Instructions to use avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw with MLX:

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

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw 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 "avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw"

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 avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw

Run Hermes

hermes

OpenClaw new

How to use avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw"

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 "avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw" \
  --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"

MLX LM

How to use avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

avlp12 commited on 7 days ago

Commit

b2e4e9c

verified ·

1 Parent(s): a707e17

main: anchor-guarded clip + DWQ-A45 rework, atomic swap (prior main preserved on dwq-noclip)

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

README.md +16 -14
assets/quality.png +2 -2
assets/quality.svg +6 -6
config.json +0 -0
model-00001-of-00047.safetensors +1 -1
model-00002-of-00047.safetensors +1 -1
model-00003-of-00047.safetensors +1 -1
model-00004-of-00047.safetensors +1 -1
model-00005-of-00047.safetensors +1 -1
model-00006-of-00047.safetensors +1 -1
model-00007-of-00047.safetensors +1 -1
model-00008-of-00047.safetensors +1 -1
model-00009-of-00047.safetensors +1 -1
model-00010-of-00047.safetensors +1 -1
model-00011-of-00047.safetensors +1 -1
model-00012-of-00047.safetensors +1 -1
model-00013-of-00047.safetensors +1 -1
model-00014-of-00047.safetensors +1 -1
model-00015-of-00047.safetensors +1 -1
model-00016-of-00047.safetensors +1 -1
model-00017-of-00047.safetensors +1 -1
model-00018-of-00047.safetensors +1 -1
model-00019-of-00047.safetensors +1 -1
model-00020-of-00047.safetensors +1 -1
model-00021-of-00047.safetensors +1 -1
model-00022-of-00047.safetensors +1 -1
model-00023-of-00047.safetensors +1 -1
model-00024-of-00047.safetensors +1 -1
model-00025-of-00047.safetensors +1 -1
model-00026-of-00047.safetensors +1 -1
model-00027-of-00047.safetensors +1 -1
model-00028-of-00047.safetensors +1 -1
model-00029-of-00047.safetensors +1 -1
model-00030-of-00047.safetensors +1 -1
model-00031-of-00047.safetensors +1 -1
model-00032-of-00047.safetensors +1 -1
model-00033-of-00047.safetensors +1 -1
model-00034-of-00047.safetensors +1 -1
model-00035-of-00047.safetensors +1 -1
model-00036-of-00047.safetensors +1 -1
model-00037-of-00047.safetensors +1 -1
model-00038-of-00047.safetensors +1 -1
model-00039-of-00047.safetensors +1 -1
model-00040-of-00047.safetensors +1 -1
model-00041-of-00047.safetensors +1 -1
model-00042-of-00047.safetensors +1 -1
model-00043-of-00047.safetensors +1 -1
model-00044-of-00047.safetensors +1 -1
model-00045-of-00047.safetensors +1 -1
model-00046-of-00047.safetensors +2 -2

