Hugging Face's logo

CortexLM
/
test

Text Generation
Transformers
Safetensors
glm_moe_dsa
nvidia
nvfp4
quantized
Mixture of Experts
modelopt
glm
8-bit precision
Model card Files
xet
 Community
echoctx commited on
Commit
cdfb602
·
verified ·
1 Parent(s): 7543e6d

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. README.md +76 -0
  3. config.json +174 -0
  4. generation_config.json +12 -0
  5. hf_quant_config.json +14 -0
  6. model-00001-of-00085.safetensors +3 -0
  7. model-00003-of-00085.safetensors +3 -0
  8. model-00006-of-00085.safetensors +3 -0
  9. model-00007-of-00085.safetensors +3 -0
  10. model-00008-of-00085.safetensors +3 -0
  11. model-00009-of-00085.safetensors +3 -0
  12. model-00012-of-00085.safetensors +3 -0
  13. model-00014-of-00085.safetensors +3 -0
  14. model-00016-of-00085.safetensors +3 -0
  15. model-00019-of-00085.safetensors +3 -0
  16. model-00022-of-00085.safetensors +3 -0
  17. model-00024-of-00085.safetensors +3 -0
  18. model-00026-of-00085.safetensors +3 -0
  19. model-00028-of-00085.safetensors +3 -0
  20. model-00029-of-00085.safetensors +3 -0
  21. model-00030-of-00085.safetensors +3 -0
  22. model-00035-of-00085.safetensors +3 -0
  23. model-00036-of-00085.safetensors +3 -0
  24. model-00037-of-00085.safetensors +3 -0
  25. model-00040-of-00085.safetensors +3 -0
  26. model-00042-of-00085.safetensors +3 -0
  27. model-00044-of-00085.safetensors +3 -0
  28. model-00045-of-00085.safetensors +3 -0
  29. model-00051-of-00085.safetensors +3 -0
  30. model-00052-of-00085.safetensors +3 -0
  31. model-00055-of-00085.safetensors +3 -0
  32. model-00057-of-00085.safetensors +3 -0
  33. model-00060-of-00085.safetensors +3 -0
  34. model-00061-of-00085.safetensors +3 -0
  35. model-00063-of-00085.safetensors +3 -0
  36. model-00064-of-00085.safetensors +3 -0
  37. model-00065-of-00085.safetensors +3 -0
  38. model-00067-of-00085.safetensors +3 -0
  39. model-00068-of-00085.safetensors +3 -0
  40. model-00070-of-00085.safetensors +3 -0
  41. model-00074-of-00085.safetensors +3 -0
  42. model-00076-of-00085.safetensors +3 -0
  43. model-00078-of-00085.safetensors +3 -0
  44. model-00079-of-00085.safetensors +3 -0
  45. model-00080-of-00085.safetensors +3 -0
  46. model-00081-of-00085.safetensors +3 -0
  47. model-00082-of-00085.safetensors +3 -0
  48. model-00083-of-00085.safetensors +3 -0
  49. model-00084-of-00085.safetensors +3 -0
  50. tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: zai-org/GLM-5.1
4
+ tags:
5
+ - nvidia
6
+ - nvfp4
7
+ - quantized
8
+ - moe
9
+ - modelopt
10
+ - glm
11
+ library_name: transformers
12
+ pipeline_tag: text-generation
13
+ ---
14
+
15
+ # CortexLM/GLM-5.1-NVFP4-MTP
16
+
17
+ NVFP4 quantized version of [zai-org/GLM-5.1](https://huggingface.co/zai-org/GLM-5.1), a 754B parameter Mixture-of-Experts language model with 256 routed experts per layer.
18
+
19
+ Quantized using [NVIDIA Model Optimizer (modelopt)](https://github.com/NVIDIA/Model-Optimizer) with full activation calibration on all 58,459 linear modules including every individual routed expert.
