初始化项目，由ModelHub XC社区提供模型
Model: Nanthasit/sakthai-context-7b-merged Source: Original Platform
This commit is contained in:
ModelHub XC
119
eval/workbench-7b-2026-07-07.json
Normal file
119
eval/workbench-7b-2026-07-07.json
Normal file
@@ -0,0 +1,119 @@
|
||||
{
|
||||
"type": "workbench_hf_jobs",
|
||||
"model": "Nanthasit/sakthai-context-7b-merged",
|
||||
"load_time_seconds": 137.3,
|
||||
"device": "cuda:0",
|
||||
"gpu": "Tesla T4",
|
||||
"vram_used_gb": 5.56,
|
||||
"timestamp": "2026-07-07T14:44:33Z",
|
||||
"results": [
|
||||
{
|
||||
"name": "basic_greeting",
|
||||
"passed": true,
|
||||
"response_preview": "Hello!",
|
||||
"response_length": 6,
|
||||
"latency_seconds": 1.08,
|
||||
"prompt_tokens": 31,
|
||||
"completion_tokens": 3,
|
||||
"checks": [
|
||||
"non_empty"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "tool_call_intent",
|
||||
"passed": true,
|
||||
"response_preview": "Searching for the latest AI news...",
|
||||
"response_length": 35,
|
||||
"latency_seconds": 0.93,
|
||||
"prompt_tokens": 37,
|
||||
"completion_tokens": 8,
|
||||
"checks": [
|
||||
"non_empty",
|
||||
"substantial"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "name_recall",
|
||||
"passed": true,
|
||||
"response_preview": "Your name is Beer.",
|
||||
"response_length": 18,
|
||||
"latency_seconds": 0.78,
|
||||
"prompt_tokens": 45,
|
||||
"completion_tokens": 6,
|
||||
"checks": [
|
||||
"non_empty",
|
||||
"substantial",
|
||||
"name_recall"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "factual_qa",
|
||||
"passed": true,
|
||||
"response_preview": "Tokyo.",
|
||||
"response_length": 6,
|
||||
"latency_seconds": 0.63,
|
||||
"prompt_tokens": 28,
|
||||
"completion_tokens": 4,
|
||||
"checks": [
|
||||
"non_empty",
|
||||
"correct"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "json_output",
|
||||
"passed": true,
|
||||
"response_preview": "{\"frameworks\": [\"TensorFlow\", \"PyTorch\", \"Keras\"]}",
|
||||
"response_length": 50,
|
||||
"latency_seconds": 1.62,
|
||||
"prompt_tokens": 41,
|
||||
"completion_tokens": 18,
|
||||
"checks": [
|
||||
"non_empty",
|
||||
"substantial",
|
||||
"valid_json"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "instruction_following",
|
||||
"passed": true,
|
||||
"response_preview": "A transformer is an electrical device that transfers electrical energy between two or more circuits through inductively coupled conductors\u2014called windings\u2014without any physical connection between the c",
|
||||
"response_length": 208,
|
||||
"latency_seconds": 2.94,
|
||||
"prompt_tokens": 29,
|
||||
"completion_tokens": 36,
|
||||
"checks": [
|
||||
"non_empty",
|
||||
"substantial"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "multi_step_reasoning",
|
||||
"passed": true,
|
||||
"response_preview": "Let's break this down step by step:\n\n1. You start with 3 apples.\n2. You give away 1 apple: 3 - 1 = 2 apples remaining.\n3. You buy 5 more apples: 2 + 5 = 7 apples.\n\nSo, you end up with 7 apples.",
|
||||
"response_length": 193,
|
||||
"latency_seconds": 5.21,
|
||||
"prompt_tokens": 50,
|
||||
"completion_tokens": 68,
|
||||
"checks": [
|
||||
"non_empty",
|
||||
"substantial",
|
||||
"correct_answer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "context_window",
|
||||
"passed": true,
|
||||
"response_preview": "The paper \"Attention Is All You Need\" was published in 2017. It introduced the transformer architecture which has since become a fundamental building block for many state-of-the-art natural language p",
|
||||
"response_length": 246,
|
||||
"latency_seconds": 4.45,
|
||||
"prompt_tokens": 65,
|
||||
"completion_tokens": 54,
|
||||
"checks": [
|
||||
"non_empty",
|
||||
"substantial",
|
||||
"correct_answer"
|
||||
]
|
||||
}
|
||||
],
|
||||
"summary": "8/8 passed"
|
||||
}
|
||||
218
eval/workbench-7b-endpoint-test.py
Normal file
218
eval/workbench-7b-endpoint-test.py
Normal file
@@ -0,0 +1,218 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Workbench test: 7B merged model via Inference Endpoint."""
