Instructions to use JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M")
config = load_config("JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M"

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 JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M"

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 "JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

jangq commited on 10 days ago

Commit

2ae2466

verified ·

1 Parent(s): 6cffa1d

rebuild

Browse files

Files changed (30) hide show

.DS_Store +0 -0
README.md +24 -12
config.json +0 -0
jang_ladder_wide.png +2 -2
jangq-logo.png +0 -0
model-00001-of-00026.safetensors +2 -2
model-00002-of-00026.safetensors +2 -2
model-00003-of-00026.safetensors +2 -2
model-00004-of-00026.safetensors +2 -2
model-00005-of-00026.safetensors +2 -2
model-00006-of-00026.safetensors +2 -2
model-00007-of-00026.safetensors +2 -2
model-00008-of-00026.safetensors +2 -2
model-00009-of-00026.safetensors +2 -2
model-00010-of-00026.safetensors +2 -2
model-00011-of-00026.safetensors +2 -2
model-00012-of-00026.safetensors +2 -2
model-00013-of-00026.safetensors +2 -2
model-00014-of-00026.safetensors +2 -2
model-00015-of-00026.safetensors +2 -2
model-00016-of-00026.safetensors +2 -2
model-00017-of-00026.safetensors +2 -2
model-00018-of-00026.safetensors +2 -2
model-00019-of-00026.safetensors +2 -2
model-00020-of-00026.safetensors +2 -2
model-00021-of-00026.safetensors +2 -2
model-00022-of-00026.safetensors +2 -2
model-00023-of-00026.safetensors +2 -2
model.safetensors.index.json +14 -14
vmlx-logo.png +0 -0

.DS_Store ADDED Viewed

Binary file (8.2 kB). View file

README.md CHANGED Viewed

@@ -25,9 +25,15 @@ tags:
 - awq
 ---
 # JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M
-**The recommended quality/size balance — median KL 0.0039 vs bf16 at 96.6 GiB (~73 GiB resident with the SSD-served table).**
 A JANG bundle of [Qwen/Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)
 — the Qwen4-architecture preview: a 125B mixture-of-experts (512 experts,
@@ -36,8 +42,10 @@ Attention hybrid layers, gated-residual streams, and vision+video towers —
 quantized for Apple Silicon / MLX. Text, image and video weights are all
 present in this exact bundle. Native multi-token-prediction head preserved (4-bit).
-> Runtime support is landing — this repo is private while the serving path
-> is finalized.
 ## Quality (measured, 5,931 held-out positions vs bf16)
@@ -45,21 +53,25 @@ present in this exact bundle. Native multi-token-prediction head preserved (4-bi
 | Tier | Size | RAM w/ SSD-table | median KL | top-1 | top-5 | top-10 |
 |---|---|---|---|---|---|---|
-| JANG_1L | 60.4 GiB | ~41 GiB | 0.0366 | 86.7% | 97.6% | 98.8% |
-| JANG_2L | 65.9 GiB | ~48 GiB | 0.0249 | 87.8% | 98.2% | 99.1% |
-| JANG_4S | 72.4 GiB | ~53 GiB | 0.0161 | 89.7% | 98.6% | 99.3% |
-| **JANG_4M** | **96.6 GiB** | **~73 GiB** | **0.0039** | **94.4%** | **99.7%** | **99.9%** |
-| JANG_6S | 106.9 GiB | ~83 GiB | 0.0035 | 94.8% | 99.7% | 99.9% |
 Margin-conditioned flip curves are monotone-decreasing on every tier —
 quantization noise lives in the reference model's own uncertainty band, with
 zero disagreement at high-confidence positions on the upper tiers.
-## The n-gram table & memory
-The 51B n-gram embedding can be served directly from SSD by supporting
-runtimes; the "RAM w/ SSD-table" column above is the resident footprint in
-that mode.
 ## What's in the bundle

