Instructions to use avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw 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/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw")

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/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw 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/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw"

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/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw 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/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw 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/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw"

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/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use avlp12/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw 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/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw"

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/Kimi-K2.7-Code-Alis-MLX-Dynamic-3.6bpw" \
  --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"

avlp12 commited on Jun 24

Commit

e9009a3

verified ·

1 Parent(s): 0edafde

Kimi-K2.7-Code 3.6bpw MLX: weights + model card + figures

Browse files

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

Files changed (50) hide show

.gitattributes +4 -0
README.md +134 -0
figures/field.png +3 -0
figures/field.svg +37 -0
figures/memory.png +3 -0
figures/memory.svg +40 -0
figures/quality.png +3 -0
figures/quality.svg +30 -0
figures/recipe.png +3 -0
figures/recipe.svg +55 -0
model-00013-of-00093.safetensors +3 -0
model-00014-of-00093.safetensors +3 -0
model-00015-of-00093.safetensors +3 -0
model-00016-of-00093.safetensors +3 -0
model-00017-of-00093.safetensors +3 -0
model-00018-of-00093.safetensors +3 -0
model-00019-of-00093.safetensors +3 -0
model-00020-of-00093.safetensors +3 -0
model-00021-of-00093.safetensors +3 -0
model-00022-of-00093.safetensors +3 -0
model-00023-of-00093.safetensors +3 -0
model-00024-of-00093.safetensors +3 -0
model-00025-of-00093.safetensors +3 -0
model-00026-of-00093.safetensors +3 -0
model-00027-of-00093.safetensors +3 -0
model-00028-of-00093.safetensors +3 -0
model-00029-of-00093.safetensors +3 -0
model-00030-of-00093.safetensors +3 -0
model-00031-of-00093.safetensors +3 -0
model-00032-of-00093.safetensors +3 -0
model-00033-of-00093.safetensors +3 -0
model-00034-of-00093.safetensors +3 -0
model-00035-of-00093.safetensors +3 -0
model-00036-of-00093.safetensors +3 -0
model-00037-of-00093.safetensors +3 -0
model-00038-of-00093.safetensors +3 -0
model-00039-of-00093.safetensors +3 -0
model-00040-of-00093.safetensors +3 -0
model-00041-of-00093.safetensors +3 -0
model-00042-of-00093.safetensors +3 -0
model-00043-of-00093.safetensors +3 -0
model-00044-of-00093.safetensors +3 -0
model-00045-of-00093.safetensors +3 -0
model-00046-of-00093.safetensors +3 -0
model-00047-of-00093.safetensors +3 -0
model-00048-of-00093.safetensors +3 -0
model-00049-of-00093.safetensors +3 -0
model-00050-of-00093.safetensors +3 -0
model-00051-of-00093.safetensors +3 -0
model-00052-of-00093.safetensors +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+figures/field.png filter=lfs diff=lfs merge=lfs -text
+figures/memory.png filter=lfs diff=lfs merge=lfs -text
+figures/quality.png filter=lfs diff=lfs merge=lfs -text
+figures/recipe.png filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,134 @@