|
||||
import json, time, os, sys
|
||||
import requests
|
||||
|
||||
MODEL = "Nanthasit/sakthai-context-7b-merged"
|
||||
ENDPOINT_URL = None # Set dynamically after deployment
|
||||
|
||||
# Read endpoint URL from args or env
|
||||
if len(sys.argv) > 1:
|
||||
ENDPOINT_URL = sys.argv[1]
|
||||
elif "ENDPOINT_URL" in os.environ:
|
||||
ENDPOINT_URL = os.environ["ENDPOINT_URL"]
|
||||
else:
|
||||
print("Usage: python3 sakthai-7b-workbench-test.py <endpoint_url>")
|
||||
print("Or set ENDPOINT_URL env var")
|
||||
sys.exit(1)
|
||||
|
||||
TOKEN_PATH = "/opt/data/profiles/sakthai/home/.cache/huggingface/token"
|
||||
with open(TOKEN_PATH) as f:
|
||||
HF_TOKEN = f.read().strip()
|
||||
|
||||
HEADERS = {
|
||||
"Authorization": f"Bearer {HF_TOKEN}",
|
||||
"Content-Type": "application/json"
|
||||
}
|
||||
|
||||
tests = [
|
||||
{
|
||||
"name": "basic_greeting",
|
||||
"desc": "Say hello in one sentence",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai, a helpful assistant. Be concise."},
|
||||
{"role": "user", "content": "Say hello in one sentence."}
|
||||
],
|
||||
"checks": ["non_empty", "substantial"]
|
||||
},
|
||||
{
|
||||
"name": "tool_call_intent",
|
||||
"desc": "Tool-use intent",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai with tools: search(query), read_file(path), run_command(command)."},
|
||||
{"role": "user", "content": "Search for the latest AI news"}
|
||||
],
|
||||
"checks": ["non_empty", "substantial"]
|
||||
},
|
||||
{
|
||||
"name": "name_recall",
|
||||
"desc": "Remember name across 3 turns",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai."},
|
||||
{"role": "user", "content": "My name is Beer."},
|
||||
{"role": "assistant", "content": "Nice to meet you, Beer!"},
|
||||
{"role": "user", "content": "What's my name?"}
|
||||
],
|
||||
"checks": ["non_empty", "name_recall"]
|
||||
},
|
||||
{
|
||||
"name": "factual_qa",
|
||||
"desc": "Simple factual question",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai. Be concise."},
|
||||
{"role": "user", "content": "What is the capital of Japan?"}
|
||||
],
|
||||
"checks": ["non_empty", "correct"]
|
||||
},
|
||||
{
|
||||
"name": "json_output",
|
||||
"desc": "Structured JSON",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai. Only respond with valid JSON."},
|
||||
{"role": "user", "content": 'List 3 ML frameworks: {"frameworks": ["a","b","c"]}'}
|
||||
],
|
||||
"checks": ["non_empty", "valid_json"]
|
||||
},
|
||||
{
|
||||
"name": "instruction_following",
|
||||
"desc": "Follow formatting instruction",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai. Exactly one sentence."},
|
||||
{"role": "user", "content": "Explain what a transformer is."}
|
||||
],
|
||||
"checks": ["non_empty", "substantial"]
|
||||
},
|
||||
{
|
||||
"name": "multi_step_reasoning",
|
||||
"desc": "Multi-step reasoning",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai, a helpful assistant."},
|
||||
{"role": "user", "content": "If you have 3 apples and give away 1, then buy 5 more, how many do you have? Show your work."}
|
||||
],
|
||||
"checks": ["non_empty", "substantial"]
|
||||
},
|
||||
{
|
||||
"name": "context_window",
|
||||