20
+
21
+ ## Model Details
22
+
23
+ | | |
24
+ |---|---|
25
+ | **Base model** | [zai-org/GLM-5.1](https://huggingface.co/zai-org/GLM-5.1) |
26
+ | **Architecture** | GlmMoeDsaForCausalLM (754B MoE) |
27
+ | **Layers** | 78 transformer layers + 1 MTP layer |
28
+ | **Experts** | 256 routed + 1 shared per MoE layer (layers 3-77) |
29
+ | **Hidden size** | 6144 |
30
+ | **Context length** | 202,752 tokens |
31
+ | **Quantization** | NVFP4 (4-bit float weights, FP8 block scales, group size 16) |
32
+ | **KV cache** | FP8 quantized |
33
+ | **MTP layer** | BF16 (stored separately in `mtp.safetensors`) |
34
+ | **Total size** | ~441 GB (vs 1.4 TB BF16 original) |
35
+
36
+ ## Quantization Details
37
+
38
+ This model was quantized using NVIDIA's official [Model Optimizer](https://github.com/NVIDIA/Model-Optimizer) (`modelopt`) NVFP4 pipeline with proper per-expert calibration:
39
+
40
+ - **Quantization format**: NVFP4 -- 4-bit floating point with FP8 per-block scaling factors (`float8_e4m3fn`) and a global FP32 `weight_scale_2`, block size of 16
41
+ - **Calibration**: 256 samples from [cnn_dailymail](https://huggingface.co/datasets/cnn_dailymail) and [nvidia/Nemotron-Post-Training-Dataset-v2](https://huggingface.co/datasets/nvidia/Nemotron-Post-Training-Dataset-v2) (chat, code, math, stem splits), sequence length 2048
42
+ - **Quantized modules**: 58,459 `nn.Linear` modules, including all 256 routed experts per layer individually quantized with calibrated `input_scale` (activation statistics)
43
+ - **KV cache**: FP8 cast quantization on all attention layers
44
+ - **Excluded**: `lm_head` (kept in BF16)
45
+ - **MTP**: Multi-Token Prediction layer (layer 78) kept in BF16 as a separate `mtp.safetensors` file (19.9 GB)
46
+ - **Hardware**: 8x NVIDIA B300 SXM6 275GB GPUs
47
+ - **Calibration time**: ~21 minutes
48
+ - **modelopt version**: 0.42.0.dev (from source, April 2026)
49
+ - **transformers version**: 5.5.0
50
+
51
+ ### Weight format
52
+
53
+ Each quantized linear layer is stored as:
54
+ - `weight`: `uint8` (two FP4 values packed per byte)
55
+ - `weight_scale`: `float8_e4m3fn` (per-block FP8 scale, one per 16 elements)
56
+ - `weight_scale_2`: `float32` scalar (global per-tensor scale)
57
+ - `input_scale`: `float32` scalar (calibrated activation scale, where applicable)
58
+
59
+ ## Usage
60
+
61
+ This checkpoint is designed for use with inference engines that support the NVFP4 format, such as [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) and [vLLM](https://github.com/vllm-project/vllm) with modelopt backend.