README.md CHANGED Viewed

@@ -27,16 +27,18 @@ Apple Silicon (MLX) **mixed-precision** quantization of [zai-org/GLM-5.2](https:
 **New:** the checkpoint now ships GLM-5.2's **native MTP (nextn) layer** for self-speculative decoding (`--mtp` — see [*Native MTP*](#native-mtp--self-speculative-decoding)). Fully backward-compatible: runtimes without MTP support strip the extra layer and behave exactly as before.
-**Update (2026-07): DWQ-retuned weights.** `main` now carries quantization scales/biases re-tuned with **layerwise DWQ** ([alis-dwq](https://github.com/avlp12/alis-dwq); upstream flag: [mlx-lm#1499](https://github.com/ml-explore/mlx-lm/pull/1499)) against the [4.5 bpw sibling](https://huggingface.co/avlp12/GLM-5.2-Alis-MLX-Dynamic-4.5bpw) as teacher, with a 45%-ZH calibration mix — low-bit damage concentrates in the model's Chinese mass, and this targets exactly that. Same recipe, size class and speed; distributional fidelity jumps:
-| KL / top-1 flip vs the 4.5 bpw reference (T=3072) | pre-DWQ | **DWQ (main)** |
-|---|---|---|
-| EN | 0.727 / 24.9% | **0.383 / 15.6%** |
-| code | 0.252 / 12.7% | **0.193 / 10.2%** |
-| ZH | 0.987 / 35.7% | **0.562 / 21.9%** |
-| overall | 0.655 / 24.4% | **0.379 / 15.9% (−42% KL)** |
-The pre-DWQ weights remain available on the [`pre-dwq`](https://huggingface.co/avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw/tree/pre-dwq) branch. **The *Quality* and *Benchmarks* figures below are measured on these DWQ weights** — the retune also moves perplexity (strided wikitext 4.34 → 3.77, code 2.20 → 2.07; `mlx_lm.perplexity` on tulu-3 3.85 → 3.56), not just the KL above.
 ## Metrics
@@ -44,7 +46,7 @@ The pre-DWQ weights remain available on the [`pre-dwq`](https://huggingface.co/a
 |---|---|
 | Base model | zai-org/GLM-5.2 (744B total / \~40B active) |
 | Bits/weight | **\~2.56** (per-tensor mixed) |
-| On-disk size | **246.9 GB** (48 shards, incl. the 4.5 GB native MTP layer) |
 | Peak memory | \~242 GB (weights, MTP-attached) · \~249 GB (8K) · \~263 GB (26K) · \~293 GB (64K) · \~344 GB (128K) — **measured** (int8 KV); the DSA prefill activation grows with context |
 | Format | MLX (Apple Silicon) |
 | Context | 1M-capable architecture (DSA); **machine-limited in practice** — ≈26–32K prefill on a 256 GiB box (see *Long context & memory*) |
@@ -58,7 +60,7 @@ GLM-5.2 is a frontier agentic-coding MoE, but at 744B it is \~1.5 TB in bf16 —
 ## Quality
-This is the **≤256 GB** option — the routed experts are 2-bit, so it is deliberately bit-starved. If you have a 512 GB machine, the **[3.5 bpw build](https://huggingface.co/avlp12/GLM-5.2-Alis-MLX-Dynamic-3.5bpw)** is still better on prose/code strided PPL (−25% wikitext, −11% code; the 3.5 bpw sibling is DWQ-retuned against an 8-bit teacher) and runs a full 1M context.
 ![Perplexity: this 2.56 bpw build vs the 3.5 bpw build — 2.56 bpw is 25% higher (worse) on wikitext, 11% on code](assets/quality.png)
@@ -70,13 +72,13 @@ Reproduced with `mlx_lm.evaluate` (0-shot) and `mlx_lm.perplexity` (seq 2048, 50
 | | GLM-5.1 · 2.7 bpw | **GLM-5.2 · 2.56 bpw (this)** | GLM-5.2 · 3.5 bpw |
 |---|---|---|---|
-| Perplexity (lower) | 4.165 | **3.564** | 3.630 |
-| HellaSwag (acc_norm) | 0.606 | **0.652** | 0.604 |
-| PIQA (acc) | 0.796 | **0.808** | 0.822 |
 | WinoGrande (acc) | 0.660 | **0.780** | 0.780 |
 | Generation (tok/s) | 18.35 | **22.87** | 21.29 |
-Perplexity here is on `allenai/tulu-3-sft-mixture` (the `mlx_lm.perplexity` default) — a different corpus and method from the wikitext strided figure above, so values are not comparable across the two. Task accuracies use a 500-sample limit (CI ±0.02–0.04). GLM-5.1 is a different (older) base model, so cross-generation gaps reflect both the newer model and quantization.
 **Quantization recipe**