 - awq
 ---
+<p align="center">
+  <img src="./jangq-logo.png" alt="JANGQ" width="220">
+  &nbsp;&nbsp;&nbsp;
+  <img src="./vmlx-logo.png" alt="vMLX" width="90">
+</p>
 # JANGQ-AI/Qwen3.8-Flash-Next-JANG_4M
+**The recommended quality/size balance — median KL 0.0042 vs bf16 at 96.0 GiB (~73 GiB resident with the SSD-served table).**
 A JANG bundle of [Qwen/Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next)
 — the Qwen4-architecture preview: a 125B mixture-of-experts (512 experts,
 quantized for Apple Silicon / MLX. Text, image and video weights are all
 present in this exact bundle. Native multi-token-prediction head preserved (4-bit).
+> **Best experienced in vMLX.** This bundle's layout — the SSD-served n-gram
+> table, per-module mixed precision, and the native MTP head — is designed for
+> the vMLX serving path. Access is gated (manual approval) while runtime
+> support rolls out.
 ## Quality (measured, 5,931 held-out positions vs bf16)
 | Tier | Size | RAM w/ SSD-table | median KL | top-1 | top-5 | top-10 |
 |---|---|---|---|---|---|---|
+| JANG_1L | 59.8 GiB | ~41 GiB | 0.0362 | 86.7% | 97.5% | 98.8% |
+| JANG_2L | 65.3 GiB | ~48 GiB | 0.0260 | 88.2% | 98.2% | 99.0% |
+| JANG_4S | 71.8 GiB | ~53 GiB | 0.0161 | 89.4% | 98.7% | 99.4% |
+| **JANG_4M** | **96.0 GiB** | **~73 GiB** | **0.0042** | **94.4%** | **99.7%** | **99.9%** |
+| JANG_6S | 106.3 GiB | ~83 GiB | 0.0035 | 94.7% | 99.7% | 99.9% |
 Margin-conditioned flip curves are monotone-decreasing on every tier —
 quantization noise lives in the reference model's own uncertainty band, with
 zero disagreement at high-confidence positions on the upper tiers.
+## The n-gram table & memory — SSD caching, fixed and fast
+The 51B n-gram embedding streams **directly from SSD** on supporting runtimes
+(16 row-reads per token) — the "RAM w/ SSD-table" column above is the true
+resident footprint in that mode. Early runtime builds throttled in this mode;
+**SSD-table caching is now fixed**: decode runs at full speed with the table
+on disk — 40+ tok/s on an M5 Max for the 4-bit tier — so the biggest tiers fit
+comfortably on 64–128 GB machines without giving up the table.
 ## What's in the bundle

config.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

jang_ladder_wide.png CHANGED Viewed

Git LFS Details

SHA256: f8de188402fea0137ca0b07c8b8dfbe46311cf6c95c5128587aa0934aeb3d3e2
Pointer size: 131 Bytes
Size of remote file: 107 kB

Git LFS Details

SHA256: d35fa74f384f243967467d5b7efc729cf0577bfd7f6f3d7f7b218e039b1e06fc
Pointer size: 131 Bytes
Size of remote file: 123 kB

jangq-logo.png ADDED Viewed

model-00001-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5873d1199ad31349130c74260a365eb447dccb5a89ebda921511ea2f04f4d39b
-size 5336991211

 version https://git-lfs.github.com/spec/v1
+oid sha256:0bd29b8a0865ff222f1e959ba46b1803c193abf53325aa1880a06c50f2ee2b58
+size 5486992131

model-00002-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc4d9becc72d9a7f3fd3c8f271fc3aeb5c1c7076dcb331afb8201420bc352ae
-size 5450036745

 version https://git-lfs.github.com/spec/v1
+oid sha256:5f2afd711ba2c1ca0bcc750033bdeed073524cd391923f52bc164ee3e67cbbc7
+size 5550037500

model-00003-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc11c3379b9382c83048bd6d5d18fc9bef66c405261ebccaca1961fc6589fce
-size 5450036521

 version https://git-lfs.github.com/spec/v1
+oid sha256:001e46e174f9c59ff7ed70a19572b6a072456fcea3b5103bef656380774cf046
+size 5450036517

model-00004-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c21c525b05099e0a2d7ef65989c2addbd8ecdc0b1abc3112369da918de62b4
-size 5550037003

 version https://git-lfs.github.com/spec/v1
+oid sha256:7a0a002f1c247841372cf8969171e9935eae06bfcb7a628ac33f97840557f6e1
+size 5550037008

model-00005-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a21a63c657c7c7779145ebce640be1d1b8e67c6a4b9a2e0999266178fb91c334
-size 5450036927

 version https://git-lfs.github.com/spec/v1
+oid sha256:1a1330b33bfb915fa070704cb3b9aaf19b9a910337f00813ac1cb61149f2b199
+size 5400036692

model-00006-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45fdb0baa834908960b1f106cea459c69a208a69e6357ea4f25547e8ca9af275
-size 3720605883

 version https://git-lfs.github.com/spec/v1
+oid sha256:1a16e3534565e3e629cd1e8ca6ff4299fd5e896298c9e9c40bb668cbff09c01a
+size 3520604420

model-00007-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:573de78dd7dd219c1bf8b4ac902cf091fe34ac545e5d59d1c9e91dff977fe9e9
-size 5482961885

 version https://git-lfs.github.com/spec/v1
+oid sha256:30418f088234d40133eceae84be586ff1210ecde7f68d2fc8f75a589a9d383c9
+size 5482961881

