Training in progress, step 10
Browse files- adapter_model.bin +1 -1
- adapter_model.safetensors +1 -1
- config.json +47 -0
- training_args.bin +1 -1
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100733709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccb869c6079ec7536306832639a795091c006326b5ab8ef2fd13867485fb1d46
|
| 3 |
size 100733709
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100690288
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6ffefb060d7970fa838e97f91f7b3ee5afa3087327a2cac2f5d088a08fe68ad
|
| 3 |
size 100690288
|
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "tiiuae/falcon-rw-1b",
|
| 3 |
+
"alibi": true,
|
| 4 |
+
"apply_residual_connection_post_layernorm": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"FalconForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"auto_map": {
|
| 10 |
+
"AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
|
| 11 |
+
"AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
|
| 12 |
+
"AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
|
| 13 |
+
"AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
|
| 14 |
+
"AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
|
| 15 |
+
"AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
|
| 16 |
+
},
|
| 17 |
+
"bias": true,
|
| 18 |
+
"bos_token_id": 1,
|
| 19 |
+
"eos_token_id": 2,
|
| 20 |
+
"hidden_dropout": 0.0,
|
| 21 |
+
"hidden_size": 2048,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"layer_norm_epsilon": 1e-05,
|
| 24 |
+
"model_type": "falcon",
|
| 25 |
+
"multi_query": false,
|
| 26 |
+
"new_decoder_architecture": false,
|
| 27 |
+
"num_attention_heads": 32,
|
| 28 |
+
"num_hidden_layers": 24,
|
| 29 |
+
"num_kv_heads": 32,
|
| 30 |
+
"parallel_attn": false,
|
| 31 |
+
"quantization_config": {
|
| 32 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 33 |
+
"bnb_4bit_quant_type": "nf4",
|
| 34 |
+
"bnb_4bit_use_double_quant": true,
|
| 35 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 36 |
+
"llm_int8_has_fp16_weight": false,
|
| 37 |
+
"llm_int8_skip_modules": null,
|
| 38 |
+
"llm_int8_threshold": 6.0,
|
| 39 |
+
"load_in_4bit": true,
|
| 40 |
+
"load_in_8bit": false,
|
| 41 |
+
"quant_method": "bitsandbytes"
|
| 42 |
+
},
|
| 43 |
+
"torch_dtype": "bfloat16",
|
| 44 |
+
"transformers_version": "4.34.1",
|
| 45 |
+
"use_cache": false,
|
| 46 |
+
"vocab_size": 50304
|
| 47 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fed2eac68a79289fc50bbfb4e84510a8be0a8fcadc6310500b4e77e6b36adf7d
|
| 3 |
size 4091
|