Upload quantized model versions of Photolens/llama-2-7b-langchain-chat

.gitattributes

@@ -33,3 +33,7 @@ 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
+llama-2-7b-langchain-chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-2-7b-langchain-chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-2-7b-langchain-chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+llama-2-7b-langchain-chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,76 @@
+---
+language:
+- en
+- es
+- ru
+- de
+- pl
+- th
+- vi
+- sv
+- bn
+- da
+- he
+- it
+- fa
+- sk
+- id
+- nb
+- el
+- nl
+- hu
+- eu
+- zh
+- eo
+- ja
+- ca
+- cs
+- bg
+- fi
+- pt
+- tr
+- ro
+- ar
+- uk
+- gl
+- fr
+- ko
+task_categories:
+- conversational
+license: llama2
+datasets:
+- Photolens/oasst1-langchain-llama-2-formatted
+---
+
+## Model Overview
+Model license: Llama-2<br>
+This model is trained based on [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) model that is QLoRA finetuned on [Photolens/oasst1-langchain-llama-2-formatted](https://huggingface.co/datasets/Photolens/oasst1-langchain-llama-2-formatted) dataset.<br>
+
+## Prompt Template: Llama-2
+```
+<s>[INST] Prompter Message [/INST] Assistant Message </s>
+```
+
+## Intended Use
+Dataset that is used to finetune base model is optimized for langchain applications.<br>
+So this model is intended for a langchain LLM.
+
+## Training Details
+This model took `1:14:16` to train in QLoRA on a single `A100 40gb` GPU.<br>
+ - *epochs*:  `1`
+ - *train batch size*:  `8`
+ - *eval batch size*:  `8`
+ - *gradient accumulation steps*:  `1`
+ - *maximum gradient normal*:  `0.3`
+ - *learning rate*:  `2e-4`
+ - *weight decay*:  `0.001`
+ - *optimizer*:  `paged_adamw_32bit`
+ - *learning rate schedule*:  `cosine`
+ - *warmup ratio (linear)*:  `0.03`
+
+## Models in this series
+| Model | Train time | Size (in params) | Base Model |
+---|---|---|---
+| [llama-2-7b-langchain-chat](https://huggingface.co/Photolens/llama-2-7b-langchain-chat/) | 1:14:16 | 7 billion | [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) |
+| [llama-2-13b-langchain-chat](https://huggingface.co/Photolens/llama-2-13b-langchain-chat/) | 2:50:27 | 13 billion | [TheBloke/Llama-2-13B-Chat-fp16](https://huggingface.co/TheBloke/Llama-2-13B-Chat-fp16) |
+| [Photolens/OpenOrcaxOpenChat-2-13b-langchain-chat](https://huggingface.co/Photolens/OpenOrcaxOpenChat-2-13b-langchain-chat/) | 2:56:54 | 13 billion | [Open-Orca/OpenOrcaxOpenChat-Preview2-13B](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B) |

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

llama-2-7b-langchain-chat-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750e96efc7b6220462eabd02938ba1410c991773896acca1317e6da51b623a3e
+size 4081004224

llama-2-7b-langchain-chat-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c1c6129bccc237cdb85b065a25b8826f96464c94946a4f28a11313f10f0362
+size 4783156928

llama-2-7b-langchain-chat-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a625393ec6f72b60c3c0c7cd7db547b875c9becb6a8d43288036c73f8c4f7b7
+size 5529194176

llama-2-7b-langchain-chat-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c321bc9173ded1e14d5a4139f524c4f809eb06c9c5ebe68a8dfd4deb43dc27
+size 7161089728