+---
+license: other
+license_name: modified-mit
+license_link: https://huggingface.co/moonshotai/Kimi-K2.7-Code/blob/main/LICENSE
+base_model: moonshotai/Kimi-K2.7-Code
+base_model_relation: quantized
+pipeline_tag: text-generation
+library_name: mlx
+tags:
+  - mlx
+  - kimi
+  - kimi-k2
+  - moe
+  - mla
+  - code
+  - quantized
+  - apple-silicon
+---
+# Kimi-K2.7-Code-MLX-3.6bpw
+A **sensitivity-graded 3.6-bit MLX quantization** of [moonshotai/Kimi-K2.7-Code](https://huggingface.co/moonshotai/Kimi-K2.7-Code) — a ~1T-parameter (32B active) DeepSeek-V3-style MoE coding model — built to run on Apple-Silicon **M3 Ultra** hardware.
+**465 GB (433 GiB)** on disk. It fits a single clean **512 GB** M3 Ultra, and runs with huge headroom **split across two 512 GB machines** (≈233 GB per box) over Thunderbolt.
+![quality](figures/quality.png)
+## Why this build exists
+Moonshot ships Kimi-K2.7-Code with its routed experts already **INT4** (`compressed-tensors`, group-size 32, QAT) and everything else in bf16 — about **595 GB**. The community MLX conversions either keep the experts at 4-bit and so need **~600–768 GB** of memory (don't fit a single 512 GB box), or drop uniformly to ~3.5-bit.
+This build takes a different route:
+- **Re-quantizes from the INT4 master correctly.** `mlx-lm` mishandles `compressed-tensors` checkpoints during re-quantization ([#907](https://github.com/ml-explore/mlx-lm/issues/907)) — asking for 3-bit yields 4.99 bpw / 640 GB. We dequantize the packed INT4 experts in-memory *before* re-quantizing, so the experts actually land below 4-bit.
+- **Spends bits where they matter.** Routed experts (≈99% of params) go to 3-bit; the residual-writing `down_proj` is upgraded to 4-bit on a spread of 16 layers (the most quantization-sensitive expert projection); attention (MLA), shared experts, the dense layer and the embeddings/head all stay at **6-bit**; the MoE router stays **bf16**.
+The result is a genuinely 512-GB-class build that keeps reasoning and coding quality intact.
+## Recipe (verified from the output `config.json`)
+![recipe](figures/recipe.png)
+| Component | Params share | Bits | Group |
+|---|---|---|---|
+| Routed experts `gate_proj` / `up_proj` | bulk | **3-bit** | 64 |
+| Routed experts `down_proj` | bulk | **4-bit on 16 / 60 layers, 3-bit on the rest** | 64 |
+| Attention (MLA `q_a/q_b/kv_a/kv_b/o`) | small | **6-bit** | 64 |
+| Shared expert · dense MLP (layer 0) | small | **6-bit** | 64 |
+| Token embedding · LM head | small | **6-bit** | 64 |
+| MoE router `gate` | tiny | **bf16** (never quantized) | — |
+Effective **3.62 bits/weight**. The `down_proj`-on-a-subset upgrade is the cheapest quality lever for a low-bit MoE — the residual-writing projection is by far the most sensitive expert matrix.
+## Memory & how to run it
+![memory](figures/memory.png)
+Kimi-K2.7-Code uses **Multi-head Latent Attention (MLA)**, so the KV cache is tiny — only the compressed latent (`kv_lora_rank` 512 + rope 64 = 576 values) per token per layer, ≈ **68.6 KB/token** across all 61 layers.
+| Context | KV cache (fp16) | KV cache (int8) |
+|---|---|---|
+| 32K | 2.3 GB | 1.2 GB |
+| 128K | 9.2 GB | 4.6 GB |
+| **256K (native max)** | **18.4 GB** | **9.2 GB** |
+The model's native context window is **256K tokens** (262,144; YaRN-extended, `rope_theta` 50000). Even at the full 256K, weights + KV stay far under memory on either deployment.
+**Single clean 512 GB box** — 465 GB weights leave ~47 GB; fine for inference, comfortable with int8 KV.
+**Two M3 Ultras over Thunderbolt (pipeline-parallel, recommended for headroom)** — each machine loads only its layer-half (~233 GB), so neither box approaches its 512 GB limit, leaving room for other workloads.
+```bash
+# 2-machine pipeline-parallel (mlx-lm, ring backend over a Thunderbolt bridge)
+mlx.launch --backend ring --hosts <ip0>,<ip1> python your_generate.py
+# each rank: model, tok = mlx_lm.utils.pipeline_load("/path/to/this/model")
+```
+## How it compares (Kimi-K2.7-Code MLX builds)
+![field](figures/field.png)
+| Build | bpw | Size | Fits 512 GB single? |
+|---|---|---|---|
+| pipenetwork 4bit-hiprec | ~5.0 | ~600 GB | ✗ (needs ~768 GB) |
+| spicyneuron 3.6bit | ~3.6 | ~460 GB | borderline |
+| **this build** | **3.62** | **465 GB** | ✓ (clean box) / ✓✓ split across 2 |
+This build is the only one shipped with the experts re-quantized **below** their INT4 master via the [#907](https://github.com/ml-explore/mlx-lm/issues/907) fix, a `down_proj`-protected sensitivity-graded recipe, and a verified two-machine pipeline path.
+## Benchmarks
+Same harness as the reference runs (`mlx_lm.perplexity` on `allenai/tulu-3-sft-mixture`, seq 2048, 50 samples; `mlx_lm.evaluate` 0-shot).
+| Metric | Value |
+|---|---|
+| **Perplexity** (tulu, seq 2048, n=50) | **3.735 ± 0.033** |
+| Decode throughput (2-machine pipeline, TB) | **~18 tok/s** |
+| Prefill throughput (warm) | ~59 tok/s |
+| Peak memory, split across 2 machines | 233 GB / 226 GB |
+| HellaSwag / PIQA / WinoGrande (0-shot, acc_norm) | _measuring_ |
+PPL is reported for build-vs-build comparison only — absolute perplexity is misleading at low bit-width. For scale, this 3.6-bit build's tulu PPL (3.735) sits right next to far larger MLX MoE builds on the same harness.
+## Correctness
+- **Real-weight reconstruction** of the INT4 experts verified sane across early/mid/late layers (finite, expected magnitudes).
+- **Coherent generation** in the distributed setup: correct iterative-Fibonacci and `merge_intervals` implementations (with passing asserts), correct technical Q&A. Kimi-K2.7-Code is a reasoning model and emits `<think>…</think>` before its answer.
+- Per-machine peak memory in the 2-machine run: **233 GB / 226 GB**.
+## Usage
+This build needs an `mlx-lm` that loads `compressed-tensors`-derived Kimi (`model_type: kimi_k25`, DeepSeek-V3 engine). Use `trust_remote_code=True` (the tokenizer is tiktoken-based — `pip install tiktoken blobfile`).
+```python
+from mlx_lm import load, generate
+from mlx_lm.sample_utils import make_sampler
+model, tok = load("avlp12/Kimi-K2.7-Code-MLX-3.6bpw",
+                  trust_remote_code=True,
+                  tokenizer_config={"trust_remote_code": True})
+msgs = [{"role": "user", "content": "Write a Python LRU cache with O(1) get/put."}]
+prompt = tok.apply_chat_template(msgs, add_generation_prompt=True)
+print(generate(model, tok, prompt=prompt, max_tokens=512, sampler=make_sampler(temp=0.0)))
+```
+## Credits
+- Base model: [moonshotai/Kimi-K2.7-Code](https://huggingface.co/moonshotai/Kimi-K2.7-Code) (Modified MIT).
+- Built with [mlx-lm](https://github.com/ml-explore/mlx-lm) on Apple MLX.
+## Citation
+> Kimi-K2.7-Code-MLX-3.6bpw — sensitivity-graded 3.6-bit MLX quantization of Kimi-K2.7-Code, 2026.
+> Base model: Moonshot AI, Kimi-K2.7-Code.