62
+
63
+ ## Files
64
+
65
+ - 85 model shards (`model-00001-of-00085.safetensors` to `model-00085-of-00085.safetensors`) -- NVFP4 quantized layers 0-77
66
+ - `mtp.safetensors` -- BF16 Multi-Token Prediction layer (layer 78, 791 keys, 19.9 GB)
67
+ - `model.safetensors.index.json` -- shard index mapping
68
+ - `config.json` -- model configuration with `quantization_config`
69
+ - `hf_quant_config.json` -- NVFP4 quantization metadata
70
+ - `tokenizer.json`, `tokenizer_config.json` -- tokenizer files
71
+ - `generation_config.json` -- generation defaults
72
+
73
+ ## Acknowledgements
74
+
75
+ - Base model by [ZhipuAI](https://huggingface.co/zai-org)
76
+ - Quantization tooling by [NVIDIA Model Optimizer](https://github.com/NVIDIA/Model-Optimizer)
config.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GlmMoeDsaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": [
10
+ 154820,
11
+ 154827,
12
+ 154829
13
+ ],
14
+ "ep_size": 1,
15
+ "first_k_dense_replace": 3,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 6144,
18
+ "index_head_dim": 128,
19
+ "index_n_heads": 32,
20
+ "index_topk": 2048,
21
+ "indexer_rope_interleave": true,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 12288,
24
+ "kv_lora_rank": 512,
25
+ "max_position_embeddings": 202752,
26
+ "mlp_layer_types": [
27
+ "dense",
28
+ "dense",
29
+ "dense",
30
+ "sparse",
31
+ "sparse",
32
+ "sparse",
33
+ "sparse",
34
+ "sparse",
35
+ "sparse",
36
+ "sparse",
37
+ "sparse",
38
+ "sparse",
39
+ "sparse",
40
+ "sparse",
41
+ "sparse",
42
+ "sparse",
43
+ "sparse",
44
+ "sparse",
45
+ "sparse",
46
+ "sparse",
47
+ "sparse",
48
+ "sparse",
49
+ "sparse",
50
+ "sparse",
51
+ "sparse",
52
+ "sparse",
53
+ "sparse",
54
+ "sparse",
55
+ "sparse",
56
+ "sparse",
57
+ "sparse",
58
+ "sparse",
59
+ "sparse",
60
+ "sparse",
61
+ "sparse",
62
+ "sparse",
63
+ "sparse",
64
+ "sparse",
65
+ "sparse",
66
+ "sparse",
67
+ "sparse",
68
+ "sparse",
69
+ "sparse",
70
+ "sparse",
71
+ "sparse",
72
+ "sparse",
73
+ "sparse",
74
+ "sparse",
75
+ "sparse",
76
+ "sparse",
77
+ "sparse",
78
+ "sparse",
79
+ "sparse",
80
+ "sparse",
81
+ "sparse",
82
+ "sparse",
83
+ "sparse",
84
+ "sparse",
85
+ "sparse",
86
+ "sparse",
87
+ "sparse",
88
+ "sparse",
89
+ "sparse",
90
+ "sparse",
91
+ "sparse",
92
+ "sparse",
93
+ "sparse",
94
+ "sparse",
95
+ "sparse",
96
+ "sparse",
97
+ "sparse",
98
+ "sparse",
99
+ "sparse",
100
+ "sparse",
101
+ "sparse",
102
+ "sparse",
103
+ "sparse",
104
+ "sparse"
105
+ ],
106
+ "model_type": "glm_moe_dsa",
107
+ "moe_intermediate_size": 2048,
108
+ "moe_layer_freq": 1,
109
+ "n_group": 1,
110
+ "n_routed_experts": 256,
111
+ "n_shared_experts": 1,
112
+ "norm_topk_prob": true,
113
+ "num_attention_heads": 64,
114
+ "num_experts_per_tok": 8,
115
+ "num_hidden_layers": 78,
116
+ "num_key_value_heads": 64,
117
+ "num_nextn_predict_layers": 1,
118
+ "pad_token_id": 154820,
119
+ "pretraining_tp": 1,
120
+ "q_lora_rank": 2048,
121
+ "qk_head_dim": 256,
122
+ "qk_nope_head_dim": 192,
123
+ "qk_rope_head_dim": 64,
124
+ "rms_norm_eps": 1e-05,
125
+ "rope_interleave": true,
126
+ "rope_parameters": {
127
+ "rope_theta": 1000000,
128
+ "rope_type": "default"
129
+ },
130
+ "routed_scaling_factor": 2.5,
131
+ "scoring_func": "sigmoid",
132
+ "tie_word_embeddings": false,
133
+ "topk_group": 1,
134
+ "topk_method": "noaux_tc",
135
+ "transformers_version": "5.5.0",
136
+ "use_cache": true,
137
+ "v_head_dim": 256,
138
+ "vocab_size": 154880,
139
+ "quantization_config": {
140
+ "config_groups": {
141
+ "group_0": {
142
+ "input_activations": {
143
+ "dynamic": false,
144
+ "num_bits": 4,
145
+ "type": "float",
146
+ "group_size": 16
147
+ },
148
+ "weights": {
149
+ "dynamic": false,
150
+ "num_bits": 4,
151
+ "type": "float",
152
+ "group_size": 16