model-00008-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d7c50c667679a0b4efc7a0c6082084c06993f97f57ce96989cb971c262ce335
-size 5562155652

 version https://git-lfs.github.com/spec/v1
+oid sha256:4fd30a4f043287ad7a90629b6d3be8bf08ef10ebe9144c69acc7a7ab261c6ba1
+size 5562155614

model-00009-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3121c82348ac6e64c3ede95958a24164897c64045022cb04946367c0484b5186
-size 1022912957

 version https://git-lfs.github.com/spec/v1
+oid sha256:b430f767e7d97c1e6a6d1f52076c132f097431b2a9d0127b7c29bad9f0c0b7c1
+size 1022912939

model-00010-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea1dca23921028c8fb051b6001dc8b30abdbb65c1a2e5f563c569756b92c121d
-size 5482961908

 version https://git-lfs.github.com/spec/v1
+oid sha256:cc3f947fe1dd516d472418770e1ec01837c6dc571bf3ae3d1817b90d7a50bf9b
+size 5482961900

model-00011-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f15bb8bcf7adb5887d8c54959a3f8e5aa15c6baadd7dfe82ab7c5ca577b658fb
-size 5562155678

 version https://git-lfs.github.com/spec/v1
+oid sha256:44832edabc381e7b9296bd4237b72207d9ba469a4432b3ea19c045373e672011
+size 5562155720

model-00012-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cebe46b2891114db643a06ee226dc11c3052f8dd4ac2e41c597646d13bfb48ca
-size 1022912983

 version https://git-lfs.github.com/spec/v1
+oid sha256:e55aed126efb552db83aee7be5d39f2a16086b5343c5bd2892f9069cdb270e03
+size 1022912927

model-00013-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9fe1529f68f2ff24506daae6ccfb43e99a4fb4750cfd1b53a4ed7f9ff888496
-size 5482961919

 version https://git-lfs.github.com/spec/v1
+oid sha256:3a91247f159acd2cf3a127af38f057fdded10bf2921debe7bb803e9ee928bc1c
+size 5482961939

model-00014-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d0621077fdf939f4ff519649735948def1ff434be8681c4e719410cfb86faa3
-size 5500533638

 version https://git-lfs.github.com/spec/v1
+oid sha256:623d8ac461c05795633e396d60ba6de5b54df83d8f05be0efc72a8bfc6a92a15
+size 5500533628

model-00015-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463dc120e4086d267e3b97d7cfe23cb3aac566e23a3bf39879b26946dc1e4cd9
-size 1077578064

 version https://git-lfs.github.com/spec/v1
+oid sha256:60d60b04e812d782e037f0147961ee30e1b252ced989180d90122ec25b5b674a
+size 1077577930

model-00016-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df968ef20337e7876670ed92289bf21cd67c38b03b056712f7b38151490c25e1
-size 5428296828

 version https://git-lfs.github.com/spec/v1
+oid sha256:7022950db97be03eb74c357444de0c623567beb4f764b1275abec3c788642a34
+size 5428296850

model-00017-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2678258f2062b4d219a9dd4525d6e864707ef2494ba31864f2d21cf1e0df52e
-size 5562155742

 version https://git-lfs.github.com/spec/v1
+oid sha256:360234a7b82bde72b4e4558fef75762e52cf909d9c3a535a8bae44c8f711d505
+size 5562155736

model-00018-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20617ddee54ede164334bad7a7a43f5c7255a2ce1a96c088169d86bfc2f1a79
-size 1077578051

 version https://git-lfs.github.com/spec/v1
+oid sha256:e9523f5f909402201b67d69caa6fc4ad37c8df6d51151804f0b15f041a3539a6
+size 1077577927

model-00019-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e633438a4af89bef6eb0c4e921bc5e124cba8136f00e8f87247452df32deb24
-size 5489918857

 version https://git-lfs.github.com/spec/v1
+oid sha256:05b6362076bac322444166387ba4d915f3a63c114e72ed8b76488c41804e7df6
+size 5489918919

model-00020-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81f102b932f5b22a9f15e1f537c85246726954e31fda214916c7afd390cf4e11
-size 5562155780

 version https://git-lfs.github.com/spec/v1
+oid sha256:d48d4da6a9bd2aa7221d454a68d410b4b54b7f9b878179f732cbfd5be1aacb2a
+size 5562155602

model-00021-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f21a5691a6cfa9bcd27ed92fae7cff41694096ffe1dca2a16853cd10a94b93a3
-size 1029190454

 version https://git-lfs.github.com/spec/v1
+oid sha256:67584e42b7a0fe09a9b807fbccbc4842b9396c9a82a4a62fe64f9f6fda02ccce
+size 1029190432

model-00022-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8f6fe0a62da688563cbfa243a69fccae437c469345f4c279068375a744b375e
-size 5415062228

 version https://git-lfs.github.com/spec/v1
+oid sha256:15e2c87f79d546bfe89b77d002492f585d1d619920a4bf02bd0b1c46b31fea6e
+size 5415062308

model-00023-of-00026.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5850923a309a6c9a2dee89598134741ea6f893e216b2ab29b95c2b334951d9ea
-size 5632512673

 version https://git-lfs.github.com/spec/v1
+oid sha256:8d5a96e5b61309ada3e2fd556e704180e8484dd74e5ce5ed9d28abccf1ecdf5c
+size 5632512775

