Instructions to use AtomicChat/Ling-3.0-flash-VL-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use AtomicChat/Ling-3.0-flash-VL-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
Use Docker
docker model run hf.co/AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use AtomicChat/Ling-3.0-flash-VL-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AtomicChat/Ling-3.0-flash-VL-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AtomicChat/Ling-3.0-flash-VL-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
- Ollama
How to use AtomicChat/Ling-3.0-flash-VL-GGUF with Ollama:
ollama run hf.co/AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use AtomicChat/Ling-3.0-flash-VL-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use AtomicChat/Ling-3.0-flash-VL-GGUF with Docker Model Runner:
docker model run hf.co/AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
- Lemonade
How to use AtomicChat/Ling-3.0-flash-VL-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Ling-3.0-flash-VL-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use AtomicChat/Ling-3.0-flash-VL-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use AtomicChat/Ling-3.0-flash-VL-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "AtomicChat/Ling-3.0-flash-VL-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Save private measured results and autonomous run checkpoint
Browse files- run/autonomy/events.jsonl +1 -0
- run/autonomy/state.json +4 -4
- run/autonomy/status.json +4 -3
- run/checkpoint-manifest.json +16 -11
- run/comparison/control-status.json +9 -4
- run/comparison/worker-a-status.json +1 -1
- run/quants/NVFP4_STOCK/manifest.json +111 -0
run/autonomy/events.jsonl
CHANGED
|
@@ -2,3 +2,4 @@
|
|
| 2 |
{"time": 1788818061.182383, "event": "stalled-job-terminated-for-recovery", "job": "controls", "pids": [2924925], "seconds_without_progress": 11436.840266942978}
|
| 3 |
{"time": 1788818091.2317636, "event": "job-started", "job": "controls", "pid": 2924989}
|
| 4 |
{"time": 1788818134.6924286, "event": "private-backup-verified", "revision": "0e67b218582cec430c9d154c1306c882e686a41f", "files": 92}
|
|
|
|
|
|
| 2 |
{"time": 1788818061.182383, "event": "stalled-job-terminated-for-recovery", "job": "controls", "pids": [2924925], "seconds_without_progress": 11436.840266942978}
|
| 3 |
{"time": 1788818091.2317636, "event": "job-started", "job": "controls", "pid": 2924989}
|
| 4 |
{"time": 1788818134.6924286, "event": "private-backup-verified", "revision": "0e67b218582cec430c9d154c1306c882e686a41f", "files": 92}
|
| 5 |
+
{"time": 1788818754.3894186, "event": "private-backup-verified", "revision": "931bcba9d88d4840b510f16209c16f785638ced1", "files": 93}
|
run/autonomy/state.json
CHANGED
|
@@ -9,12 +9,12 @@
|
|
| 9 |
},
|
| 10 |
"stop_requests": {},
|
| 11 |
"backed_up_workers": [],
|
| 12 |
-
"credit":
|
| 13 |
"hourly": 2.116296296296296,
|
| 14 |
"storage_after_stop_usd_per_day": 9.51111111111111,
|
| 15 |
"last_verified_backup": {
|