figures/field.png ADDED Viewed

Git LFS Details

SHA256: c080ed004cf16a76bba0e8ba1f18fd870c8fdd2d9082d9d43b5f986ede189519
Pointer size: 131 Bytes
Size of remote file: 211 kB

figures/field.svg ADDED Viewed

figures/memory.png ADDED Viewed

Git LFS Details

SHA256: a739b6d3459f280f65fe0b3f43e31c80287fd97e0d0df94c0dc704c9b554a2e8
Pointer size: 131 Bytes
Size of remote file: 225 kB

figures/memory.svg ADDED Viewed

figures/quality.png ADDED Viewed

Git LFS Details

SHA256: 0d551dd243d4a8aaa35c37fc9e8c90497ff2b392f08a6219d4a0fbe2831320f1
Pointer size: 131 Bytes
Size of remote file: 222 kB

figures/quality.svg ADDED Viewed

figures/recipe.png ADDED Viewed

Git LFS Details

SHA256: fac9d404d98e9604e0799889145558327e0308980577a8380c6d503289680c09
Pointer size: 131 Bytes
Size of remote file: 187 kB

figures/recipe.svg ADDED Viewed

model-00013-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ea42e9f62248ff91b09582f33628bb43a3e4650b2e976c6ac871333960354fcc
+size 5284823636

model-00014-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a229daeb9ac36635b69b0d00812863baf82fe59bbbba1f8068241e5077dee2d6
+size 5232151430

model-00015-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f28591ed7126d6314711570fad68613452fcb493acea787a904f41a921564c6a
+size 5232151455

model-00016-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:43bcf1b1e9c7b6d00936512116153c0f5fffaf9ff0c0c5a49b160e59896097a4
+size 5055990436

model-00017-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d81803932ee0e1f30c0cc7351461bd5e3534ed7d8e3138b826340c7476e949c8
+size 4932502386

model-00018-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0b29ecfbaa7b7bb9e6d2bfa08392dfdd644e6d27ab8e19875c063477d16ae05c
+size 5055990518

model-00019-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe4225e6bf435744b99c4f0246bb1649657cb154ff8ea31123966695372335
+size 5284823640

model-00020-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:50debd44d7fa0605df9b8793682b3d304f8d92ba26e4007abe5a43a18b98a3ab
+size 5232151470