 **New:** the checkpoint now ships GLM-5.2's **native MTP (nextn) layer** for self-speculative decoding (`--mtp` — see [*Native MTP*](#native-mtp--self-speculative-decoding)). Fully backward-compatible: runtimes without MTP support strip the extra layer and behave exactly as before.
+**Update 2 (2026-07): anchor-guarded clip + DWQ re-run.** `main` is now rebuilt from a **Q8 source** with an anchor-guarded clip search (per-group outlier clipping at max-err slack 1.1 that preserves the min-max anchor weights; method in [alis-dwq](https://github.com/avlp12/alis-dwq)), then DWQ-retuned with the same recipe as before (4.5 bpw-teacher targets, 45%-ZH calibration, upstream flag [mlx-lm#1499](https://github.com/ml-explore/mlx-lm/pull/1499)). Held-out perplexity improves or holds everywhere vs the previous DWQ main: strided wikitext **3.774 → 3.698 (−2.0%)**, code **2.069 → 2.054**, tulu-3 flat (3.564 → 3.571 ±0.027); the clip alone moves the raw pre-DWQ build 4.34 → 4.17. The checkpoint also sheds 4.5 GB: the MTP layer used to ship twice (a module-named copy inside the base shards plus the standalone MTP shard), and now ships once.
+| KL / top-1 flip vs the 4.5 bpw reference (T=3072) | pre-DWQ | first DWQ (`dwq-noclip`) | **clip+DWQ (main)** |
+|---|---|---|---|
+| EN | 0.727 / 24.9% | 0.383 / 15.6% | 0.464 / 17.3% |
+| code | 0.252 / 12.7% | 0.193 / 10.2% | **0.183 / 10.0%** |
+| ZH | 0.987 / 35.7% | 0.562 / 21.9% | 0.610 / 24.8% |
+| overall | 0.655 / 24.4% | 0.379 / 15.9% | 0.419 / 17.4% |
+*How to read this table: the reference is the 4.5 bpw **quantized** sibling, not ground truth. The first DWQ was derived from the same 4-bit-lattice family as that reference, so it sits unusually close to it; the clip step re-derives every tensor from a Q8 source (removing the lattice-resonance failure mode), which drifts slightly away from this particular reference even as held-out perplexity — the metric that tracks real quality — improves. Judge builds by the PPL numbers.* Greedy loop-probe (256 tok × EN/code/ZH): clean, no cycles.
+Weights history: original quant on [`pre-dwq`](https://huggingface.co/avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw/tree/pre-dwq) · first DWQ retune on [`dwq-noclip`](https://huggingface.co/avlp12/GLM-5.2-Alis-MLX-Dynamic-2.56bpw/tree/dwq-noclip) · current `main` = clip + DWQ.
 ## Metrics
 |---|---|
 | Base model | zai-org/GLM-5.2 (744B total / \~40B active) |
 | Bits/weight | **\~2.56** (per-tensor mixed) |
+| On-disk size | **242.4 GB** (47 shards: 46 base + the 4.5 GB native MTP layer, which no longer ships twice) |
 | Peak memory | \~242 GB (weights, MTP-attached) · \~249 GB (8K) · \~263 GB (26K) · \~293 GB (64K) · \~344 GB (128K) — **measured** (int8 KV); the DSA prefill activation grows with context |
 | Format | MLX (Apple Silicon) |
 | Context | 1M-capable architecture (DSA); **machine-limited in practice** — ≈26–32K prefill on a 256 GiB box (see *Long context & memory*) |
 ## Quality
+This is the **≤256 GB** option — the routed experts are 2-bit, so it is deliberately bit-starved. If you have a 512 GB machine, the **[3.5 bpw build](https://huggingface.co/avlp12/GLM-5.2-Alis-MLX-Dynamic-3.5bpw)** is still better on prose/code strided PPL (−25% wikitext, −11% code; both builds are clip+DWQ retunes, the 3.5 bpw sibling against an 8-bit teacher) and runs a full 1M context.
 ![Perplexity: this 2.56 bpw build vs the 3.5 bpw build — 2.56 bpw is 25% higher (worse) on wikitext, 11% on code](assets/quality.png)
 | | GLM-5.1 · 2.7 bpw | **GLM-5.2 · 2.56 bpw (this)** | GLM-5.2 · 3.5 bpw |
 |---|---|---|---|
+| Perplexity (lower) | 4.165 | **3.571** | 3.644 |
+| HellaSwag (acc_norm) | 0.606 | **0.652** | 0.626 |
+| PIQA (acc) | 0.796 | **0.808** | 0.838 |
 | WinoGrande (acc) | 0.660 | **0.780** | 0.780 |
 | Generation (tok/s) | 18.35 | **22.87** | 21.29 |
+Perplexity here is on `allenai/tulu-3-sft-mixture` (the `mlx_lm.perplexity` default) — a different corpus and method from the wikitext strided figure above, so values are not comparable across the two. Task accuracies use a 500-sample limit (CI ±0.02–0.04). This column's perplexity is measured on the current `main` (clip+DWQ); its task accuracies were measured on the previous retune (now `dwq-noclip`) — a task-accuracy re-run on the current `main` is queued. The 3.5 bpw column is that build's current `main` (all re-measured). GLM-5.1 is a different (older) base model, so cross-generation gaps reflect both the newer model and quantization.
 **Quantization recipe**