| 16 |
-
"time":
|
| 17 |
-
"revision": "
|
| 18 |
-
"files":
|
| 19 |
}
|
| 20 |
}
|
|
|
|
| 9 |
},
|
| 10 |
"stop_requests": {},
|
| 11 |
"backed_up_workers": [],
|
| 12 |
+
"credit": 78.59068545241553,
|
| 13 |
"hourly": 2.116296296296296,
|
| 14 |
"storage_after_stop_usd_per_day": 9.51111111111111,
|
| 15 |
"last_verified_backup": {
|
| 16 |
+
"time": 1788818754.3887765,
|
| 17 |
+
"revision": "931bcba9d88d4840b510f16209c16f785638ced1",
|
| 18 |
+
"files": 93
|
| 19 |
}
|
| 20 |
}
|
run/autonomy/status.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"stage": "running",
|
| 3 |
-
"time":
|
| 4 |
"source_revision": "869591498e8dbb41d4d96e3e2a5b428a2f70eb1e",
|
| 5 |
"repo_id": "AtomicChat/Ling-3.0-flash-VL-GGUF",
|
| 6 |
"private": true,
|
|
@@ -12,7 +12,8 @@
|
|
| 12 |
"Q4_K_M_STOCK",
|
| 13 |
"Q5_K_M_STOCK",
|
| 14 |
"Q6_K_STOCK",
|
| 15 |
-
"Q4_K_FLAT"
|
|
|
|
| 16 |
],
|
| 17 |
"quality_complete": [],
|
| 18 |
"quality_expected": [
|
|
@@ -47,7 +48,7 @@
|
|
| 47 |
"stage": "waiting-for-original-full-quality",
|
| 48 |
"time": 1788806332.9215345
|
| 49 |
},
|
| 50 |
-
"credit":
|
| 51 |
"hourly": 2.116296296296296,
|
| 52 |
"stop_requests": {},
|
| 53 |
"storage_after_stop_usd_per_day": 9.51111111111111,
|
|
|
|
| 1 |
{
|
| 2 |
"stage": "running",
|
| 3 |
+
"time": 1788819365.8423069,
|
| 4 |
"source_revision": "869591498e8dbb41d4d96e3e2a5b428a2f70eb1e",
|
| 5 |
"repo_id": "AtomicChat/Ling-3.0-flash-VL-GGUF",
|
| 6 |
"private": true,
|
|
|
|
| 12 |
"Q4_K_M_STOCK",
|
| 13 |
"Q5_K_M_STOCK",
|
| 14 |
"Q6_K_STOCK",
|
| 15 |
+
"Q4_K_FLAT",
|
| 16 |
+
"NVFP4_STOCK"
|
| 17 |
],
|
| 18 |
"quality_complete": [],
|
| 19 |
"quality_expected": [
|
|
|
|
| 48 |
"stage": "waiting-for-original-full-quality",
|
| 49 |
"time": 1788806332.9215345
|
| 50 |
},
|
| 51 |
+
"credit": 78.59068545241553,
|
| 52 |
"hourly": 2.116296296296296,
|
| 53 |
"stop_requests": {},
|
| 54 |
"storage_after_stop_usd_per_day": 9.51111111111111,
|
run/checkpoint-manifest.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"time":
|
| 3 |
"source_revision": "869591498e8dbb41d4d96e3e2a5b428a2f70eb1e",
|
| 4 |
"files": [
|
| 5 |
{
|
|
@@ -24,8 +24,8 @@
|
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"path": "run/autonomy/events.jsonl",
|
| 27 |
-
"bytes":
|
| 28 |
-
"sha256": "
|
| 29 |
},
|
| 30 |
{
|
| 31 |
"path": "run/autonomy/plan.json",
|
|
@@ -39,13 +39,13 @@
|
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"path": "run/autonomy/state.json",
|
| 42 |
-
"bytes":
|
| 43 |
-
"sha256": "
|
| 44 |
},
|
| 45 |
{
|
| 46 |
"path": "run/autonomy/status.json",
|
| 47 |
-
"bytes":
|
| 48 |
-
"sha256": "
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"path": "run/autonomy/supervisor.py",
|
|
@@ -69,8 +69,8 @@
|
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"path": "run/comparison/control-status.json",
|
| 72 |
-
"bytes":
|
| 73 |
-
"sha256": "
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"path": "run/comparison/finish-status.json",
|
|
