Add deepseek Mixtral-8x7B-Instruct-v0.1 nxd compiled model
Browse files- model.pt +3 -0
- neuron_config.json +172 -0
- weights/tp0_sharded_checkpoint.safetensors +3 -0
- weights/tp10_sharded_checkpoint.safetensors +3 -0
- weights/tp11_sharded_checkpoint.safetensors +3 -0
- weights/tp12_sharded_checkpoint.safetensors +3 -0
- weights/tp13_sharded_checkpoint.safetensors +3 -0
- weights/tp14_sharded_checkpoint.safetensors +3 -0
- weights/tp15_sharded_checkpoint.safetensors +3 -0
- weights/tp16_sharded_checkpoint.safetensors +3 -0
- weights/tp17_sharded_checkpoint.safetensors +3 -0
- weights/tp18_sharded_checkpoint.safetensors +3 -0
- weights/tp19_sharded_checkpoint.safetensors +3 -0
- weights/tp1_sharded_checkpoint.safetensors +3 -0
- weights/tp20_sharded_checkpoint.safetensors +3 -0
- weights/tp21_sharded_checkpoint.safetensors +3 -0
- weights/tp22_sharded_checkpoint.safetensors +3 -0
- weights/tp23_sharded_checkpoint.safetensors +3 -0
- weights/tp24_sharded_checkpoint.safetensors +3 -0
- weights/tp25_sharded_checkpoint.safetensors +3 -0
- weights/tp26_sharded_checkpoint.safetensors +3 -0
- weights/tp27_sharded_checkpoint.safetensors +3 -0
- weights/tp28_sharded_checkpoint.safetensors +3 -0
- weights/tp29_sharded_checkpoint.safetensors +3 -0
- weights/tp2_sharded_checkpoint.safetensors +3 -0
- weights/tp30_sharded_checkpoint.safetensors +3 -0
- weights/tp31_sharded_checkpoint.safetensors +3 -0
- weights/tp3_sharded_checkpoint.safetensors +3 -0
- weights/tp4_sharded_checkpoint.safetensors +3 -0
- weights/tp5_sharded_checkpoint.safetensors +3 -0
- weights/tp6_sharded_checkpoint.safetensors +3 -0
- weights/tp7_sharded_checkpoint.safetensors +3 -0
- weights/tp8_sharded_checkpoint.safetensors +3 -0
- weights/tp9_sharded_checkpoint.safetensors +3 -0
model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fbe1c5cdc6a02c03f98e5daf389ac7f47d2f341622a09efb039bd14c7aecf91
|
3 |
+
size 2702139
|
neuron_config.json
ADDED
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
3 |
+
"add_cross_attention": false,
|
4 |
+
"architectures": [
|
5 |
+
"MixtralForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"attribute_map": {},
|
9 |
+
"bad_words_ids": null,
|
10 |
+
"begin_suppress_tokens": null,
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"chunk_size_feed_forward": 0,
|
13 |
+
"cross_attention_hidden_size": null,
|
14 |
+
"decoder_start_token_id": null,
|
15 |
+
"diversity_penalty": 0.0,
|
16 |
+
"do_sample": false,
|
17 |
+
"early_stopping": false,
|
18 |
+
"encoder_no_repeat_ngram_size": 0,
|
19 |
+
"eos_token_id": 2,
|
20 |
+
"exponential_decay_length_penalty": null,
|
21 |
+
"finetuning_task": null,
|
22 |
+
"forced_bos_token_id": null,
|
23 |
+
"forced_eos_token_id": null,
|
24 |
+
"fused_spec_config": null,
|
25 |
+
"hidden_act": "silu",
|
26 |
+
"hidden_size": 4096,
|
27 |
+
"id2label": {
|
28 |
+
"0": "LABEL_0",
|
29 |
+
"1": "LABEL_1"
|
30 |
+
},
|
31 |
+
"initializer_range": 0.02,
|
32 |
+
"intermediate_size": 14336,
|
33 |
+
"is_decoder": false,
|
34 |
+
"is_encoder_decoder": false,
|
35 |
+
"label2id": {
|
36 |
+
"LABEL_0": 0,
|
37 |
+
"LABEL_1": 1
|
38 |
+
},
|
39 |
+
"length_penalty": 1.0,
|
40 |
+
"max_length": 20,