assets/quality.png CHANGED Viewed

Git LFS Details

SHA256: 1d40d38568fd965753b35d0008be5480e1b68f4ad1e33353bc99a762ef25b705
Pointer size: 130 Bytes
Size of remote file: 65.9 kB

Git LFS Details

SHA256: 9772e208c8728d3d5305163375e4fce56a08ea48b1934bcfaf220fb279891032
Pointer size: 130 Bytes
Size of remote file: 61.7 kB

assets/quality.svg CHANGED Viewed

config.json CHANGED Viewed

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

model-00001-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a4940f13fa66bbffe0179befc8444ecfcea7298494f2e4c3380aec73245db2b
 size 4720139752

 version https://git-lfs.github.com/spec/v1
+oid sha256:004fbaeac7db373cb77541d4cc64cfb448893fba19ef935945c51b7270b189ac
 size 4720139752

model-00002-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef903c239e355401ee8fbb14d6a453ca427f8a838ec14893195fb28f6039b21
 size 5150404363

 version https://git-lfs.github.com/spec/v1
+oid sha256:175661504973cffd2872c567a1f347cd28ce86030e9b15b44001f168d27a4111
 size 5150404363

model-00003-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c14f10a1c8a73c411086d677ecadc1f7b40dfa7bc79be36b1138a24466c914c
 size 5286386379

 version https://git-lfs.github.com/spec/v1
+oid sha256:44e7f0786ba71b2e9089ebefa1106b7f81a22163c26f6c013a1bf556718d09ef
 size 5286386379

model-00004-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ff1e786ce75d6f279e5c777be1b87a89b5bf5c4362d2336e833775e83d61bf1
 size 5267641891

 version https://git-lfs.github.com/spec/v1
+oid sha256:951b0790233659e390783fc8928295ee4cdeaad0cbe645b07a9b5c0ca21f3fb4
 size 5267641891

model-00005-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:907dc6c8b2ad41ed38dd8bbe6ba0097793dd2f8e00eaed8fb860f1538840b992
 size 5169148808

 version https://git-lfs.github.com/spec/v1
+oid sha256:65baa849dba3c6a842d8f86dff809e19e8d9098c3330ed2c9e69f7c754bbf357
 size 5169148808

model-00006-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6884f72dd597a89f890621f1462aba69b8b5f184f08586ebe37e361530f9e124
 size 5267642066

 version https://git-lfs.github.com/spec/v1
+oid sha256:5b7e75090bf85c987e7e512c1eeb5c61debd67657a2b32ee976b1571980d96d1
 size 5267642066

model-00007-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d57f5103595f98767f223ed314ac50bbc6ab7efd629b6cc19946482f2bc462a
 size 5286386413

 version https://git-lfs.github.com/spec/v1
+oid sha256:07f1feeae8cfb9d8a464f0c9be3479da80f90a7e5e5283a1e6092532c4c99fa8
 size 5286386413

model-00008-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:385b518fd74b88b22d5103fa372054ebc4be54ff0c8819ae3ec935698071934c
 size 5150404393

 version https://git-lfs.github.com/spec/v1
+oid sha256:9483a9d597cfab5181f583da7f7c1f38f6220456e6d555f4bf294d3f17d89cf1
 size 5150404393

model-00009-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d5c8cac2a8c46b45ee551ecaa2f3f9afd0067ee9bec1de62f857e8142f9a5b
 size 5267642054

 version https://git-lfs.github.com/spec/v1
+oid sha256:01f29bbd0f8bedbcaf75396b724a2aed5465a69083efd2ca1b68ebe6014496f0
 size 5267642054

