Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- config.json +89 -0
- gpt-oss-120b-F16.gguf +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 |
+
gpt-oss-120b-F16.gguf filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"GptOssForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": true,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"eos_token_id": 200002,
|
8 |
+
"experts_per_token": 4,
|
9 |
+
"head_dim": 64,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2880,
|
12 |
+
"initial_context_length": 4096,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 2880,
|
15 |
+
"layer_types": [
|
16 |
+
"sliding_attention",
|
17 |
+
"full_attention",
|
18 |
+
"sliding_attention",
|
19 |
+
"full_attention",
|
20 |
+
"sliding_attention",
|
21 |
+
"full_attention",
|
22 |
+
"sliding_attention",
|
23 |
+
"full_attention",
|
24 |
+
"sliding_attention",
|
25 |
+
"full_attention",
|
26 |
+
"sliding_attention",
|
27 |
+
"full_attention",
|
28 |
+
"sliding_attention",
|
29 |
+
"full_attention",
|
30 |
+
"sliding_attention",
|
31 |
+
"full_attention",
|
32 |
+
"sliding_attention",
|
33 |
+
"full_attention",
|
34 |
+
"sliding_attention",
|
35 |
+
"full_attention",
|
36 |
+
"sliding_attention",
|
37 |
+
"full_attention",
|
38 |
+
"sliding_attention",
|
39 |
+
"full_attention",
|
40 |
+
"sliding_attention",
|
41 |
+
"full_attention",
|
42 |
+
"sliding_attention",
|
43 |
+
"full_attention",
|
44 |
+
"sliding_attention",
|
45 |
+
"full_attention",
|
46 |
+
"sliding_attention",
|
47 |
+
"full_attention",
|
48 |
+
"sliding_attention",
|
49 |
+
"full_attention",
|
50 |
+
"sliding_attention",
|
51 |
+
"full_attention"
|
52 |
+
],
|
53 |
+
"max_position_embeddings": 131072,
|
54 |
+
"model_type": "gpt_oss",
|
55 |
+
"num_attention_heads": 64,
|
56 |
+
"num_experts_per_tok": 4,
|
57 |
+
"num_hidden_layers": 36,
|
58 |
+
"num_key_value_heads": 8,
|
59 |
+
"num_local_experts": 128,
|
60 |
+
"output_router_logits": false,
|
61 |
+
"pad_token_id": 200017,
|
62 |
+
"quantization_config": {
|
63 |
+
"modules_to_not_convert": [
|
64 |
+
"model.layers.*.self_attn",
|
65 |
+
"model.layers.*.mlp.router",
|
66 |
+
"model.embed_tokens",
|
67 |
+
"lm_head"
|
68 |
+
],
|
69 |
+
"quant_method": "mxfp4"
|
70 |
+
},
|
71 |
+
"rms_norm_eps": 1e-05,
|
72 |
+
"rope_scaling": {
|
73 |
+
"beta_fast": 32.0,
|
74 |
+
"beta_slow": 1.0,
|
75 |
+
"factor": 32.0,
|
76 |
+
"original_max_position_embeddings": 4096,
|
77 |
+
"rope_type": "yarn",
|
78 |
+
"truncate": false
|
79 |
+
},
|
80 |
+
"rope_theta": 150000,
|
81 |
+
"router_aux_loss_coef": 0.9,
|
82 |
+
"sliding_window": 128,
|
83 |
+
"swiglu_limit": 7.0,
|
84 |
+
"tie_word_embeddings": false,
|
85 |
+
"transformers_version": "4.56.0.dev0",
|
86 |
+
"unsloth_fixed": true,
|
87 |
+
"use_cache": true,
|
88 |
+
"vocab_size": 201088
|
89 |
+
}
|
gpt-oss-120b-F16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74aad2b5c69ed542ec998128e61d1c82fe181e05ef461af18d6356ecb4c4598b
|
3 |
+
size 65369015872
|