153
+ },
154
+ "targets": [
155
+ "Linear"
156
+ ]
157
+ }
158
+ },
159
+ "ignore": [
160
+ "lm_head"
161
+ ],
162
+ "quant_algo": "NVFP4",
163
+ "kv_cache_scheme": {
164
+ "dynamic": false,
165
+ "num_bits": 8,
166
+ "type": "float"
167
+ },
168
+ "producer": {
169
+ "name": "modelopt",
170
+ "version": "0.0.1.dev1+g5dc17dfd1.d20260407"
171
+ },
172
+ "quant_method": "modelopt"
173
+ }
174
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 154820,
5
+ 154827,
6
+ 154829
7
+ ],
8
+ "pad_token_id": 154820,
9
+ "temperature": 1.0,
10
+ "top_p": 0.95,
11
+ "transformers_version": "5.4.0"
12
+ }
hf_quant_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "producer": {
3
+ "name": "modelopt",
4
+ "version": "0.0.1.dev1+g5dc17dfd1.d20260407"
5
+ },
6
+ "quantization": {
7
+ "quant_algo": "NVFP4",
8
+ "kv_cache_quant_algo": "FP8",
9
+ "group_size": 16,
10
+ "exclude_modules": [
11
+ "lm_head"
12
+ ]
13
+ }
14
+ }
model-00001-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb7f509b7f0c5b841d3b7c39d47e0c9cde54d8a990877deba45c1412afb6db4
3
+ size 4999575736
model-00003-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1367c56079a0e47472f213643eb37032d4960298d8d73181ab895b5404a3a7d
3
+ size 4999506536
model-00006-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5156f32255d87f214611a3830f07ce283ae9201e4121560abe2aec9ed89f282e
3
+ size 4997327120
model-00007-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f527633e1c4d01e99de355930cb2ddaf031a6ff7514313ea0da6a89170c6ab
3
+ size 4999507056
model-00008-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e1f8adf000a74d5b7c64724526fcbcd97a76fe4b073b259416e4e82dc2fefe
3
+ size 4999505068
model-00009-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1999bf42c9b756d0cfc3f30083b46453baced237b67320a2279d48ff4c090d99
3
+ size 4999499836
model-00012-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58aa0c1ede39f29c9b97cc9dadae4987ae79501d808b1a4d184e9108ef6f7d5b
3
+ size 4999482268
model-00014-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc17d55f89dec89daa8cf220c5a2fa8fc4b3adf10fb60efe2d22e1f250381f05
3
+ size 4999489336
model-00016-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a15553828325040c1ee1749c64e1e28fe25567b337a1ef3ca5070ba5a12c434
3
+ size 4997301720
model-00019-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98379a62ab06349dc904647ad67ce405e1fc4a5d641112976eb739e0e65920c6
3
+ size 4999468960
model-00022-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c028c69e425ae4da9a5d810504ece10f37e9b11d8ed3524c11ea49ebc7624b
3
+ size 4999465028
model-00024-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7bfac22237d6b894c481a5e42a178a42891f6843a9468b247755ac9e1a5bb4b
3
+ size 4999466220
model-00026-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5640c129d9245d127714bfcb2a1aeb5627762a06107c027578786a8c41e146e
3
+ size 4997286104
model-00028-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f32eba103ec07dad22c8396f72e63f54fc32873d1ec5a1c671c1c6e301a08e1
3
+ size 4999470076
model-00029-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9118a7b7594bbd58c7dc0778196f67482e0a3ce1bb0c8ef72491c178dfc95e
3
+ size 4999469424
model-00030-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40407806babbdd63a0d9bacaa2fac8e904fbdf84dc446b4c5aa610aa95dc7680
3
+ size 4999464644
model-00035-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286e3628620ad0c5353b25e7eadb104d3594fe826d68402d3e392dc720ad7f08
3
+ size 4958797740
model-00036-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b45ef2085482defb217c894de566afa3ad97cf9a8cffa549ef88a6138a142b
3
+ size 4995468148
model-00037-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c78128b323fd9f3bd26f6187908204e934260a36582ff2886e512b4509ab7ee8
3
+ size 4999456216
