149 lines
4.6 KiB
YAML
149 lines
4.6 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: 0
|
|
likes: 0
|
|
private: false
|
|
gated: false
|
|
created: '2026-07-30T10:46:30.000Z'
|
|
last_modified: '2026-07-31T04:45:44.000Z'
|
|
model_age_days: 0.7975
|
|
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: 17
|
|
total_repo_bytes: 3098921317
|
|
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: 12137
|
|
weight_note: Single BF16 shard model.safetensors (2.875 GiB), clean monolith.
|
|
benchmarks:
|
|
model_index_count: 1
|
|
metrics_count: 3
|
|
all_verified: false
|
|
pending_metrics: 0
|
|
entries:
|
|
- dataset: Nanthasit/sakthai-bench-v2
|
|
task: text-generation
|
|
metrics:
|
|
- name: Selection Accuracy
|
|
value: 34.9
|
|
- name: Arguments Accuracy
|
|
value: 44.2
|
|
- name: Strict Accuracy
|
|
value: 34.2
|
|
source: .eval_results/sakthai-bench-v2.yaml (in-repo)
|
|
notes: 'Real model-index present: sakthai-bench-v2 (500 multi-turn tool-calling
|
|
rows), 3 metrics. Repo .eval_results/sakthai-bench-v2.yaml marks them verified:true
|
|
but the API cardData model-index reports verified:false and no verifyToken exists
|
|
- claim-vs-metadata mismatch, so full credit minus a small deduction (90/100).
|
|
Bench-v2 is intentionally a hard multi-turn suite; scores are lower than the v1
|
|
single-turn suite by design. No inference re-run possible in cron env (hosted
|
|
router 400, local 1.5B OOMs in constrained env).'
|
|
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
|
|
- rslora
|
|
- conversational
|
|
- assistant
|
|
- safetensors
|
|
- benchmark
|
|
- eval-results
|
|
- text-generation
|
|
datasets_count: 3
|
|
datasets:
|
|
- Nanthasit/sakthai-combined-v7
|
|
- Nanthasit/sakthai-combined-v10
|
|
- Nanthasit/sakthai-irrelevance-supplement
|
|
model_index_present: true
|
|
readme_size_bytes: 12137
|
|
deductions:
|
|
- README and bench YAML claim verified:true while API cardData model-index says
|
|
verified:false (no verifyToken) - 5 pts
|
|
- No GGUF variant published yet despite README recommending it for local llama.cpp
|
|
use - 2 pts
|
|
score: 93
|
|
health_score:
|
|
overall: 55.4
|
|
components:
|
|
popularity: 0.0
|
|
momentum: 0.0
|
|
benchmarks: 90
|
|
card_quality: 93
|
|
repo_hygiene: 95
|
|
weights:
|
|
popularity: 0.2
|
|
momentum: 0.2
|
|
benchmarks: 0.25
|
|
card_quality: 0.2
|
|
repo_hygiene: 0.15
|
|
formula_note: 0.20*popularity + 0.20*momentum + 0.25*benchmarks + 0.20*card_quality
|
|
+ 0.15*repo_hygiene. Day-1 model with 0 downloads -> popularity/momentum 0. Benchmarks
|
|
carry the score via the real bench-v2 model-index entry.
|
|
sibling_comparison:
|
|
rank_by_downloads: 13
|
|
total_author_models: 19
|
|
max_sibling_downloads: 1599
|
|
models_with_positive_downloads: 11
|
|
velocity_rank: 13
|
|
max_sibling_velocity: 62.54
|
|
our_velocity: 0.0
|
|
eval_type: metadata_cron
|
|
eval_note: 'sakthai-context-1.5b-merged-v2 is the v2 flagship of the SakThai tool-calling
|
|
family: Qwen2.5-1.5B-Instruct QLoRA + rsLoRA merge, 1.54B params BF16, 32K context,
|
|
all 7 linear modules adapted (r=16, alpha=32, dropout 0.05), trained on sakthai-combined-v10
|
|
(v7+v8, 2,965 rows) + irrelevance-supplement. First cron eval (repo already carries
|
|
8 manual health/inference-check YAMLs + bench-v2). Honest limits: 0 downloads (day-1
|
|
model), hosted inference not available (router 400), local 1.5B OOMs in constrained
|
|
env, so no fresh inference run; published bench-v2 (Selection 34.9 / Arguments 44.2
|
|
/ Strict 34.2) taken from the repo''s own .eval_results YAML. Recommendation: publish
|
|
a GGUF (Q4_K_M) for llama.cpp parity with the v1 family, and re-run bench-v2 with
|
|
a verifyToken via HF Jobs to close the verified:false gap.'
|
|
eval_metadata:
|
|
model: Nanthasit/sakthai-context-1.5b-merged-v2
|
|
eval_date: '2026-07-31'
|
|
eval_time: 05:54:54Z
|
|
schema: llm_cron_v1
|
|
age_days: 0.7975
|
|
days_since_last_update: 0.048
|
|
download_velocity: 0.0
|
|
cron_run: 17
|