|
41 |
+
"max_position_embeddings": 32768,
|
42 |
+
"min_length": 0,
|
43 |
+
"model_type": "mixtral",
|
44 |
+
"neuron_config": {
|
45 |
+
"async_mode": false,
|
46 |
+
"attn_cls": "NeuronLlamaAttention",
|
47 |
+
"attn_kernel_enabled": false,
|
48 |
+
"batch_size": 1,
|
49 |
+
"bucket_n_active_tokens": false,
|
50 |
+
"buckets": [
|
51 |
+
128
|
52 |
+
],
|
53 |
+
"capacity_factor": null,
|
54 |
+
"cc_pipeline_tiling_factor": 2,
|
55 |
+
"context_encoding_buckets": null,
|
56 |
+
"ctx_batch_size": 1,
|
57 |
+
"enable_bucketing": true,
|
58 |
+
"enable_eagle_draft_input_norm": false,
|
59 |
+
"enable_eagle_speculation": false,
|
60 |
+
"enable_fused_speculation": false,
|
61 |
+
"ep_degree": 1,
|
62 |
+
"flash_decoding_enabled": false,
|
63 |
+
"fused_qkv": false,
|
64 |
+
"glu_mlp": true,
|
65 |
+
"is_chunked_prefill": false,
|
66 |
+
"is_continuous_batching": false,
|
67 |
+
"is_eagle_draft": false,
|
68 |
+
"is_medusa": false,
|
69 |
+
"is_paged_attention": false,
|
70 |
+
"kv_cache_quant": false,
|
71 |
+
"kv_cache_tiling": false,
|
72 |
+
"local_ranks_size": 32,
|
73 |
+
"logical_neuron_cores": 1,
|
74 |
+
"lora_config": null,
|
75 |
+
"max_batch_size": 1,
|
76 |
+
"max_context_length": 128,
|
77 |
+
"max_length": 128,
|
78 |
+
"max_new_tokens": null,
|
79 |
+
"medusa_speculation_length": 0,
|
80 |
+
"medusa_tree": null,
|
81 |
+
"mlp_kernel_enabled": false,
|
82 |
+
"mlp_kernel_fuse_residual_add": false,
|
83 |
+
"n_active_tokens": 128,
|
84 |
+
"n_positions": 128,
|
85 |
+
"num_medusa_heads": 0,
|
86 |
+
"on_cpu": false,
|
87 |
+
"on_device_sampling_config": {
|
88 |
+
"deterministic": false,
|
89 |
+
"do_sample": true,
|
90 |
+
"dynamic": true,
|
91 |
+
"global_topk": 64,
|
92 |
+
"on_device_sampling_config": true,
|
93 |
+
"temperature": 1.0,
|
94 |
+
"top_k": 1,
|
95 |
+
"top_p": 1.0
|
96 |
+
},
|
97 |
+
"output_logits": false,
|
98 |
+
"overrides_torch_dtype": true,
|
99 |
+
"pa_block_size": 128,
|
100 |
+
"pa_num_blocks": 1,
|
101 |
+
"padding_side": "right",
|
102 |
+
"pp_degree": 1,
|
103 |
+
"qk_layernorm": false,
|
104 |
+
"qkv_kernel_enabled": false,
|
105 |
+
"quantization_dtype": "int8",
|
106 |
+
"quantization_type": "per_tensor_symmetric",
|
107 |
+
"quantized": false,
|
108 |
+
"quantized_checkpoints_path": null,
|
109 |
+
"quantized_kernel_lower_bound": 1200.0,
|
110 |
+
"quantized_mlp_kernel_enabled": false,
|
111 |
+
"rmsnorm_quantize_kernel_enabled": false,
|
112 |
+
"rpl_reduce_dtype": "bfloat16",
|
113 |
+
"save_sharded_checkpoint": true,
|
114 |
+
"seq_len": 128,
|
115 |
+
"sequence_parallel_enabled": true,
|
116 |
+
"spec_batch_size": 1,
|
117 |
+
"speculation_length": 0,
|
118 |
+
"start_rank_id": 0,
|
119 |
+
"target": null,
|
120 |
+
"tkg_batch_size": 1,
|
121 |
+
"token_generation_buckets": null,
|
122 |
+
"torch_dtype": "bfloat16",
|
123 |
+
"tp_degree": 32,
|
124 |
+
"trace_tokengen_model": true,
|
125 |
+
"vocab_parallel": false,
|
126 |
+
"weights_to_skip_layout_optimization": [],
|
127 |
+
"world_size": 32
|
128 |
+
},
|
129 |
+
"no_repeat_ngram_size": 0,
|
130 |
+
"num_attention_heads": 32,
|
131 |
+
"num_beam_groups": 1,
|
132 |
+
"num_beams": 1,
|
133 |
+
"num_cores_per_group": 1,