model-00040-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8753dc763c93624cdbd95629da26aefabf949479c12646fe4e35d5efa7925e4b
3
+ size 4999454044
model-00042-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b504eaf7f0c0a306a67936047a2167a72f7b53cb187889db9973c3527aa32d7b
3
+ size 4999457936
model-00044-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a05336cc25dd8fa1d8b55f2da663642ab4dcf4e36cc25af2a7f1a16b6ad32a43
3
+ size 4999462320
model-00045-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74cca9c32cf6aa04f91aeb8788a828805908501bae863c71a74e2ba3018b83e6
3
+ size 4999635488
model-00051-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d7ed232958e9530e884e43770f2f05a0ce2f50511df86bfa70baf040ceb41f
3
+ size 4999462704
model-00052-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78bb941fba46577d93bee6d875040085583e9e60b60a506eb4ad1dc9675f9c87
3
+ size 4999461304
model-00055-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94bc426b001bd74e6e603ae0ae0acb2868ff0181256d6cc3beb10d060ab341ac
3
+ size 4997280008
model-00057-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeff47e54102e6902c4d2ec24b40c59208c656db59d4c81f0a96f2c6f8217630
3
+ size 4999463932
model-00060-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a597c3beb4a96b763d185ed3361766605ac476c60ed32351fc881a4f448f984
3
+ size 4999461924
model-00061-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c136378840d5731f500630be9c456ee5de5b53565e1e5475370e7db8dcc0dd
3
+ size 4999460488
model-00063-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bafa6f7ffa649825bca670cb30792561e94565a72ad7d558f1ea2fbfe44e6608
3
+ size 4999460276
model-00064-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb55d1759959aa48fc9dde7101eaaa251d8b1c478d6b432695ed66607510b05c
3
+ size 4999460784
model-00065-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9af318aa69404d967102fa7ec506014e12ece81a913a72795f0f82da43024c
3
+ size 4997280440
model-00067-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd8d6bb7e2aa9475ed2fd404a66582c06e328afd8edc42638d5127ebd200f9f
3
+ size 4999462496
model-00068-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0d618b43e3c9675bc0908efb8fc5f8c1260a7c03b66bed27fd459be850e443
3
+ size 4999465208
model-00070-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500f99068f1393bebdc675ac2f396f8ef13e78f8a44c163e5f8ae78a34ac23dd
3
+ size 4999459576
model-00074-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d8bb4d2c1f4158625e5c9627023fc989669091a22e63a317a9c7c30a27e336
3
+ size 4999463464
model-00076-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8deef5978ca7a367536eb08365f9c56f3c9731101e62546910f8348d27db28c5
3
+ size 4999458732
model-00078-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8876ea722058351980502738475600111e3fab2aa894e6e729317a895c32590b
3
+ size 4999460680
model-00079-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8940a8c70a1ff20a5cb2330bf5b763e98134afc6b1070650b096d9924df0a47c
3
+ size 4999463284
model-00080-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f91f5a61ef7343849c157e0d36e4cb23e4b7e63d6b94e6f40dc7d8143946e0f2
3
+ size 4999461600
model-00081-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56049d50b2ac490f83d0adacfa3db6e00739f0a321e22ba2c230ecb57cad1b3b
3
+ size 4999458340
model-00082-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41cd87cfbf73f0745451e91cdd27f3680a71d0356fef14a22067206cc7efb12a
3
+ size 4999458772
model-00083-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdad5e268e84b774f5340e920029c70f88b88798be890f45f1b16dde6b49a0c0
3
+ size 4999459488
model-00084-of-00085.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14433c686404beedadc58fdbc21af6eeb5dcf297f028fec04642fd8c58a144d8
3
+ size 4582843272
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
3
+ size 20217442