@@ -84,8 +84,8 @@
|
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"path": "run/comparison/worker-a-status.json",
|
| 87 |
-
"bytes":
|
| 88 |
-
"sha256": "
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"path": "run/comparison/worker-b-status.json",
|
|
@@ -202,6 +202,11 @@
|
|
| 202 |
"bytes": 171363,
|
| 203 |
"sha256": "dd12c27edfb789a1123c4015b26db63bed892da25ed4d2b368dfdc844fad04db"
|
| 204 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 205 |
{
|
| 206 |
"path": "run/quants/NVFP4_STOCK/protected-f32-verification.json",
|
| 207 |
"bytes": 37697,
|
|
|
|
| 1 |
{
|
| 2 |
+
"time": 1788819365.8966794,
|
| 3 |
"source_revision": "869591498e8dbb41d4d96e3e2a5b428a2f70eb1e",
|
| 4 |
"files": [
|
| 5 |
{
|
|
|
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"path": "run/autonomy/events.jsonl",
|
| 27 |
+
"bytes": 652,
|
| 28 |
+
"sha256": "b6b4e9b792301f041bb782661ddddbbe10a8bb9f0f18cf1df12b5d02db079918"
|
| 29 |
},
|
| 30 |
{
|
| 31 |
"path": "run/autonomy/plan.json",
|
|
|
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"path": "run/autonomy/state.json",
|
| 42 |
+
"bytes": 460,
|
| 43 |
+
"sha256": "bdd5a7d8850d8d0480383a6190155ee761e851c4f9d5df28bbb2529b09f07782"
|
| 44 |
},
|
| 45 |
{
|
| 46 |
"path": "run/autonomy/status.json",
|
| 47 |
+
"bytes": 1277,
|
| 48 |
+
"sha256": "2b7d6c95a0e307975174afc89b2d5cee5707f82cd0961b001839dd35791ecda6"
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"path": "run/autonomy/supervisor.py",
|
|
|
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"path": "run/comparison/control-status.json",
|
| 72 |
+
"bytes": 169,
|
| 73 |
+
"sha256": "405c30391213732120cd8aa0124cc3434ccf65204da82c4cd0b89db7db0e6abf"
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"path": "run/comparison/finish-status.json",
|
|
|
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"path": "run/comparison/worker-a-status.json",
|
| 87 |
+
"bytes": 221,
|
| 88 |
+
"sha256": "3e2f74e076de448a7593546be4eb07a48f3aa841f0ed9f42711fadb5ef0e6d0c"
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"path": "run/comparison/worker-b-status.json",
|
|
|
|
| 202 |
"bytes": 171363,
|
| 203 |
"sha256": "dd12c27edfb789a1123c4015b26db63bed892da25ed4d2b368dfdc844fad04db"
|
| 204 |
},
|
| 205 |
+
{
|
| 206 |
+
"path": "run/quants/NVFP4_STOCK/manifest.json",
|
| 207 |
+
"bytes": 4753,
|
| 208 |
+
"sha256": "07624d3837e3de4d0a0a8221ace3353e46f9e69f5433bb1b1fe6c6f50c43ea88"
|
| 209 |
+
},
|
| 210 |
{
|
| 211 |
"path": "run/quants/NVFP4_STOCK/protected-f32-verification.json",
|
| 212 |
"bytes": 37697,
|
run/comparison/control-status.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"stage": "
|
| 3 |
-
"
|
| 4 |
-
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"stage": "complete",
|
| 3 |
+
"controls": [
|
| 4 |
+
"Q4_K_M_STOCK",
|
| 5 |
+
"Q5_K_M_STOCK",
|
| 6 |
+
"Q6_K_STOCK",
|
| 7 |
+
"Q4_K_FLAT",
|
| 8 |
+
"NVFP4_STOCK"
|
| 9 |
+
],
|
| 10 |
+
"time": 1788818770.1660993
|
| 11 |
}
|