"desc": "Longer context understanding",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai. Be concise."},
|
||||
{"role": "user", "content": "The transformer architecture introduced in 'Attention Is All You Need' revolutionized NLP by replacing recurrent layers with multi-head self-attention. It uses positional encodings, layer normalization, and feed-forward networks in an encoder-decoder structure. BERT, GPT, and T5 all build on this foundation. What year was the original transformer paper published?"}
|
||||
],
|
||||
"checks": ["non_empty", "correct_answer"]
|
||||
}
|
||||
]
|
||||
|
||||
print(f"🧪 WORKBENCH TEST — SakThai Context 7B")
|
||||
print(f" Endpoint: {ENDPOINT_URL}")
|
||||
print(f" Model: {MODEL}")
|
||||
print(f" Time: {time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())}")
|
||||
print()
|
||||
|
||||
results = []
|
||||
for i, test in enumerate(tests):
|
||||
print(f"{'─'*60}")
|
||||
print(f"TEST {i+1}: {test['name']} — {test['desc']}")
|
||||
print(f" Turns: {len(test['messages'])}", flush=True)
|
||||
|
||||
try:
|
||||
t0 = time.time()
|
||||
resp = requests.post(
|
||||
f"{ENDPOINT_URL}/v1/chat/completions",
|
||||
headers=HEADERS,
|
||||
json={
|
||||
"model": "tgi",
|
||||
"messages": test["messages"],
|
||||
"max_tokens": 256,
|
||||
"temperature": 0.1,
|
||||
},
|
||||
timeout=120
|
||||
)
|
||||
elapsed = time.time() - t0
|
||||
|
||||
if resp.status_code != 200:
|
||||
raise Exception(f"HTTP {resp.status_code}: {resp.text[:200]}")
|
||||
|
||||
data = resp.json()
|
||||
choice = data["choices"][0]
|
||||
content = choice["message"]["content"].strip()
|
||||
finish = choice.get("finish_reason", "")
|
||||
usage = data.get("usage", {})
|
||||
|
||||
# Run quality checks
|
||||
checks = []
|
||||
if len(content) > 0:
|
||||
checks.append("non_empty")
|
||||
if len(content) > 10:
|
||||
checks.append("substantial")
|
||||
|
||||
if "beer" in content.lower() and test["name"] == "name_recall":
|
||||
checks.append("name_recall")
|
||||
if "tokyo" in content.lower() and test["name"] == "factual_qa":
|
||||
checks.append("correct")
|
||||
if "2017" in content and test["name"] == "context_window":
|
||||
checks.append("correct_answer")
|
||||
if test["name"] == "json_output":
|
||||
try:
|
||||
json.loads(content)
|
||||
checks.append("valid_json")
|
||||
except:
|
||||
pass
|
||||
|
||||
result = {
|
||||
"name": test["name"],
|
||||
"passed": len(checks) > 0,
|
||||
"response_preview": content[:200],
|
||||
"response_length": len(content),
|
||||
"latency_seconds": round(elapsed, 2),
|
||||
"prompt_tokens": usage.get("prompt_tokens"),
|
||||
"completion_tokens": usage.get("completion_tokens"),
|
||||
"finish_reason": finish,
|
||||
"checks": checks
|
||||
}
|
||||
|
||||
print(f" {'✅' if result['passed'] else '❌'} Response: {content[:150]}")
|
||||
print(f" ⏱ {elapsed:.2f}s | ✅ {checks} | 🔚 {finish}")
|
||||
if result.get("prompt_tokens"):
|
||||
print(f" 📝 {result['prompt_tokens']}→{result['completion_tokens']}")
|
||||
|
||||
except Exception as e:
|
||||
result = {
|
||||
"name": test["name"],
|
||||
"passed": False,
|
||||
"error": str(e)[:300]
|
||||
}
|
||||
print(f" ❌ FAIL: {e}")
|
||||
|
||||
