Upload 6 files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,32 @@
----
-license: openrail
----
+# BLOOM, a version for Petals
+
+This model is a version of [bigscience/bloom](https://huggingface.co/bigscience/bloom)
+post-processed to be run at home using the [Petals](https://github.com/bigscience-workshop/petals#readme) swarm.
+
+Please check out:
+
+- The [original model card](https://huggingface.co/bigscience/bloom)
+  to learn about the model's capabilities, specifications, and terms of use.
+- The [Petals repository](https://github.com/bigscience-workshop/petals#readme)
+  to learn how to install Petals and run this model over the Petals swarm.
+
+We provide minimal code examples below.
+
+## Using the model
+
+```python
+from petals import DistributedBloomForCausalLM
+
+model = DistributedBloomForCausalLM.from_pretrained("bigscience/bloom-petals")
+# Embeddings & prompts are on your device, BLOOM blocks are distributed across the Internet
+
+inputs = tokenizer("A cat sat", return_tensors="pt")["input_ids"]
+outputs = model.generate(inputs, max_new_tokens=5)
+print(tokenizer.decode(outputs[0]))  # A cat sat on a mat...
+```
+
+## Serving the model blocks
+
+```bash
+python -m petals.cli.run_server bigscience/bloom-petals
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bos_token_id": 1,
+  "dht_prefix": "bigscience/bloom-petals",
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 14336,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 112,
+  "n_layer": 70,
+  "pad_token_id": 3,
+  "pretraining_tp": 4,
+  "slow_but_exact": false,
+  "transformers_version": "4.21.0.dev0",
+  "torch_dtype": "bfloat16",
+  "use_cache": true,
+  "vocab_size": 250880
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62847c8302767493f72ec684c4a7bfe6d21247c163bea70e82ef8e5c209e0a2
+size 7193348019

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
+size 14500443

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "name_or_path": "bigscience/bloom",
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}