jekunz
/

smollm-135m-fineweb-swedish-from-scratch

Text Generation

text-generation-inference

Model card Files Files and versions Community

jekunz commited on Apr 30

Commit

4d3f4c7

·

verified ·

1 Parent(s): 2ef8ee1

Training in progress, step 25600

Files changed (3) hide show

config.json +2 -2
model.safetensors +2 -2
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -26,7 +26,7 @@
   "rope_scaling": null,
   "rope_theta": 100000,
   "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
   "transformers.js_config": {
     "kv_cache_dtype": {
       "fp16": "float16",

 {
+  "_name_or_path": "jekunz/smollm-135m-fineweb-swedish-from-scratch",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "rope_scaling": null,
   "rope_theta": 100000,
   "tie_word_embeddings": true,
+  "torch_dtype": "float32",
   "transformers.js_config": {
     "kv_cache_dtype": {
       "fp16": "float16",

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b607f9b9dd742e370737b990ecd06916445978437c03426cdeaecf5119249e14
-size 269060552

 version https://git-lfs.github.com/spec/v1
+oid sha256:470c630e1a1356b010a559c87b17cbb1b87e3cdddaedd84aac20d02b91827f2a
+size 538090408

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a723b432df48ba16d3c523795d8d13c126fd4f81e2d2fe909917de104e3db8
 size 5432

 version https://git-lfs.github.com/spec/v1
+oid sha256:09f761d6d63fbf3abca72e7092dd84025d7b9ff13444f5a15ceb16300e1e78e1
 size 5432