moving model weights to ibm-granite org

README.md

@@ -1,3 +1,166 @@
----
-license: apache-2.0
----
+---
+license: llama2
+---
+
+## Installation from source
+
+```bash
+git clone https://github.com/foundation-model-stack/fms-extras
+cd fms-extras
+pip install -e .
+```
+
+
+## Description
+
+This model is intended to be used as an accelerator for [granite 7B (instruct lab)](https://huggingface.co/instructlab/granite-7b-lab) and takes inspiration 
+from the Medusa speculative decoding architecture. This accelerator modifies the MLP into a multi-stage MLP, where each stage predicts 
+a single token in the draft based on both a state vector and sampled token
+from the prior stage (the base model can be considered stage 0).
+The state vector from the base model provides contextual information to the accelerator, 
+while conditioning on prior sampled tokens allows it to produce higher-quality draft n-grams.
+
+Note: The underlying MLP speculator is a generic architecture that can be trained with any generative model to accelerate inference. 
+Training is light-weight and can be completed in only a few days depending on base model size and speed.
+
+## Repository Links
+
+1. [Paged Attention KV-Cache / Speculator](https://github.com/foundation-model-stack/fms-extras)
+2. [Production Server with speculative decoding](https://github.com/IBM/text-generation-inference.git)
+3. [Speculator training](https://github.com/foundation-model-stack/fms-fsdp/pull/35)
+
+## Samples
+
+_Note: For all samples, your environment must have access to cuda_
+
+### Production Server Sample
+
+*To try this out running in a production-like environment, please use the pre-built docker image:*
+
+#### Setup
+
+```bash
+HF_HUB_CACHE=/hf_hub_cache
+chmod a+w $HF_HUB_CACHE
+HF_HUB_TOKEN="your huggingface hub token"
+TGIS_IMAGE=quay.io/wxpe/text-gen-server:main.ee927a4
+
+docker pull $TGIS_IMAGE
+
+# optionally download granite-7b-lab if the weights do not already exist
+docker run --rm \
+    -v $HF_HUB_CACHE:/models \
+    -e HF_HUB_CACHE=/models \
+    -e TRANSFORMERS_CACHE=/models \
+    $TGIS_IMAGE \
+    text-generation-server download-weights \
+    instructlab/granite-7b-lab \
+    --token $HF_HUB_TOKEN
+
+# optionally download the speculator model if the weights do not already exist
+docker run --rm \
+    -v $HF_HUB_CACHE:/models \
+    -e HF_HUB_CACHE=/models \
+    -e TRANSFORMERS_CACHE=/models \
+    $TGIS_IMAGE \
+    text-generation-server download-weights \
+    ibm/granite-7b-lab-accelerator \
+    --token $HF_HUB_TOKEN
+
+# note: if the weights were downloaded separately (not with the above commands), please place them in the HF_HUB_CACHE directory and refer to them with /models/<model_name>
+docker run -d --rm --gpus all \
+    --name my-tgis-server \
+    -p 8033:8033 \
+    -v $HF_HUB_CACHE:/models \
+    -e HF_HUB_CACHE=/models \
+    -e TRANSFORMERS_CACHE=/models \
+    -e MODEL_NAME=instructlab/granite-7b-lab \
+    -e SPECULATOR_NAME=ibm/granite-7b-lab-accelerator \
+    -e FLASH_ATTENTION=true \
+    -e PAGED_ATTENTION=true \
+    -e DTYPE=float16 \
+    $TGIS_IMAGE
+
+# check logs and wait for "gRPC server started on port 8033" and "HTTP server started on port 3000"
+docker logs my-tgis-server -f
+
+# get the client sample (Note: The first prompt will take longer as there is a warmup time)
+conda create -n tgis-client-env python=3.11
+conda activate tgis-client-env
+git clone --branch main --single-branch https://github.com/IBM/text-generation-inference.git
+cd text-generation-inference/integration_tests
+make gen-client
+pip install . --no-cache-dir
+```
+
+#### Run Sample
+
+```bash
+python sample_client.py
+```
+
+_Note: first prompt may be slower as there is a slight warmup time_
+
+### Minimal Sample
+
+*To try this out with the fms-native compiled model, please execute the following:*
+
+#### Install
+
+```bash
+git clone --branch ibm_7b_instruct_lab_variant --single-branch https://github.com/JRosenkranz/fms-extras.git
+(cd fms-extras && pip install -e .)
+pip install transformers==4.35.0 sentencepiece numpy
+```
+
+#### Run Sample
+
+##### batch_size=1 (compile + cudagraphs)
+
+```bash
+MODEL_PATH=/path/to/instructlab/granite-7b-lab
+python fms-extras/scripts/paged_speculative_inference.py \
+    --variant=7b.ibm_instruct_lab \
+    --model_path=$MODEL_PATH \
+    --model_source=hf \
+    --tokenizer=$MODEL_PATH \
+    --speculator_path=ibm/granite-7b-lab-accelerator \
+    --speculator_source=hf \
+    --speculator_variant=1_4b \
+    --top_k_tokens_per_head=4,3,2,2,2 \
+    --compile \
+    --compile_mode=reduce-overhead
+```
+
+##### batch_size=1 (compile)
+
+```bash
+MODEL_PATH=/path/to/instructlab/granite-7b-lab
+python fms-extras/scripts/paged_speculative_inference.py \
+    --variant=7b.ibm_instruct_lab \
+    --model_path=$MODEL_PATH \
+    --model_source=hf \
+    --tokenizer=$MODEL_PATH \
+    --speculator_path=ibm/granite-7b-lab-accelerator \
+    --speculator_source=hf \
+    --speculator_variant=1_4b \
+    --top_k_tokens_per_head=4,3,2,2,2 \
+    --compile \
+```
+
+##### batch_size=4 (compile)
+
+```bash
+MODEL_PATH=/path/to/instructlab/granite-7b-lab
+python fms-extras/scripts/paged_speculative_inference.py \
+    --variant=7b.ibm_instruct_lab \
+    --model_path=$MODEL_PATH \
+    --model_source=hf \
+    --tokenizer=$MODEL_PATH \
+    --speculator_path=ibm/granite-7b-lab-accelerator \
+    --speculator_source=hf \
+    --speculator_variant=1_4b \
+    --top_k_tokens_per_head=4,3,2,2,2 \
+    --batch_input \
+    --compile \
+```

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<|assistant|>": 32003,
+  "<|endoftext|>": 32000,
+  "<|pad|>": 32001,
+  "<|system|>": 32004,
+  "<|user|>": 32002
+}

config.json

@@ -0,0 +1,20 @@
+{
+  "architectures": [
+    "MLPSpeculatorPreTrainedModel"
+  ],
+  "emb_dim": 4096,
+  "inner_dim": 4096,
+  "model_type": "mlp_speculator",
+  "n_candidates": 5,
+  "n_predict": 5,
+  "top_k_tokens_per_head": [
+    4,
+    3,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "vocab_size": 32008
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f0815eb53a3cee5448c4a46edf38e23f09f42d939420eabbc7ac27384c93ca
+size 2789951944

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,86 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>'+ '\n' + message['content'] + '\n'}}{% elif message['role'] == 'user' %}{{'<|user|>' + '\n' + message['content'] + '\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>' + '\n' + message['content'] + '<|endoftext|>' + ('' if loop.last else '\n')}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "fast_tokenizer": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}