run/comparison/worker-a-status.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"stage": "quality-running",
|
| 3 |
-
"time":
|
| 4 |
"worker": "a",
|
| 5 |
"active": [
|
| 6 |
"Q8_0",
|
|
|
|
| 1 |
{
|
| 2 |
"stage": "quality-running",
|
| 3 |
+
"time": 1788819338.22562,
|
| 4 |
"worker": "a",
|
| 5 |
"active": [
|
| 6 |
"Q8_0",
|
run/quants/NVFP4_STOCK/manifest.json
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"source_revision": "869591498e8dbb41d4d96e3e2a5b428a2f70eb1e",
|
| 3 |
+
"source_files": [
|
| 4 |
+
"/workspace/ling-vl/bf16-staging/Ling-3.0-flash-VL-BF16-00001-of-00006.gguf",
|
| 5 |
+
"/workspace/ling-vl/bf16-staging/Ling-3.0-flash-VL-BF16-00002-of-00006.gguf",
|
| 6 |
+
"/workspace/ling-vl/bf16-staging/Ling-3.0-flash-VL-BF16-00003-of-00006.gguf",
|
| 7 |
+
"/workspace/ling-vl/bf16-staging/Ling-3.0-flash-VL-BF16-00004-of-00006.gguf",
|
| 8 |
+
"/workspace/ling-vl/bf16-staging/Ling-3.0-flash-VL-BF16-00005-of-00006.gguf",
|
| 9 |
+
"/workspace/ling-vl/bf16-staging/Ling-3.0-flash-VL-BF16-00006-of-00006.gguf"
|
| 10 |
+
],
|
| 11 |
+
"rung": "NVFP4_STOCK",
|
| 12 |
+
"series": "nvfp4",
|
| 13 |
+
"uses_imatrix": false,
|
| 14 |
+
"command": [
|
| 15 |
+
"/workspace/ling-vl/runtime/build/bin/llama-quantize",
|
| 16 |
+
"--tensor-type-file",
|
| 17 |
+
"/workspace/ling-vl/recipes/NVFP4_STOCK.txt",
|
| 18 |
+
"--output-tensor-type",
|
| 19 |
+
"f16",
|
| 20 |
+
"--token-embedding-type",
|
| 21 |
+
"q8_0",
|
| 22 |
+
"--keep-split",
|
| 23 |
+
"--override-kv",
|
| 24 |
+
"general.name=str:Ling-3.0-flash-VL / NVFP4_STOCK",
|
| 25 |
+
"--override-kv",
|
| 26 |
+
"general.base_model.count=int:1",
|
| 27 |
+
"--override-kv",
|
| 28 |
+
"general.base_model.0.name=str:Ling-3.0-flash-VL",
|
| 29 |
+
"--override-kv",
|
| 30 |
+
"general.base_model.0.repo_url=str:https://huggingface.co/inclusionAI/Ling-3.0-flash-VL",
|
| 31 |
+
"--override-kv",
|
| 32 |
+
"atomic.source_revision=str:869591498e8dbb41d4d96e3e2a5b428a2f70eb1e"
|
| 33 |
+
],
|
| 34 |
+
"quantize_seconds": 466.0478697609942,
|
| 35 |
+
"recipe_sha256": "c6447b8d1c7f43e9bf391652b83aaaeba5bb04690cb8778b50d0c60f0e592fcf",
|
| 36 |
+
"imatrix_sha256": null,
|
| 37 |
+
"runtime_base": "cd560939087c95b93a1f30a95603d6b079436952",
|
| 38 |
+
"runtime_patch_sha256": "e2a12a63df72410b0e7bc9cf09960f6348476cd53b11cb0ad541f2c63cc035c7",
|
| 39 |
+
"runtime_provenance": {
|
| 40 |
+
"base": "cd560939087c95b93a1f30a95603d6b079436952",
|
| 41 |
+
"tracked_patch_sha256": "e2a12a63df72410b0e7bc9cf09960f6348476cd53b11cb0ad541f2c63cc035c7",
|
| 42 |
+
"new_files_archive_sha256": "021a1b1baa9d2621f26c87c74d2e320e33dc6c9b634eab63f7b5c3ec5c7b9544",
|
| 43 |
+
"binaries": {
|
| 44 |
+
"llama-quantize": "cf158191770d6a1df1ecba2fee5612a80b60aff4a4bce5a76b79f70d655840df",
|
| 45 |
+
"llama-mtmd-cli": "ddd2ef0100b807fa9176ef77b2c196bb8012c24618172ff01793a5f02c2ca700",
|
| 46 |
+
"llama-perplexity": "e5f7c4d5d9aa20d6a26cdec16497ead95e9e41faa7ea99a32663a00b95d6b4c1"
|
| 47 |
+
},
|
| 48 |
+