model-00010-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afdf9dc23e7938686edf32ed39d253a52b011b569c45a85d23e423993e6519aa
 size 5286386433

 version https://git-lfs.github.com/spec/v1
+oid sha256:591f4c3f82ff6238b058d99e236f3a81c48b37716a63a97ba3f9b6485e467093
 size 5286386433

model-00011-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f4967eb1b4da1bb6926917963dd4333281ebfc4218675edb6fa3b8621a11d2
 size 5150404409

 version https://git-lfs.github.com/spec/v1
+oid sha256:98967e6de2686d7c3a1ec251b9b2505886010779ec406e9f44495305dc06b681
 size 5150404409

model-00012-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d6ef0c6c2da27254716846aec19c46102added0d3d0344dba901d38a7fedf39
 size 5286386459

 version https://git-lfs.github.com/spec/v1
+oid sha256:f26da6cd9cb630aec4dbe10d4bc0881899d5f9ce7e249fb517fbaca4a5759d6d
 size 5286386459

model-00013-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a160455286773ac2bb1b3539512b8819c5fd3efcc6ee108e7fd15eda374985
 size 5267642000

 version https://git-lfs.github.com/spec/v1
+oid sha256:ed93032925e3d6fb2fd1b066a87d21b30eb3b339f4286b4840f13f7ee46e2c59
 size 5267642000

model-00014-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1488417083b95c8dea6fb687d31f31ea55b530441e75437cc94d3b3d07210ec8
 size 5150404409

 version https://git-lfs.github.com/spec/v1
+oid sha256:9206a05b46e4d387b78dfbf2318dc06a644c7905837b2bec368ef61c97d9c7e3
 size 5150404409

model-00015-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de16cae33d6dc83ca220175225144b1432492ede39448dda4163850a489d1e7
 size 5286386493

 version https://git-lfs.github.com/spec/v1
+oid sha256:d562a05059f522f1c72adf43d7b6e0ecf074f26f03d4c1289fc37f81e8bc7afa
 size 5286386493

model-00016-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87357d30246b39e09423c6d8cbb4b3973a05ad3147b73fe8719a008f55382216
 size 5267641968

 version https://git-lfs.github.com/spec/v1
+oid sha256:00aadafc65250d712bdc9efef751c9c57869fc3a56b58a91192b5eba20214aee
 size 5267641968

model-00017-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d0c1b5f980c3c3136fde813c2484d4f5aa8f202659916b569538010e5be025
 size 5169148832

 version https://git-lfs.github.com/spec/v1
+oid sha256:b0bb3ed42952336b68375de98c212e5c6a291534e58d1c9e69411b2359e393f7
 size 5169148832

model-00018-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68eea5b9b58699365f6d2e5c24050a143cce4baab7c27d4782df38c72132b61e
 size 5267642050

 version https://git-lfs.github.com/spec/v1
+oid sha256:eb67d4bd91bfa408b5c23e1b4fa8731c961c9c5f85efea6067ec97d9313e53d8
 size 5267642050

model-00019-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d2b0fd9a1868e56833a793c83e0ca0ff38282ff84a7c821a5a6bde2931e6256
 size 5286386411

 version https://git-lfs.github.com/spec/v1
+oid sha256:6a6288778eadd867b499b60ec39d7dad4d6552e0f144574773b1f6774b21771e
 size 5286386411

model-00020-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7ebe9c2ccf446f034fcb8bf4bef2a4291ffecc884b64238988c1cdfaee9232
 size 5150404399

 version https://git-lfs.github.com/spec/v1
+oid sha256:22ed9fc05d50e00986f9681cf0a22a7f6c0f8155e72e2c06f4fbc1d001a6187b
 size 5150404399

model-00021-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27da782a7bff0780010e550c96e6feec86577ece859988544ed71a76793f7b9e
 size 5267642036

 version https://git-lfs.github.com/spec/v1
+oid sha256:b1638dd9480cfdb9dbe4072e01d52ee421fe39c59df2424b562e7743b3d27e8c
 size 5267642036

model-00022-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:320aac92d2b229b76299865045c5ca46d6195dd87c90030943a243d7581f972a
 size 5286386421