|
134 |
+
"num_experts_per_tok": 2,
|
135 |
+
"num_hidden_layers": 32,
|
136 |
+
"num_key_value_heads": 8,
|
137 |
+
"num_local_experts": 8,
|
138 |
+
"num_return_sequences": 1,
|
139 |
+
"output_attentions": false,
|
140 |
+
"output_hidden_states": false,
|
141 |
+
"output_router_logits": false,
|
142 |
+
"output_scores": false,
|
143 |
+
"pad_token_id": null,
|
144 |
+
"prefix": null,
|
145 |
+
"problem_type": null,
|
146 |
+
"pruned_heads": {},
|
147 |
+
"remove_invalid_values": false,
|
148 |
+
"repetition_penalty": 1.0,
|
149 |
+
"return_dict": true,
|
150 |
+
"return_dict_in_generate": false,
|
151 |
+
"rms_norm_eps": 1e-05,
|
152 |
+
"rope_theta": 1000000.0,
|
153 |
+
"router_aux_loss_coef": 0.02,
|
154 |
+
"router_jitter_noise": 0.0,
|
155 |
+
"sep_token_id": null,
|
156 |
+
"sliding_window": null,
|
157 |
+
"suppress_tokens": null,
|
158 |
+
"task_specific_params": null,
|
159 |
+
"temperature": 1.0,
|
160 |
+
"tf_legacy_loss": false,
|
161 |
+
"tie_encoder_decoder": false,
|
162 |
+
"tie_word_embeddings": false,
|
163 |
+
"tokenizer_class": null,
|
164 |
+
"top_k": 50,
|
165 |
+
"top_p": 1.0,
|
166 |
+
"torchscript": false,
|
167 |
+
"transformers_version": "4.45.2",
|
168 |
+
"typical_p": 1.0,
|
169 |
+
"use_bfloat16": false,
|
170 |
+
"use_cache": true,
|
171 |
+
"vocab_size": 32000
|
172 |
+
}
|
weights/tp0_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2cf265cdf4253ee3fc6916220aa7ed8b5f96c362e769c437b05255b2ea1dc4e
|
3 |
+
size 2971838096
|
weights/tp10_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55afa9bd733e6d69aeabd4b32846c17b8dcd43a47ad9e93507b48fd6af0c5b0d
|
3 |
+
size 2971838096
|
weights/tp11_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f987d98f99cd9d0edde0214b73bf4c656f8ffce83e2f158e7e10aecea4a2b77
|
3 |
+
size 2971838096
|
weights/tp12_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a74ef7f60564af5d5c105660f7963ff6340dec8b856f098446d627a1290c4242
|
3 |
+
size 2971838096
|
weights/tp13_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b4c64912d9281a408a34cf36387a084a2ac54a3ebfd2385957c376bbd46ca78
|
3 |
+
size 2971838096
|
weights/tp14_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6d86f1bcdfe5e504db87ed47b177be1e454ee0b9c17a95e3a0ab9967dcd7d88
|
3 |
+
size 2971838096
|
weights/tp15_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c538abec3cf7d54baea8eb695261ae8056a47284a3d03e35938b823d704427a
|
3 |
+
size 2971838096
|
weights/tp16_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23de7c3117c135222417d052122a80ac2b30c2a69c1b9fb89217708747e8c8a3
|
3 |
+
size 2971838096
|
weights/tp17_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da22b30c4c0a6601ef857bc0f9498128f47e821cc94084951a828407891e6b10
|
3 |
+
size 2971838096
|
weights/tp18_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b75a62706233c5f45bf22dbf222bbb75fce835a4e8f3214307dfbbe4d2d696d8
|
3 |
+
size 2971838096
|
weights/tp19_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7a8d77ff435def2fb3e661370eff9988e0caf752b5e93e450dcd3c879b11d6f
|
3 |
+
size 2971838096
|
weights/tp1_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6710749f189000e9c6ce91c76d3db1942a71f7e43b28cb8fafae0ba1ec4a7baa