results.append(result)
|
||||
sys.stdout.flush()
|
||||
|
||||
# Summary
|
||||
print(f"\n{'='*60}")
|
||||
passed = sum(1 for r in results if r.get("passed"))
|
||||
total = len(results)
|
||||
print(f"📊 WORKBENCH SUMMARY — 7B ({MODEL})")
|
||||
print(f"\nResults: {passed}/{total} passed")
|
||||
print()
|
||||
|
||||
for r in results:
|
||||
status = "✅" if r.get("passed") else "❌"
|
||||
name = r["name"].ljust(22)
|
||||
lat = f"{r.get('latency_seconds', 0):.1f}s" if r.get("passed") else " - "
|
||||
detail = str(r.get("checks", r.get("error", "?")[:60]))
|
||||
print(f" {status} {name} ⏱ {lat} {detail}")
|
||||
|
||||
# Save record
|
||||
record = {
|
||||
"test_run": f"workbench-{time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())}",
|
||||
"model": MODEL,
|
||||
"endpoint_url": ENDPOINT_URL,
|
||||
"timestamp": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
|
||||
"results": results,
|
||||
"summary": f"{passed}/{total} passed"
|
||||
}
|
||||
|
||||
output_path = "/opt/data/sakthai-7b-workbench-test-record.json"
|
||||
with open(output_path, "w") as f:
|
||||
json.dump(record, f, indent=2)
|
||||
print(f"\n💾 Saved: {output_path}")
|
||||
print("🏁 Done.")
|
||||
204
eval/workbench-7b-hfjobs.py
Normal file
204
eval/workbench-7b-hfjobs.py
Normal file
@@ -0,0 +1,204 @@
|
||||
#!/usr/bin/env python3
|
||||
"""HF Jobs workbench test: SakThai Context 7B merged model, 4-bit, T4 GPU."""
|
||||
|
||||
import json, time, os, sys
|
||||
import torch
|
||||
|
||||
MODEL = "Nanthasit/sakthai-context-7b-merged"
|
||||
HF_TOKEN = os.environ.get("HF_TOKEN", "")
|
||||
os.environ["HF_TOKEN"] = HF_TOKEN
|
||||
os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "expandable_segments:True"
|
||||
|
||||
print("=" * 60)
|
||||
print(f"WORKBENCH TEST — SakThai Context 7B")
|
||||
print(f"Model: {MODEL}")
|
||||
print(f"GPU: {torch.cuda.get_device_name(0) if torch.cuda.is_available() else 'NONE'}")
|
||||
print(f"VRAM: {torch.cuda.get_device_properties(0).total_memory / 1e9:.1f}GB" if torch.cuda.is_available() else "N/A")
|
||||
print(f"Time: {time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())}")
|
||||
print("=" * 60)
|
||||
sys.stdout.flush()
|
||||
|
||||
# Load model with 4-bit quantization
|
||||
print("\n📥 Loading model in 4-bit...", flush=True)
|
||||
t0 = time.time()
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
|
||||
|
||||
bnb_config = BitsAndBytesConfig(
|
||||
load_in_4bit=True,
|
||||
bnb_4bit_compute_dtype=torch.bfloat16,
|
||||
bnb_4bit_use_double_quant=True,
|
||||
bnb_4bit_quant_type="nf4",
|
||||
)
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(MODEL, token=HF_TOKEN)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
MODEL,
|
||||
quantization_config=bnb_config,
|
||||
device_map="auto",
|
||||
torch_dtype=torch.bfloat16,
|
||||
token=HF_TOKEN,
|
||||
trust_remote_code=True,
|
||||
)
|
||||
load_time = time.time() - t0
|
||||
print(f"✅ Loaded in {load_time:.1f}s on {model.device}", flush=True)
|
||||
print(f" VRAM: {torch.cuda.memory_allocated() / 1e9:.2f}GB used", flush=True)
|
||||
|
||||
# Tests
|
||||
tests = [
|
||||
{"name": "basic_greeting", "desc": "Say hello",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai, a helpful assistant. Be concise."},