 version https://git-lfs.github.com/spec/v1
+oid sha256:abdafa0a5568b06f7f5b0d8aab16dfb04c99bf5f73f7f8a562cab90628224304
 size 5286386421

model-00023-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e481ba6f816f34476af50bbb03be1e3a2074d813eacb8de51e158e94d7c7598
 size 5150404381

 version https://git-lfs.github.com/spec/v1
+oid sha256:3e46e54856a010b97aac321f77c18718b78f7dbc955a9ee877e06f8701a70a67
 size 5150404381

model-00024-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:618eaadcb23d42b61e4288383695caebba37a47dd737ae7d97ff5c25708c8b9e
 size 5286386447

 version https://git-lfs.github.com/spec/v1
+oid sha256:10d40fb04b895ea04f703bd132ac3f380cdf3aa336366100b2da0b24be1d0a1e
 size 5286386447

model-00025-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f5b2b62de98a0cd4a5aed3c3d2c65ef7baf042e675e578959dff80a06232e4
 size 5267642004

 version https://git-lfs.github.com/spec/v1
+oid sha256:70a6f9e50b16bb86813f9fd8982398f925d61865dcc5b72b2ac482d6467b3932
 size 5267642004

model-00026-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29e363694db8810e75bf07d4f14ca3e3d8fc2f5c13bd19d0d98771be4133cdd4
 size 5150404401

 version https://git-lfs.github.com/spec/v1
+oid sha256:a3664a3420aafd9f76f357f015c6d1ac899f34a7d36328d6f7a1a734c181db9d
 size 5150404401

model-00027-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df1b0f9e2eb88af211ece851517d76c8ed21a48155f2931502be74b032cdd863
 size 5286386459

 version https://git-lfs.github.com/spec/v1
+oid sha256:2054385a09f60949885a25f14788aba56148039ea443443967409c4c0e9a9871
 size 5286386459

model-00028-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc72d25c2045861b1400ec00c82755f915ca5e1fd70c8c3d666f259962d95f45
 size 5267641994

 version https://git-lfs.github.com/spec/v1
+oid sha256:255510c734a911b453238484633235b319c0e35509c48c68f3f30c647d66e037
 size 5267641994

model-00029-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d244ce6ecb998da15a9a88b986d3664093616b0090f46420c1a65d18d7483318
 size 5169148832

 version https://git-lfs.github.com/spec/v1
+oid sha256:4ed4ed5614c8884df5e377db66b52898eefb41834a94226e179db837642e63a3
 size 5169148832

model-00030-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c90a69358a0f6f40ef860ab48416b541068a45dd1934ad267a9182ed7baa064
 size 5267642066

 version https://git-lfs.github.com/spec/v1
+oid sha256:213226a26b7928b5f23afc81016cf21699c15e264ee75a73728495c6ec97014a
 size 5267642066

model-00031-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffc9e60858cabbd05d2d92fe4bb676ba458bf71f61442191ac33818be347c263
 size 5286386417

 version https://git-lfs.github.com/spec/v1
+oid sha256:ef5eead9583a6f1c49cc92ca8caa43abc304337ec0c18440a2fcb011fd359ca1
 size 5286386417

model-00032-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:002ff572ea3e7432ff2676add4d6e42e6ee45225743ec8013db031b79c16d292
 size 5150404399

 version https://git-lfs.github.com/spec/v1
+oid sha256:d69193f6abd05ff495f9d1f6ae8dc2daddefcede2369636f0fec1ff19ecf26fd
 size 5150404399

model-00033-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90fec08ba906faa9ad37ad947f0a8da2a1f86ec6f3b248b75ac84832ee3aecbb
 size 5267642052

 version https://git-lfs.github.com/spec/v1
+oid sha256:79b6275b85808bb84749ee8b1d3be5853ca1680e0f1433e78b412ee7c0173afd
 size 5267642052

model-00034-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542477f95736743a0ea838828f61c9bffcf35f865e87f79876ddaaa262599a7a
 size 5286386423

 version https://git-lfs.github.com/spec/v1
+oid sha256:5959b3d13b7794ee97a68aec73ed1f7e6073126299d032eda534eb0ea988cf1b
 size 5286386423

