added checkpoint 10/141

README.md

@@ -1,20 +0,0 @@
----
-datasets:
-  - ewof/koishi-instruct-metharme
----
-
-trained on commit 33b25a5 of the linked dataset (lamini)
-
-## Base Model
-
-native fine tune of togethercomputer/RedPajama-INCITE-Base-3B-v1
-
-## Prompting
-
-The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.
-
-The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input. The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.
-
-## Benchmarks
-
-![koishi_instruct_3b_v2_benchmarks.png](https://media.discordapp.net/attachments/1108805965421228052/1110025834699427840/tDcBmTvnLLSTdOUEKyHZMfra.png)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "togethercomputer/RedPajama-INCITE-Base-3B-v1",
+  "_name_or_path": "/mnt/gpt-storage/0x000011b/base-models/redpajama-3b-base-v1",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
@@ -19,7 +19,7 @@
   "rotary_pct": 1.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.30.0.dev0",
   "use_cache": true,
   "use_parallel_residual": false,
   "vocab_size": 50432

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.30.0.dev0"
+}

pytorch_model.bin → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eaf2c9bb1751e91459801cb2657e3af4ef0210dcaf2725a67227869999f84cd
-size 5686115609
+oid sha256:42b1578e648740e6e357ce72c7786506995d6040d3a871f40270be587694208d
+size 5686008384