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
  "metadata": {
-  "total_size": 103754740088
  },
  "weight_map": {
   "language_model.embed_tokens.weight": "model-00001-of-00026.safetensors",
@@ -136,7 +136,7 @@
   "language_model.layers.1.ple.ngram_embedding.shards.104.weight": "model-00001-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.104.scales": "model-00001-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.104.biases": "model-00001-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.105.weight": "model-00002-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.105.scales": "model-00002-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.105.biases": "model-00002-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.106.weight": "model-00002-of-00026.safetensors",
@@ -212,9 +212,9 @@
   "language_model.layers.1.ple.ngram_embedding.shards.127.scales": "model-00002-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.127.biases": "model-00002-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.13.weight": "model-00002-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.13.scales": "model-00003-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.13.biases": "model-00003-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.14.weight": "model-00003-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.14.scales": "model-00003-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.14.biases": "model-00003-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.15.weight": "model-00003-of-00026.safetensors",
@@ -287,9 +287,9 @@
   "language_model.layers.1.ple.ngram_embedding.shards.35.scales": "model-00003-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.35.biases": "model-00003-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.36.weight": "model-00003-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.36.scales": "model-00004-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.36.biases": "model-00004-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.37.weight": "model-00004-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.37.scales": "model-00004-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.37.biases": "model-00004-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.38.weight": "model-00004-of-00026.safetensors",
@@ -362,9 +362,9 @@
   "language_model.layers.1.ple.ngram_embedding.shards.58.scales": "model-00004-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.58.biases": "model-00004-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.59.weight": "model-00004-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.59.scales": "model-00005-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.59.biases": "model-00005-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.6.weight": "model-00005-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.6.scales": "model-00005-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.6.biases": "model-00005-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.60.weight": "model-00005-of-00026.safetensors",
@@ -440,9 +440,9 @@
   "language_model.layers.1.ple.ngram_embedding.shards.81.scales": "model-00005-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.81.biases": "model-00005-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.82.weight": "model-00005-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.82.scales": "model-00006-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.82.biases": "model-00006-of-00026.safetensors",
-  "language_model.layers.1.ple.ngram_embedding.shards.83.weight": "model-00006-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.83.scales": "model-00006-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.83.biases": "model-00006-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.84.weight": "model-00006-of-00026.safetensors",

 {
  "metadata": {
+  "total_size": 103108944248
  },
  "weight_map": {
   "language_model.embed_tokens.weight": "model-00001-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.104.weight": "model-00001-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.104.scales": "model-00001-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.104.biases": "model-00001-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.105.weight": "model-00001-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.105.scales": "model-00002-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.105.biases": "model-00002-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.106.weight": "model-00002-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.127.scales": "model-00002-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.127.biases": "model-00002-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.13.weight": "model-00002-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.13.scales": "model-00002-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.13.biases": "model-00002-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.14.weight": "model-00002-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.14.scales": "model-00003-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.14.biases": "model-00003-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.15.weight": "model-00003-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.35.scales": "model-00003-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.35.biases": "model-00003-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.36.weight": "model-00003-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.36.scales": "model-00003-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.36.biases": "model-00003-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.37.weight": "model-00003-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.37.scales": "model-00004-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.37.biases": "model-00004-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.38.weight": "model-00004-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.58.scales": "model-00004-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.58.biases": "model-00004-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.59.weight": "model-00004-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.59.scales": "model-00004-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.59.biases": "model-00004-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.6.weight": "model-00004-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.6.scales": "model-00005-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.6.biases": "model-00005-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.60.weight": "model-00005-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.81.scales": "model-00005-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.81.biases": "model-00005-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.82.weight": "model-00005-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.82.scales": "model-00005-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.82.biases": "model-00005-of-00026.safetensors",
+  "language_model.layers.1.ple.ngram_embedding.shards.83.weight": "model-00005-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.83.scales": "model-00006-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.83.biases": "model-00006-of-00026.safetensors",
   "language_model.layers.1.ple.ngram_embedding.shards.84.weight": "model-00006-of-00026.safetensors",

vmlx-logo.png ADDED Viewed