
|
|
- benchmark
|
|
- eval-results
|
|
datasets_count: 3
|
|
datasets:
|
|
- Nanthasit/sakthai-combined-v7
|
|
- Nanthasit/sakthai-combined-v10
|
|
- Nanthasit/sakthai-irrelevance-supplement
|
|
model_index_present: true
|
|
widget_example: "What's the weather in Bangkok?"
|
|
readme_size_bytes: 12252
|
|
deductions:
|
|
- README badges use img.shields.io endpoint style which may not render for all viewers — 2 pts
|
|
- No GGUF variant published despite README recommending local llama.cpp use — 2 pts
|
|
score: 96
|
|
|
|
health_score:
|
|
overall: 65.8
|
|
components:
|
|
popularity: 3.37
|
|
momentum: 33.9
|
|
benchmarks: 95
|
|
card_quality: 96
|
|
repo_hygiene: 97
|
|
weights:
|
|
popularity: 0.20
|
|
momentum: 0.20
|
|
benchmarks: 0.25
|
|
card_quality: 0.20
|
|
repo_hygiene: 0.15
|
|
formula_note: >-
|
|
0.20*popularity + 0.20*momentum + 0.25*benchmarks + 0.20*card_quality
|
|
+ 0.15*repo_hygiene. Popularity = min(100, downloads/100) = 3.37.
|
|
Momentum = min(100, download_velocity*10) = 33.9 (338.7 dl/day * 0.1).
|
|
Benchmarks 95 (verified:true entries in repo's own eval YAML).
|
|
repo_hygiene 97 (all files present, 12 eval files — small deduction for
|
|
no adapter_config.json or training artifacts since this is a merged model).
|
|
|
|
sibling_comparison:
|
|
rank_by_downloads: 8
|
|
total_author_models: 22
|
|
max_sibling_downloads: 1855
|
|
models_with_positive_downloads: 18
|
|
velocity_rank: 1
|
|
max_sibling_velocity: 338.69
|
|
our_velocity: 338.69
|
|
velocity_note: >-
|
|
#1 download velocity among all Nanthasit models (338.7 dl/day) —
|
|
this is the highest-velocity model in the family, likely driven by the
|
|
v2 improvements and social reach from earlier cron cycles.
|
|
Rank: 8/22 by absolute downloads — solid mid-upper position for a
|
|
model published only ~1 day ago.
|
|
|
|
eval_type: metadata_cron
|
|
eval_note: >-
|
|
SECOND cron eval for sakthai-context-1.5b-merged-v2. Since the first
|
|
eval (run 17, ~18h ago), downloads have gone from 0 to 337 — the
|
|
highest velocity (338.7 dl/day) of any Nanthasit model, surpassing
|
|
even the 7B merged (1,024 dl over 30+ days). The model carries 12
|
|
.eval_results/ files including bench-v2 metrics (all verified:true).
|
|
The repository is well-maintained with a full README, 3 cited
|
|
datasets (combined-v7, combined-v10, irrelevance-supplement), and
|
|
active commits within hours. Recommendation: publish a Q4_K_M GGUF
|
|
to extend reach to CPU/local llama.cpp users, and consider adding
|
|
the sakthai-bench-v2 verifyToken to close the API-vs-YAML
|
|
verification gap.
|
|
|
|
eval_metadata:
|
|
model: Nanthasit/sakthai-context-1.5b-merged-v2
|
|
eval_date: '2026-07-31'
|
|
eval_time: '12:00:00Z'
|
|
schema: llm_cron_v1
|
|
age_days: 0.9950
|
|
days_since_last_update: 0.0
|
|
download_velocity: 338.69
|
|
cron_run: 25
|