TeichAI/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: TeichAI/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-24 13:09:18 +08:00
commit 62809e5fc4
11 changed files with 151 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
.gitattributes vendored Normal file
View File

@@ -0,0 +1,43 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz 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
Nemotron-Cascade-8B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Nemotron-Cascade-8B-Thinking.F16.gguf filter=lfs diff=lfs merge=lfs -text
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.bf16.gguf filter=lfs diff=lfs merge=lfs -text
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text

3
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17ab3dd225ceabb5a824e4a33e33b217346d7b0f35bb34982768b2caf0b10c52
size 16388045056

3
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.iq4_nl.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f30070040b7f42ab48a6a616e008b9f1c2a74e768e64916653fdcff528bf0a69
size 4818790656

3
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.q3_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:acacd2f9e1e66261bfd4f410a3a4d06bb0359af972114806121eb47be545d96f
size 4124162304

3
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.q3_k_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9f5c7fa612d6c578e9b74e7a1df418f592aa1792f9f4f5da34cf6182cd4704ec
size 3769612544

3
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.q4_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b1dcb2f009662158a91de05d44b13a9e8120862759b0c16c1630894e65b4a6a
size 5027784960

3
Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-Distill.q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7363ed935f171a0ee3798649ad5f81b9cd4d1b77fccdf4f2bea1398370d8b7cc
size 8709519616

3
Nemotron-Cascade-8B-Thinking.F16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4479e5b1afe0ef87cada1826b2a60692e57b91324a10d20ac4b6f4f58c6cf6c
size 16388044224

3
Nemotron-Cascade-8B-Thinking.Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8e6a81d7a44184b562138da041db3ae6a1fca1b1a5168af79dfcefa32f0c7fd6
size 8709518784

14
README.md Normal file
View File

@@ -0,0 +1,14 @@
---
tags:
- gguf
- llama.cpp
- unsloth
base_model:
- TeichAI/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill
datasets:
- TeichAI/claude-4.5-opus-high-reasoning-250x
---
# Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-GGUF
This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).

70
config.json Normal file
View File

@@ -0,0 +1,70 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"torch_dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_length": 8192,
"max_position_embeddings": 32768,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.57.3",
"unsloth_version": "2025.12.5",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}