lines/mini-chat/latest.json: lines/mini-chat/checkpoints/3848209k (step 96,979)

lines/mini-chat/README.md

@@ -16,7 +16,7 @@ datasets:
 
 # Nirca Mini 0.1 (chat)
 
-A chat continuation of Nirca Mini 0: the base model, trained on for one pass over chat data, from step 96,484 (the parent's step 96,467 at the fork) to 96,840; its base line is `latest.json` at the repo root.
+A chat continuation of Nirca Mini 0: the base model, trained on for one pass over chat data, from step 96,484 (the parent's step 96,467 at the fork) to 96,979; its base line is `latest.json` at the repo root.
 
 Nirca Mini is a small chat model trained from scratch, with ternary weights:
 its linear layers' weights are -1, 0 or +1, with a scale and a bias for each
@@ -32,7 +32,7 @@ deliberately derived from it: Nirca began as a port of mini-AGI to MLX.
 ➡️ **Try it in your browser (WebGPU):** https://tg-techie-agents.github.io/nirca-mini-webgpu/mini/
 
 This card is written by program from the checkpoint's own record, at step
-96,840 (3,843,511,753 tokens seen).
+96,979 (3,848,209,986 tokens seen).
 
 ## Model details
 
@@ -117,9 +117,9 @@ Each step is listed because the run's records show it was done:
 
 ## Training procedure
 
-- **Steps:** 96,840
-- **Tokens seen:** 3,843,511,753 (one token is one byte)
-- **Quantization-aware training:** from step 14,655 of 96,840, so for 99% of its 3,843,511,753 tokens
+- **Steps:** 96,979
+- **Tokens seen:** 3,848,209,986 (one token is one byte)
+- **Quantization-aware training:** from step 14,655 of 96,979, so for 99% of its 3,848,209,986 tokens
 - **Objective:** next-byte prediction; on chats, loss on the assistant's turns only
 - **Recurrence:** the number of passes is drawn per step during training, and
   the halting head learns when to stop

lines/mini-chat/latest.json

@@ -1,6 +1,6 @@
 {
  "name": "nirca-mini",
- "step": 96840,
+ "step": 96979,
  "quant": "ternary",
  "quant_scope": "all",
  "n_experts": 32,
@@ -40,17 +40,17 @@
   "pool_depth": 1,
   "pool_max": 32
  },
- "tokens": 3843511753,
- "checkpoint": "lines/mini-chat/checkpoints/3843511k/",
+ "tokens": 3848209986,
+ "checkpoint": "lines/mini-chat/checkpoints/3848209k/",
  "files": {
   "config.json": {
-   "url": "https://huggingface.co/nirca/nirca-mini/resolve/main/lines/mini-chat/checkpoints/3843511k/config.json",
-   "sha256": "3b82984b139d262d77461369250af3ae7d3970eb64670c99df82da778be73eaa",
+   "url": "https://huggingface.co/nirca/nirca-mini/resolve/main/lines/mini-chat/checkpoints/3848209k/config.json",
+   "sha256": "0f9593b590f4368fca918bc03a30307e6559f2deab25333e250b385d9690aeeb",
    "bytes": 873
   },
   "model.safetensors": {
-   "url": "https://huggingface.co/nirca/nirca-mini/resolve/main/lines/mini-chat/checkpoints/3843511k/model.safetensors",
-   "sha256": "393aa705db77592852962ff3afbdda61a8242cfb7bd07316ef9261fa40442922",
+   "url": "https://huggingface.co/nirca/nirca-mini/resolve/main/lines/mini-chat/checkpoints/3848209k/model.safetensors",
+   "sha256": "70412dba451f31a6f8b511c6f2250fb7d96f83307ea86789c80cb04343aeac43",
    "bytes": 32638048
   }
  }

lines/mini-chat/latest/config.json

@@ -1,7 +1,7 @@
 {
  "name": "nirca-mini",
- "step": 96840,
- "tokens": 3843511753,
+ "step": 96979,
+ "tokens": 3848209986,
  "quant": "ternary",
  "quant_scope": "all",
  "n_experts": 32,

lines/mini-chat/latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:393aa705db77592852962ff3afbdda61a8242cfb7bd07316ef9261fa40442922
+oid sha256:70412dba451f31a6f8b511c6f2250fb7d96f83307ea86789c80cb04343aeac43
 size 32638048