"deployment_files_verified": [
|
| 49 |
+
"runtime.patch",
|
| 50 |
+
"runtime-new-files.tar.gz",
|
| 51 |
+
"source-files.json",
|
| 52 |
+
"download_pinned_source.py",
|
| 53 |
+
"prepare_baseline.py",
|
| 54 |
+
"quantize_rung.py",
|
| 55 |
+
"recipes/Q4_K_M.txt",
|
| 56 |
+
"recipes/Q5_K_M.txt",
|
| 57 |
+
"recipes/Q6_K.txt",
|
| 58 |
+
"recipes/Q8_0.txt",
|
| 59 |
+
"eval/corpus-manifest.json",
|
| 60 |
+
"RUNBOOK.md",
|
| 61 |
+
"evaluate_quality.py",
|
| 62 |
+
"hash_baseline.py",
|
| 63 |
+
"smoke_baseline.py",
|
| 64 |
+
"smoke_quant.py",
|
| 65 |
+
"vision-reference-tensor-hashes.json",
|
| 66 |
+
"smoke_queue.py",
|
| 67 |
+
"smoke_batch.py",
|
| 68 |
+
"smoke_remaining.py",
|
| 69 |
+
"runtime-before-message-batch-fix.patch",
|
| 70 |
+
"full_quality_queue.py"
|
| 71 |
+
],
|
| 72 |
+
"deployment_manifest_sha256": "809ccdb38811363b049468b1371d62411def0f662d279514e267c81321b3dbcf",
|
| 73 |
+
"deployment_verified_at": 1788805454.4741771,
|
| 74 |
+
"shared_libraries_manifest_sha256": "f3d86eeb4725554f579033e445fd3deda1100a09a4a6c2e6afccce967d73bfd4"
|
| 75 |
+
},
|
| 76 |
+
"baseline_manifest_sha256": "d687ab6f3603495d520c632403317fc7db281145d79651aac9be694a374caa3c",
|
| 77 |
+
"files": [
|
| 78 |
+
{
|
| 79 |
+
"path": "/workspace/ling-vl/quants/NVFP4_STOCK/Ling-3.0-flash-VL-NVFP4_STOCK-00001-of-00006.gguf",
|
| 80 |
+
"bytes": 13846162912,
|
| 81 |
+
"sha256": "c59fe4872d93adb3d7fcb96d8468b3ab66b54950d5abcf1428b471b37685489c"
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"path": "/workspace/ling-vl/quants/NVFP4_STOCK/Ling-3.0-flash-VL-NVFP4_STOCK-00002-of-00006.gguf",
|
| 85 |
+
"bytes": 13776942208,
|
| 86 |
+
"sha256": "c53d491d1034e8d8ddda790518f2b3d57acd01099b28811b4a87b5aca9fed390"
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"path": "/workspace/ling-vl/quants/NVFP4_STOCK/Ling-3.0-flash-VL-NVFP4_STOCK-00003-of-00006.gguf",
|
| 90 |
+
"bytes": 13383537632,
|
| 91 |
+
"sha256": "5d88da3cc611616ba22ac11654fc06997c711f7318e28a5186fa70d8bf7491d8"
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"path": "/workspace/ling-vl/quants/NVFP4_STOCK/Ling-3.0-flash-VL-NVFP4_STOCK-00004-of-00006.gguf",
|
| 95 |
+
"bytes": 13743759520,
|
| 96 |
+
"sha256": "a1a5f524311bb7937aece23942c8c6edae69af0586c1664bc51d8499a2d1f7f7"
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"path": "/workspace/ling-vl/quants/NVFP4_STOCK/Ling-3.0-flash-VL-NVFP4_STOCK-00005-of-00006.gguf",
|
| 100 |
+
"bytes": 14188330080,
|
| 101 |
+
"sha256": "a83d2c7af3a66e1ca989590735a6233cdd350eb943c792282c46d512d314ea32"
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"path": "/workspace/ling-vl/quants/NVFP4_STOCK/Ling-3.0-flash-VL-NVFP4_STOCK-00006-of-00006.gguf",
|
| 105 |
+
"bytes": 3397386816,
|
| 106 |
+
"sha256": "f005e3961352218695d2c2e2577697fc9fecc98c2b1320f80305b64d813c4709"
|
| 107 |
+
}
|
| 108 |
+
],
|
| 109 |
+
"tensor_count": 917,
|
| 110 |
+
"status": "integrity-verified; inference and quality checks pending"
|
| 111 |
+
}
|