model-00035-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9076d25e40677647f5df4703e77576c5ed6ae2331dcba6712535ba9242a60d25
 size 5150404411

 version https://git-lfs.github.com/spec/v1
+oid sha256:c13f8b0e4ca255f0592f06257b2c43cd3b66a318467d9f40cb4c3072d484872c
 size 5150404411

model-00036-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff73977e96ceaa3888710a92e7cae5ad365039c562be00b401ef608d79dd774e
 size 5286386467

 version https://git-lfs.github.com/spec/v1
+oid sha256:76831644ce07a658eaf9cf3105a2d4f339633c69321340cb309161a9c1fbd087
 size 5286386467

model-00037-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14879964d8ccb3308a2fda96c57987eb0b67023440e0f426bf997c6841724c47
 size 5267641972

 version https://git-lfs.github.com/spec/v1
+oid sha256:d4ff61c9d03f90445c3ae55120105575b774b962ab3fd5cc6b72f51ba752c9c6
 size 5267641972

model-00038-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2f6dc99ae8577086c85ba19c00e68d4d130c92a4e60c568f8fdd5ba2ef13cc
 size 5150404397

 version https://git-lfs.github.com/spec/v1
+oid sha256:d156e5bfeceae466549bfd9635e084a9aae6d9c8e1300b1c645ff1ef7b702ebb
 size 5150404397

model-00039-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b37ae3298d03d9a44789a9dea69f2ea92955913ef371c4cde5f368eb02ecb78
 size 5286386501

 version https://git-lfs.github.com/spec/v1
+oid sha256:9b0f091b53e8a19169eb3dadf3eacd379c5ecd1233af2df9a2593a611a8285ca
 size 5286386501

model-00040-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd9b69cfbe060690d965039b9786e4b2992ae91b58ae56ab1a858abe7aa164c
 size 5267641930

 version https://git-lfs.github.com/spec/v1
+oid sha256:93b9ef8e99d2df0adea7a999ea5a81b6f156637eb949bd9d93423cdf2c125448
 size 5267641930

model-00041-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858cd465af14715644d2d92ccdc493d1af1a2d3298637cbae0b5a12f55ce619f
 size 5169148832

 version https://git-lfs.github.com/spec/v1
+oid sha256:fbebcd01a2bd2880f37d10622d7772e9918534033bf7d130815ee9bdc483cf42
 size 5169148832

model-00042-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5e8cbc925884be9278cc8fc66da5856c2fc82799ea411d0b1c4c5b2160971f
 size 5267642050

 version https://git-lfs.github.com/spec/v1
+oid sha256:f3100fe613ad5f6d5b336bc10130d91684d52cbe5fa17eb3b02c0793b7cd2ce5
 size 5267642050

model-00043-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7ccc776c95446925e0cfd27917438642ea05e1cef36f91a571eef3f01bc2ed
 size 5286386411

 version https://git-lfs.github.com/spec/v1
+oid sha256:4f9a413034dd2d34d9b6e06f638a4ff982b82be693c1701e78452057923a2445
 size 5286386411

model-00044-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66cc59c2647dfa6db59accc5452db6461fff8eb4fc2bf952a92fbdc3b56af501
 size 5150404411

 version https://git-lfs.github.com/spec/v1
+oid sha256:b920b7c3b6da779a1966a4a7a3f268842b0eac1995d783cbc3df51f1027fe897
 size 5150404411

model-00045-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9999b0f020323454efecb565c7cd711a4f750257a7280498ea55aaa005b077f4
 size 5267642038

 version https://git-lfs.github.com/spec/v1
+oid sha256:050567bfb45ef6db5acab0ddcf9366604ffce2109d048d50a048cbf1aeac3cc1
 size 5267642038

model-00046-of-00047.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05a1513a7f548705634a59d3f523cf16d6d866d3d7fa3ae71922e8701678f41e
-size 4482728585

 version https://git-lfs.github.com/spec/v1
+oid sha256:91da2f99bf45232f376d5a32c27c6542a56f234f4dc95d4fe10920d5336d9d0e
+size 2810846901