|
3 |
+
size 2971838096
|
weights/tp20_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0301b6c3be78d96c5cccb8af34706f3e86d17baae04469ec488ce679c44432ee
|
3 |
+
size 2971838096
|
weights/tp21_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46f050da97397e6113554e1a08cc88130d5a5cb3e39a0703aa22c4254381f4c5
|
3 |
+
size 2971838096
|
weights/tp22_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50e9acb37baea058605770fcbfa3b41617debc941810d2bb18d8451a92de55db
|
3 |
+
size 2971838096
|
weights/tp23_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:996243d38c53779fb4a1e681fd5a7f561ded43b634a6b4ff488de3ec1af8eae5
|
3 |
+
size 2971838096
|
weights/tp24_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7db4c0b89eba6dd1288d2c1bdb69f4788ed3007053fff68fe272436d74af8052
|
3 |
+
size 2971838096
|
weights/tp25_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c2687762476e01d6a85cb1bf170fc6da77a1935866611ce9677efcf7149b23c
|
3 |
+
size 2971838096
|
weights/tp26_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38d0a1671ecf6dc4b228c54593f117df4649a1d41f63bbf359d0fae793214960
|
3 |
+
size 2971838096
|
weights/tp27_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c6fc961285a0f27c2f2d3a867cb22116684d3e5171cfb7023eb01fc6fd68bbd
|
3 |
+
size 2971838096
|
weights/tp28_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54f1060a621de9ecd3499129a974ec3c1774b06d8e729636c840096acf24125d
|
3 |
+
size 2971838096
|
weights/tp29_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05dcce702c245aad0d58aecc04db20394a46de565c29b407eb0a18e1e261ea18
|
3 |
+
size 2971838096
|
weights/tp2_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7835b75441bcd69da8571c967968b2b074a533a4b25b27ab3876201147baf666
|
3 |
+
size 2971838096
|
weights/tp30_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fc12818dd8c972c53b0c9b0da1d45f1f18dffcd591e0f8b33172daf3319dc01
|
3 |
+
size 2971838096
|
weights/tp31_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42f404a33e9e8b14c395e539edc9ff245a8e5fd7a4e4ca73dfdec9247c9268c1
|
3 |
+
size 2971838096
|
weights/tp3_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ddd5cb644b1ca6b566e64f2f99f66912cf5c5720be7ee0915e2c08a3715c316
|
3 |
+
size 2971838096
|
weights/tp4_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84e2831df9f9457d3c9a9b63ad8e14c951473cf877ada24d09e406b3f9e4ba35
|
3 |
+
size 2971838096
|
weights/tp5_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44bed47612bb8dde0c05e1d758d0f0c1e7a0e867ab0201b45301dbe2bfaf5bc3
|
3 |
+
size 2971838096
|
weights/tp6_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e878130354cf82625863bbd7e74e6004703f85435951d05d8a93526f9c4bc7fa
|
3 |
+
size 2971838096
|
weights/tp7_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f21f613c2648788275d091ada9fe92309e143f300c52655bbb535a3e0a47dba1
|
3 |
+
size 2971838096
|
weights/tp8_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d88ef71b2e46675bc393be38fa20c47f1fb27da18b8efe30845f1164cb59148
|
3 |
+
size 2971838096
|
weights/tp9_sharded_checkpoint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b848b06d3fd9ffe955e61b162f6f663ba89fbe790524b5eeb5e451801528e85e
|
3 |
+
size 2971838096
|