misterkuka
commited on
Commit
•
0a0c79a
1
Parent(s):
3f68bca
Upload model
Browse files- config.json +52 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cerebras/btlm-3b-8k-base",
|
3 |
+
"activation_function": "swiglu",
|
4 |
+
"architectures": [
|
5 |
+
"BTLMLMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "cerebras/btlm-3b-8k-base--configuration_btlm.BTLMConfig",
|
10 |
+
"AutoModel": "cerebras/btlm-3b-8k-base--modeling_btlm.BTLMModel",
|
11 |
+
"AutoModelForCausalLM": "cerebras/btlm-3b-8k-base--modeling_btlm.BTLMLMHeadModel",
|
12 |
+
"AutoModelForQuestionAnswering": "cerebras/btlm-3b-8k-base--modeling_btlm.BTLMForQuestionAnswering",
|
13 |
+
"AutoModelForSequenceClassification": "cerebras/btlm-3b-8k-base--modeling_btlm.BTLMForSequenceClassification",
|
14 |
+
"AutoModelForTokenClassification": "cerebras/btlm-3b-8k-base--modeling_btlm.BTLMForTokenClassification"
|
15 |
+
},
|
16 |
+
"bos_token_id": 50256,
|
17 |
+
"embd_pdrop": 0.0,
|
18 |
+
"eos_token_id": 50256,
|
19 |
+
"initializer_range": 0.073,
|
20 |
+
"layer_norm_epsilon": 1e-05,
|
21 |
+
"model_type": "btlm",
|
22 |
+
"mup_embeddings_scale": 14.6,
|
23 |
+
"mup_output_alpha": 2.22,
|
24 |
+
"mup_scale_qk_dot_by_d": true,
|
25 |
+
"mup_width_scale": 0.1,
|
26 |
+
"n_embd": 2560,
|
27 |
+
"n_head": 32,
|
28 |
+
"n_inner": 6826,
|
29 |
+
"n_layer": 32,
|
30 |
+
"n_positions": 8192,
|
31 |
+
"position_embedding_type": "alibi",
|
32 |
+
"quantization_config": {
|
33 |
+
"bnb_4bit_compute_dtype": "float32",
|
34 |
+
"bnb_4bit_quant_type": "fp4",
|
35 |
+
"bnb_4bit_use_double_quant": false,
|
36 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
37 |
+
"llm_int8_has_fp16_weight": false,
|
38 |
+
"llm_int8_skip_modules": null,
|
39 |
+
"llm_int8_threshold": 6.0,
|
40 |
+
"load_in_4bit": false,
|
41 |
+
"load_in_8bit": true,
|
42 |
+
"quant_method": "bitsandbytes"
|
43 |
+
},
|
44 |
+
"reorder_and_upcast_attn": false,
|
45 |
+
"resid_pdrop": 0.0,
|
46 |
+
"scale_attn_by_inverse_layer_idx": false,
|
47 |
+
"scale_attn_weights": true,
|
48 |
+
"torch_dtype": "float16",
|
49 |
+
"transformers_version": "4.32.1",
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 50257
|
52 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.32.1"
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dba6de6af2646951416ebc014ecdf6fa801efa28f96a6b176dd54e760614c299
|
3 |
+
size 2779674717
|