|
||||
{"role": "user", "content": "Say hello in one sentence."}
|
||||
]},
|
||||
{"name": "tool_call_intent", "desc": "Tool-use intent",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai with tools: search(query), read_file(path), run_command(command)."},
|
||||
{"role": "user", "content": "Search for the latest AI news"}
|
||||
]},
|
||||
{"name": "name_recall", "desc": "Remember name across 3 turns",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai."},
|
||||
{"role": "user", "content": "My name is Beer."},
|
||||
{"role": "assistant", "content": "Nice to meet you, Beer!"},
|
||||
{"role": "user", "content": "What's my name?"}
|
||||
]},
|
||||
{"name": "factual_qa", "desc": "Capital of Japan",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai. Be concise."},
|
||||
{"role": "user", "content": "What is the capital of Japan?"}
|
||||
]},
|
||||
{"name": "json_output", "desc": "Structured JSON",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai. Respond only with valid JSON."},
|
||||
{"role": "user", "content": 'List 3 ML frameworks: {"frameworks": ["a","b","c"]}'}
|
||||
]},
|
||||
{"name": "instruction_following", "desc": "One sentence only",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai. Exactly one sentence."},
|
||||
{"role": "user", "content": "Explain what a transformer is."}
|
||||
]},
|
||||
{"name": "multi_step_reasoning", "desc": "Math reasoning",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai, a helpful assistant."},
|
||||
{"role": "user", "content": "If you have 3 apples and give away 1, then buy 5 more, how many do you have? Show your work."}
|
||||
]},
|
||||
{"name": "context_window", "desc": "Recall from context",
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are SakThai."},
|
||||
{"role": "user", "content": "'Attention Is All You Need' introduced the transformer architecture with multi-head self-attention, positional encodings, and encoder-decoder structure. BERT, GPT, T5 build on it. What year was the paper published?"}
|
||||
]},
|
||||
]
|
||||
|
||||
results = []
|
||||
for i, test in enumerate(tests):
|
||||
print(f"\n{'─'*60}", flush=True)
|
||||
print(f"TEST {i+1}: {test['name']} — {test['desc']}", flush=True)
|
||||
|
||||
try:
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
test["messages"], tokenize=False, add_generation_prompt=True
|
||||
)
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||
|
||||
t1 = time.time()
|
||||
with torch.no_grad():
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=256,
|
||||
temperature=0.1,
|
||||
do_sample=True,
|
||||
pad_token_id=tokenizer.eos_token_id,
|
||||
)
|
||||
elapsed = time.time() - t1
|
||||
|
||||
input_len = inputs.input_ids.shape[1]
|
||||
response = tokenizer.decode(outputs[0][input_len:], skip_special_tokens=True).strip()
|
||||
prompt_tokens = input_len
|
||||
completion_tokens = outputs.shape[1] - input_len
|
||||
|
||||
# Quality checks
|
||||
checks = []
|
||||
if len(response) > 0: checks.append("non_empty")
|
||||
if len(response) > 10: checks.append("substantial")
|
||||
if test["name"] == "name_recall" and "beer" in response.lower():