model-00021-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dcea8b3ef03ace925117aca9f0719fde0e319ca83b614b8720f877910b5bee3d
+size 5232151472

model-00022-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5a3115ca7615412e25ec82401d4c8b1b1ca0acc407da69a8b350fc56ca809a
+size 5055990440

model-00023-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:95bd5b9160e184c8e1832f2caaa1067120ee93f7f5df8711cbf0aca5d633880c
+size 4932502386

model-00024-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1e63be15be7cd9fdc9d27b299046151335167c523f4d2c67d42b761818579d70
+size 5055990558

model-00025-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0cab96e1729bbabbb71d48d9b02e7e8f2f78e11d3843434ff1c45fd03b4ff6
+size 5284823640

model-00026-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:359905a87f926a0566563018918dffde421da374ee16a002eb13afd810bb1ddb
+size 5232151470

model-00027-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:decb39d2f6f8920fdeaca20b63c5e18e86aecd793c9749617b76d234c1d508cb
+size 5232151468

model-00028-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:730004c4d76d33b12cdb1f5beeab6883fa8ed186003fe401947b429e419dec96
+size 5055990468

model-00029-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf8cca9af4925f8667da6c19185bfbc350ca3bba2d6c15b6670cc41e16ec0d0
+size 4932502388

model-00030-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae23076e30d84135199976bd83dd7e4d3552026100edb358e348472761a5aa2
+size 3294382393

model-00031-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b06806c9fe71bd675641ee0e1ad9e6b3dba058ebf18a40cec44de83c5dfb7d
+size 4932502390

model-00032-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7ad039e7382783dca1c59c01bbff77d75e7f018c16d009eafe006cd1da9694
+size 5055990498

model-00033-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:23458f91b279968e7979a71fbec229e8f7c7965c036eff410d6c873e3b661c87
+size 5055990466

model-00034-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:adb643bd7128b9f5d033d91ae363567acc9a5628fb581c9e0620d9280fab6a90
+size 4932502390

model-00035-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:be15120fc12d597f37dca8c243092bd96f939f35ec46a2c041ab8321c3ca3baa
+size 5055990538

model-00036-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e3cd3b2f488d71736b82e368e77a47a7dbd92a409eb58581f4b4b0e7f28542
+size 5284823640

model-00037-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5768524eccbf3036bbaba1c822b4507f7fb59be41bebff2b73a030c8a1b78704
+size 5232151470

model-00038-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3ccde2e337aa1d7646e9fa898c7103679e176a402ae19833649e03c566c8e4ed
+size 5232151466

model-00039-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:72f5d4bcf4e435b125bcf9d5a7aef98509122d325b6543d6a19afa2eda5f46ce
+size 5055990450

model-00040-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:96449be2b28d77246ebd31f01d37316f3c63e79feea0575a871ff2ec7b61b15d
+size 4932502390

model-00041-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:55122bc35006a8dad1e6d00b679c8daca68dfa78cde1e4934b76841651389086
+size 5055990560

model-00042-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:000f131fea5cd91833047d5d4f0a01a9cf6721a12c3a64aee25fdb587aa3960b
+size 5284823640

model-00043-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:591ffaa707c9fd91a9f9902caeefcf0a5e68d0d1d0f982e4e9aa943ac801bc6a
+size 5232151464

model-00044-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:44c52d2f55bf43b4e22af651c5a1f753a044e6e2ed9a133d52862e6c9154b655
+size 5232151468

model-00045-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e1065f687ac0243ee022da95a7e74a09068f0a4acbd379325ed0b4fbd4b09393
+size 5055990442

model-00046-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f6b0db79bbae89a554c2b134459650a89fab85f90511840854d4ff4dfc2f62d6
+size 4932502388

model-00047-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e44519b9b33a40b60f6befe004243a3b98773ad8f6b23110e5606046df36a4
+size 5055990502

model-00048-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6d416e2479bdbf0802758ce5021f18ef9442b8ef9acc23028e91eee25569a440
+size 5284823640

model-00049-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e89791a080708474a783850eb09d5f3070da9a58a508357a99a3e7257412a367
+size 5232151454

model-00050-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:47704ea7811014b7e5e3a3b04f046bcdd7af4296092a944aa495ef6981a88896
+size 5232151470

model-00051-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:25f91a1ed227c1d534904463b7b68891dad883741b263def2e3f8d066758920a
+size 5055990508

model-00052-of-00093.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7480313f949a4d5dd8b9580099c73b4bf85a8ba14814b6f44dd070837984611a
+size 4932502390