danielhanchen commited on
Commit
5e4ccdf
·
verified ·
1 Parent(s): 4953a38

Add files using upload-large-folder tool

Browse files
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. config.json +1 -9
  3. gpt-oss-20b-F32.gguf +3 -0
.gitattributes CHANGED
@@ -45,3 +45,4 @@ gpt-oss-20b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
45
  gpt-oss-20b-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
46
  gpt-oss-20b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
47
  gpt-oss-20b-UD-Q8_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 
 
45
  gpt-oss-20b-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
46
  gpt-oss-20b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
47
  gpt-oss-20b-UD-Q8_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
48
+ gpt-oss-20b-F32.gguf filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -47,15 +47,6 @@
47
  "num_local_experts": 32,
48
  "output_router_logits": false,
49
  "pad_token_id": 200017,
50
- "quantization_config": {
51
- "modules_to_not_convert": [
52
- "model.layers.*.self_attn",
53
- "model.layers.*.mlp.router",
54
- "model.embed_tokens",
55
- "lm_head"
56
- ],
57
- "quant_method": "mxfp4"
58
- },
59
  "rms_norm_eps": 1e-05,
60
  "rope_scaling": {
61
  "beta_fast": 32.0,
@@ -70,6 +61,7 @@
70
  "sliding_window": 128,
71
  "swiglu_limit": 7.0,
72
  "tie_word_embeddings": false,
 
73
  "transformers_version": "4.55.0",
74
  "unsloth_fixed": true,
75
  "use_cache": true,
 
47
  "num_local_experts": 32,
48
  "output_router_logits": false,
49
  "pad_token_id": 200017,
 
 
 
 
 
 
 
 
 
50
  "rms_norm_eps": 1e-05,
51
  "rope_scaling": {
52
  "beta_fast": 32.0,
 
61
  "sliding_window": 128,
62
  "swiglu_limit": 7.0,
63
  "tie_word_embeddings": false,
64
+ "torch_dtype": "bfloat16",
65
  "transformers_version": "4.55.0",
66
  "unsloth_fixed": true,
67
  "use_cache": true,
gpt-oss-20b-F32.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f0781fdd16a6db5cdadfa4aa1145851e6c708a430d883ba54b2f0645cd8b9a
3
+ size 41860886880