|
||||
checks.append("name_recall")
|
||||
if test["name"] == "factual_qa" and "tokyo" in response.lower():
|
||||
checks.append("correct")
|
||||
if test["name"] == "context_window" and "2017" in response:
|
||||
checks.append("correct_answer")
|
||||
if test["name"] == "json_output":
|
||||
try:
|
||||
json.loads(response)
|
||||
checks.append("valid_json")
|
||||
except:
|
||||
pass
|
||||
if test["name"] == "multi_step_reasoning":
|
||||
if any(c in response for c in ["7", "seven"]) and ("apple" in response.lower()):
|
||||
checks.append("correct_answer")
|
||||
|
||||
passed = len(response) > 0 # at minimum non-empty
|
||||
result = {
|
||||
"name": test["name"], "passed": passed,
|
||||
"response_preview": response[:200],
|
||||
"response_length": len(response),
|
||||
"latency_seconds": round(elapsed, 2),
|
||||
"prompt_tokens": prompt_tokens,
|
||||
"completion_tokens": completion_tokens,
|
||||
"checks": checks,
|
||||
}
|
||||
status = "✅" if passed else "❌"
|
||||
print(f" {status} {response[:120]}", flush=True)
|
||||
print(f" ⏱ {elapsed:.2f}s | 📝 {prompt_tokens}→{completion_tokens} | ✅ {checks}", flush=True)
|
||||
|
||||
except Exception as e:
|
||||
result = {"name": test["name"], "passed": False, "error": str(e)[:300]}
|
||||
print(f" ❌ {e}", flush=True)
|
||||
|
||||
results.append(result)
|
||||
sys.stdout.flush()
|
||||
|
||||
# Summary
|
||||
print(f"\n{'='*60}", flush=True)
|
||||
passed = sum(1 for r in results if r.get("passed"))
|
||||
total = len(results)
|
||||
print(f"📊 7B WORKBENCH SUMMARY: {passed}/{total} passed", flush=True)
|
||||
for r in results:
|
||||
status = "✅" if r.get("passed") else "❌"
|
||||
lat = f"{r.get('latency_seconds',0):.1f}s" if r.get("passed") else " - "
|
||||
detail = str(r.get("checks", r.get("error","?")[:60]))
|
||||
print(f" {status} {r['name']:<22} ⏱ {lat} {detail}", flush=True)
|
||||
|
||||
# Save record
|
||||
record = {
|
||||
"type": "workbench_hf_jobs",
|
||||
"model": MODEL,
|
||||
"load_time_seconds": round(load_time, 1),
|
||||
"device": str(model.device),
|
||||
"gpu": torch.cuda.get_device_name(0) if torch.cuda.is_available() else "cpu",
|
||||
"vram_used_gb": round(torch.cuda.memory_allocated() / 1e9, 2) if torch.cuda.is_available() else 0,
|
||||
"timestamp": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
|
||||
"results": results,
|
||||
"summary": f"{passed}/{total} passed",
|
||||
}
|
||||
|
||||
record_path = "/tmp/sakthai-7b-workbench-record.json"
|
||||
with open(record_path, "w") as f:
|
||||
json.dump(record, f, indent=2)
|
||||
print(f"\n💾 Saved: {record_path}", flush=True)
|
||||
|
||||
# Upload record to HF repo
|
||||
try:
|
||||
from huggingface_hub import HfApi, login
|
||||
login(token=HF_TOKEN)
|
||||
api = HfApi()
|
||||
api.upload_file(
|
||||
path_or_fileobj=record_path,
|
||||
path_in_repo=f"eval/workbench-7b-{time.strftime('%Y-%m-%d')}.json",
|
||||
repo_id="Nanthasit/sakthai-context-7b-merged",
|
||||
repo_type="model",
|
||||
)
|
||||
print(f"📤 Uploaded to HF repo", flush=True)
|
||||
except Exception as e:
|
||||
print(f"⚠️ Upload failed: {e}", flush=True)
|
||||
|
||||
print("\n🏁 Done.", flush=True)
|
||||
Reference in New Issue
Block a user