Name override with rsLoRA(rank=128, alpha=256)

README.md

@@ -2,6 +2,7 @@
 base_model: meta-llama/Llama-3.2-3B-Instruct
 datasets:
 - KingNish/reasoning-base-20k
+- piotr25691/thea-name-overrides
 language:
 - en
 license: llama3.2
@@ -17,9 +18,9 @@ tags:
 
 # Model Description
 
-A work in progress reasoning Llama 3.2 3B model trained on reasoning data.
+A reasoning Llama 3.2 3B model trained on reasoning data.
 
-Since I used different training code, it is unknown whether it generates the same kind of reasoning.
+It has been trained using improved training code, and gives an improved performance.
 Here is what inference code you should use:
 ```py
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -43,7 +44,7 @@ reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.d
 reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
 reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
 
-# print("REASONING: " + reasoning_output)
+print("REASONING: " + reasoning_output)
 
 # Generate answer
 messages.append({"role": "reasoning", "content": reasoning_output})

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da0b2143eafde4be0eed4a8c5ec61dab7e481b844024334c2390bb8a68eab582
+oid sha256:b65251bf1b27f3fcc2fb19eaff33a962d7cda8155ecfd86dda8048280d92d752
 size 4965799096

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a3c2337805bf1fc483e8fea6dbc12631db07125178b50d251cde947ea457514
+oid sha256:4c7c2b9397064dec3da56323da1d07644410516aeb588ba3b1257366a8436efb
 size 1459729952

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051830f2f6c06d23b79bfeb1cb00c36ab32a29c2905e80e0b8e22148b654ec8b
-size 17210197
+oid sha256:12487b766b0b1584dcc5311824df327d5ea154939524790c643cdf2a3f6adf9f
+size 17209921